WorkerKitFor Claude
AI workers for Claude.
Claude is the assistant you think with. WorkerKit gives it a fleet of specialists: background AI workers with their own instruction, memory, schedule, budget and pre-scoped app access, hosted around the clock and reporting back in short, costed digests. Long jobs stay out of the conversation, each worker gets its own narrow grant, and every run comes back with its settled cost. Setup takes about a minute of your time.
Start here
Add WorkerKit to Claude.
For claude.ai, Claude Desktop and Cowork. The button opens Claude's Add custom connector dialog with WorkerKit filled in. Sign in and approve access.
- 01
Add WorkerKit
Press Add WorkerKit to Claude, confirm, then sign in. A WorkerKit account admin approves the access Claude receives.
- 02
Ask Claude to check it
Paste the prompt into a new chat. Claude reads what its key allows and lists your workers, or suggests a first one.
- Paste into a new Claude chat
Use my WorkerKit connection. Read https://workerkit.ai/claude/SKILL.md and follow its operating rules whenever you work with my workers. Call key_info and tell me which account and scopes you have. List my workers and recent runs. If there are none, ask what job I want done and suggest a ready-made kit for it. Ask me before you run, install or change anything.
- Add WorkerKit to Claude Your workers, behind a WorkerKit sign-in and approval.
On Team and Enterprise an Owner adds WorkerKit for everyone, and each member then connects. In Claude Code, the setup guide has the command.
Claude Duet uses this connection too. Check access in Duet.
Why WorkerKit
Control your AI workforce from Claude.
Ready-made, self-learning AI workers with only the access each job needs, a budget you set, and a record of every job and action.
- Put AI workers on jobs with real ROI. Install a kit for work your team already repeats, and a worker arrives with its instructions, app permissions and schedule already written and reviewed. Start with the job that costs the most time, or build your own kit.
- Turn your AI workers’ jobs and data into shared company knowledge. Each job’s instructions, apps and limits live in one kit your team keeps current, and workers that use the Records app keep what they find in shared tables and lists your team can open. Your team and every connected assistant work from the same process.
- Choose what each AI worker can access. Each worker holds its own grant for each app, read-only by default, and nothing it reads can widen it. An assistant's key carries only the scopes you choose and never an app credential.
- Track what your AI workers did and what they changed. Every run leaves a receipt with its result and its cost, and every tool call is logged with its outcome, so you can see what each worker did, when, and at what price.
- Keep AI spending within the limits you set. Each worker has a per-run and a daily spending limit, under a limit for the whole account. When one is reached, new runs stop before any money moves, and the receipt says why.
- Your AI workers learn as they work and keep getting better. A language worker can check every run against its job's quality criteria. A change that makes it better waits for your approval or, in Apply proven changes mode, applies on its own once it passes a comparison on your own examples. Its runs also propose what it should remember, and you approve what it keeps.
What Claude is
The assistant that wrote the protocol.
Claude is Anthropic's assistant, and it reaches the same person through several surfaces: the web app, the desktop and mobile apps, Cowork, and Claude Code in a terminal. It extends itself through connectors, which are MCP servers, and through skills, which are folders of instructions it loads when they are relevant. Anthropic created the Model Context Protocol, so a hosted tool surface is not a bolt-on here: it is the native way Claude reaches anything that is not itself.
| What a fleet adds | Why it helps |
|---|---|
| Room in the conversation | Machine output lands in a digest instead of the thread, so the reasoning you came for stays in front of you. |
| A session per job | Each job gets its own context and its own model, chosen for that job rather than inherited from the chat. |
| A grant per job | App access is wired once, per worker, so Claude orchestrates the work without every integration hanging off one connector list. |
| Work that outlives the window | A hosted worker keeps its schedule whether or not Claude is open, which no conversation and no connector can do on its own. |
Claude is already excellent at the work you watch it do, and that is where it should stay. A fleet beside it takes the standing jobs: the ones that should keep running when the window is closed, hold their own app access, and report a paragraph rather than a screen.
Hired specialists
What a worker adds beside Claude.
An AI worker is a background agent with its own instruction, memory, triggers, budget, model, app permissions and key. WorkerKit hosts the runs, so Claude never has to hold a window open for them.
| Aspect | Claude | A WorkerKit worker |
|---|---|---|
| Context | One conversation, plus the projects and skills you keep | Its own, sealed per run; only the digest returns |
| Model | The Claude model behind this conversation | Chosen per worker from any supported provider, or your own provider key |
| Identity | The connectors you have added and approved | Its own, holding only the apps, tools and permissions its job needs |
| When it runs | While you are there | Hosted around the clock: on demand, on a schedule in its own time zone, or on a signed inbound webhook |
| What comes back | The work itself, in the conversation | A closing report of at most 8,000 characters, a typed digest beside it, and the settled cost |
| Memory | Project knowledge and the memory you curate | The worker's own rules and facts, carried across runs, and approved by you before a run may use them |
| Taking it back | Remove a connector or turn a skill off | Disable or revoke one worker; nothing else moves |
The operator pattern
Claude operates. Workers work.
| Step | Who | What happens |
|---|---|---|
| 1 | You | Ask in plain language. "Which workers ran today?", "Run the invoice chase now", "Pause the scanner." |
| 2 | Claude | Reads its key's scopes first with key_info, picks the matching MCP tool, and follows the operating rules in its WorkerKit skill. |
| 3 | The worker | Executes in its own context, on its own runtime, on its schedule or on demand. |
| 4 | Both | Claude reads the result with runs_feed and run_get: one connection covers the whole fleet, and the run's receipt carries the digest, the typed structure when the run produced one, and the settled cost. People receive it through the worker's delivery channels. |
Claude becomes the fleet operator. The workers do the unattended work, Claude does the thinking about it, and the interactive work workers are not for stays exactly where it is.
Why Claude and WorkerKit
Each one covers what the other is not for.
Use Claude for the work you want to watch and steer. Use a WorkerKit worker for run unattended against my apps, on a schedule, with its own grant, and deliver to Slack.
| Claude strength | What WorkerKit adds beside it |
|---|---|
| Native MCP, on every surface | WorkerKit connects over streamable HTTP with fleet operations and kit discovery |
| Skills that teach it your way of working | A skill file of our own, so the fleet arrives with its operating rules already written |
| Deep, careful reasoning in the moment | Sealed specialists that hand back digests, so a long job costs a paragraph of conversation rather than a screen of it |
| Claude Code, for work with a repository in reach | Hosted runs that keep going after the terminal is closed, with a receipt for every one |
| Projects that hold context for a body of work | Workers that hold context for a JOB, across runs, with memory you approve before it is used |
What it unlocks
Background work that stays out of the chat.
Each run executes sealed inside its own context, settles its exact cost and returns a digest. The worker remembers its own state. Your conversation stays clean.
- Sealed jobs, small returns Every job runs in its own context and only the digest comes back. A long crawl becomes the few paragraphs that matter, so many workers fit in one conversation.
- The right model per job Inexpensive models scan, frontier models judge. Every run is priced to the token, with reserved-versus-settled tracking, so background work is never a black box on your bill.
- Money you can trust A run that never started costs nothing. A run that went silent mid-flight is absorbed by WorkerKit and labelled as an unbilled estimate. A failed run settles at actual usage with no minimum charge.
- Standing monitors and briefings Workers watch on a schedule and report only what is new, so you stop relying on remembering to ask.
- Two-way work A run that needs input does not guess or stall. It asks on every delivery channel and resumes as a linked follow-on run when you answer.
- Memory that compounds Rules and facts persist across runs, so the tenth run is smarter than the first. Anything a run proposes for memory waits for your approval before a future run may use it.
- Kits: install one or make your own Browse the catalog, install a ready-made worker, or author your own through the authoring guide, the validator and the publisher. Every path runs the same validators.
- Fleet operations Clone a tuned worker for the next client, set budgets, route deliveries, and start and stop workers, all from the assistant you already talk to.
- Delivery where people live Results land in email, Slack, Teams, Telegram, Discord, Notion, or SMS and WhatsApp, where their readers already are, instead of waiting in a chat nobody opens.
- Auditable trails Every run leaves a typed event stream, liveness heartbeats, owner and self scores, and the allow or redact outcome of each tool call underneath it.
MCP connections
WorkerKit for your fleet. Knowledge for your reports.
Use WorkerKit to discover kits, build workers and manage your fleet. Add Knowledge to search published worker reports. Both use the same sign-in or key.
| Mount | Address | What it carries |
|---|---|---|
| WorkerKit (default) | https://mcp.workerkit.ai/workers | Discover and install kits, build workers, and run and manage your fleet. Choose the full profile or a focused decision profile. Connect with OAuth or a bearer key. |
| Knowledge | https://mcp.workerkit.ai/knowledge | Company Knowledge: 6 tools to search and read published worker reports and track changes. Admins manage publication and reader access. Uses the same sign-in or key. |
| Area | Tools | What it covers |
|---|---|---|
| Continuous Learning | worker_quality_get, worker_quality_set, worker_quality_preview | Read criteria, three gates and availability reasons; save reviewed settings with expectedRevision; preview samples without a run. The worker dashboard offers owner-reviewed activation and a quoted AI draft when criteria are missing. Paid comparisons, diagnosis, monitoring, apply/rollback and company/shadow learning stay owner-only. Manager keys can disable any gate, but cannot enable automatic/shared learning. Kit install leaves all gates off. |
| Key | key_info | What your key is and exactly which scopes the other tools will honour. Call it first. |
| Fleet | workers_list, worker_get, worker_set_enabled | Every worker with live run state, one worker in full, and start or stop. |
| Apps and workers | worker_permissions_get, worker_permissions_set, worker_bindings_get, worker_bindings_set | What a worker may touch, in the same vocabulary a kit is written in, and its grants to call other workers: read both, replace its app set (account Admin) and fill, re-point or clear its worker grants. The writes need manageAppsAndWorkers; rules, identities and MCP tool bindings stay in the dashboard. |
| Runs | worker_run, run_bulk, worker_runs, run_get, run_events, run_transcript, run_cancel, run_score, run_clear_digest | Trigger a run with a prompt for that run, or one prompt across up to 20 workers; watch it step by step, read the receipt and the stored process log, cancel or grade it. On a decision worker it decides instead and acts on what it routes: sourceArgs and maxItems narrow and cap what is judged, and waitSeconds waits for the settled receipt, which carries the per-item decisions. |
| Fleet activity | runs_feed, fleet_pulse, fleet_health, account_usage, activity_feed, activity_summary, account_spend | Worker runs, app calls and configuration changes, activity counts, everything running now, fleet health, account headroom and spend by worker, day and model. |
| Two-way runs | run_question, run_answer | A run that needs an answer ends by asking; the answer starts a linked follow-on run. |
| Memory | memory_get, memory_add, memory_update, memory_delete | The rules and facts a worker carries into every run. |
| Schedules | schedules_list, schedule_create, schedule_update, schedule_delete, worker_timezone_set | When a worker starts on its own, and the time zone it works in: its local dates, its report times and the clock its daily schedules follow. |
| Instruction | instruction_get, instruction_set, instruction_versions, instruction_version_get, instruction_restore | The standing instruction, versioned on every change, with the history to compare against and roll back to. On a decision worker it reads the routing table and the install questions instead, and writes their answers. |
| Deliveries | delivery_list, delivery_channels, delivery_create, delivery_update, delivery_secret_rotate, delivery_delete | Where a run report goes when the worker finishes: email, Slack, Teams, Telegram, Notion, Discord, SMS or a signed webhook. |
| Deployment | models_list, deployments_list, deployment_get, worker_deploy, deployment_update, worker_undeploy | What makes an installed worker actually run: pick its model from the priced catalog, cap its spend, pause or resume it, take it off again. A worker with no deployment fires no schedule and refuses a run with not_deployed. |
| Budgets | budget_get, budget_set, fleet_budget_get, fleet_budget_set | A worker’s spend and run ceilings, and the account-wide fleet ceiling. Their own scope, because raising a dollar cap is the one management action that can cost money. |
| Creation | worker_clone_preview, worker_clone, worker_clone_bulk | Clone a worker into new ones, singly or in bulk, with a dry run first. A clone carries only permissions a person already approved on the source. |
| Deletion | worker_delete | Remove a worker for good, with its sub-workers. Permanent, where stopping one is not — which is why it is a scope of its own. |
| Kits | kit_install_preview, kit_install | Preview a directory kit against your account, then install it as a new worker — with deploy set, in the same call, which is what makes it run. |
| Kit authoring | kit_validate, kit_publish, kit_update, kit_replace, kit_unpublish, kit_relist, kit_make_private, kit_delete, kit_scan_get, my_kits_list, publisher_get_mine, publisher_set | Validate a kit in one dry run that reports every gate at once, publish it from content or from a worker you own, keep it private or list it, and keep your publisher profile. A private kit installed with kit_install is how an agent builds a worker from scratch. |
| Connected apps | apps_list, app_connect, app_disconnect, app_github_accounts, app_github_repos, app_github_branches, app_slack_workspaces, app_slack_conversations | Which apps an operator can use right now, in the kit vocabulary, and connecting the rest by credential: validated live, stored encrypted, never returned. Browser sign-ins stay on the Apps page. The GitHub and Slack lookups find repository and channel IDs for an install (discoverAppResources). |
| Model keys | model_keys_list, model_key_set, model_key_delete | Your own model-provider API keys, so runs bill your provider account instead of the wallet. |
| Onboarding and wallet | onboarding_get, wallet_get, wallet_checkout_create, wallet_checkout_get | Check model funding, hand off BYOK setup, inspect wallet balance, and request a human-confirmed Stripe checkout. A purchase is complete only when its status is credited. |
| Custom MCP servers | mcp_servers_list, mcp_server_get, mcp_server_create, mcp_server_discover, mcp_server_set_tools, mcp_server_delete | An app the platform does not offer, reached through its MCP server: register it as your own custom MCP app with its credential in the same call, enable the tools a job needs, and bind it in a kit. |
| API apps | api_apps_list, api_app_get, api_app_create, api_app_update, api_app_validate, api_app_preview, api_app_publish, api_app_version_get, api_app_version_revoke | Account-private API apps: validate and preview a definition offline, create and update drafts, publish immutable versions and revoke them. Authoring needs a live account Admin and managePrivateApiApps; connections and worker bindings are configured in the dashboard. |
| Decision authoring | decision_worker_create, worker_decision_set | Compile typed questions and a supported source recipe into a private kit and installed decision worker. Optional deploy; never starts a run. Requires createWorkers, plus manageDeployments when deploying. Retry the same requestId and body to recover the receipt. worker_decision_set attaches, replaces or removes a hybrid worker's classifier. |
| Action workers | action_worker_options, action_worker_create, worker_tools, worker_tool_call, worker_tool_invocation | Selected app tools with no model, called one at a time with exact inputs. Create with createWorkers; call and read receipts with invokeActions. A write needs an idempotencyKey; never resend an outcome_unknown call. |
| Support | support_request_create | Contact support about an error you cannot fix, a bug, an app request or a question. Returns a PE-XXXXXX reference. |
| Discovery and authoring reads | workerkit_about, directory_overview, kits_search, kit_get, kit_app_tools, kit_authoring_guide, kit_vocabulary | Public reads also available on the workers connection. Discover classification sources with kit_app_tools(purpose:"decision") and read kit_authoring_guide(section:"decision"). These reads never forward the manager bearer upstream. |
| Company Knowledge | knowledge_sources, knowledge_search, knowledge_get, knowledge_changes, knowledge_configuration_get, knowledge_configuration_set | On the separate mcp.workerkit.ai/knowledge mount, with the same key: discover, search and read published worker reports, reconcile changes, and configure sharing as an admin. Access follows publication and reader grants. |
The manager key holds no app credentials: workers reach apps under their own grants and firewall, and no prompt can widen that. With readRuns or invokeActions the key can read what those workers return, including an Action worker's tool results.
Your fleet is also available from other MCP clients and the REST API.
Classification on demand
Create a decision worker from your questions.
Categorize, score or triage connected data, then reuse and adjust the worker.
Reuse an existing worker or decision kit when its questions fit. For a custom classification task, creation compiles a supported source recipe and typed questions into a private kit and an installed decision worker. Optional deploy:true adds deployment; creation never starts a run or adds a schedule. The kit can be edited and published later through the normal kit lifecycle.
On the workers connection, call kit_app_tools(purpose:"decision") for recipes, argument schemas, permissions and examples, then kit_authoring_guide(section:"decision"). Check account connections with apps_list; public discovery does not check them. Send the request to decision_worker_create, follow nextCall, then use worker_run and run_get. Running needs runWorkers; results need readRuns. Use instruction_get / instruction_set for saved category or level answers, or answers on one run. Structural question/source changes need a revised kit and a replacement install. Check receipt status, coverage, omissions, warnings and cost before claiming completion.
Start with email-previews, calendar-events or sheets-rows. These recipes return judgments without app writes. Email previews do not include full threads; calendar events are invitation data, not transcripts; Sheets needs a Google file ID, a finite tab-qualified range and a columns map. A connected app alone does not make every tool a supported source. Source filters select evidence, not permissions: the Sheets recipe grants spreadsheet reads across the linked Drive account.
Supply 1–8 questions: choice with named options, score with ordered levels, or noul for the probability of a statement. Choice adds unclear automatically. Set an explicit confidenceFloor between 0 and 1; it routes uncertainty and does not promise accuracy. maxItems is 1–50, default 20. Creation requires createWorkers; optional deployment also needs manageDeployments.
Use a fresh requestId for each new worker. Retry with the same ID and identical body to recover the original receipt; a changed body returns 409. The response includes tokenId for MCP/CLI worker commands, stable workerId, kitSlug, readiness and nextCall. A deploymentError means the worker already exists: fix deployment on that worker. The receipt is a snapshot; check current worker readiness before running. No worker API secret is returned.
The workers connection includes discovery and authoring, so classification needs one MCP connection. Its full profile includes fleet management, app resource discovery, kit authoring and public directory reads. For a smaller list, a client that supports custom headers can send X-WorkerKit-Profile: decision on every request, including initialization, listing and calls, to select the smaller workflow tool set. A server operator can instead set MCP_WORKERS_PROFILE=decision. The endpoint and existing sign-in stay the same; a profile grants no additional permissions. Reconnect and relist after changing profiles. Use the advertised tool list: fleet administration, publishing, Action worker and event-stream tools require the full profile. Successful responses include structured content and a text fallback; creation declares an output schema.
App tools, no model
Call app tools through an Action worker.
One exact app operation per call, with the inputs you supply.
An Action worker (modelType: "none") exposes 1 to 64 selected app tools and has no model, instruction, schedule or deployment. Each call invokes one tool with the arguments the caller sends, under the worker's own app access, and readiness.canInvoke on worker_get says whether its tools can be called now. Run and deploy requests answer 400 action_worker_requires_invoke.
On the workers connection's full profile: action_worker_options lists apps with no tools selected; pass an explicit app for schemas and defaults (readWorkers). action_worker_create requires an explicit app or actionSpec and copies the selected app's default tools, or takes an actionSpec of 1 to 64, plus a slackConnectionId for Slack tools when the account has more than one Slack bot (createWorkers); worker_tools lists the saved tools (readWorkers); worker_tool_call calls one with arguments, plus an idempotencyKey on a write (invokeActions); worker_tool_invocation reads a write's receipt (invokeActions). Pass the returned tokenId. kits_search(modelType:"none") finds Action kits; install one with kit_install and no deploy.
An explicit actionSpec needs no app and can span native or reviewed MCP apps. Private API tools require a dashboard binding to a published version; they are not actionSpec refs.
A write tool (readOnly: false) needs an idempotency key. Repeating the key with the same arguments returns the stored receipt (a confirmation, not the app's response) without calling the app again; with other arguments it is a 409. A call answers with status succeeded, denied, failed, in_progress or outcome_unknown; branch on it, not on the HTTP code. On outcome_unknown the write may have happened: never resend it automatically, under any key; read the receipt and check the app. Each call counts toward the worker's daily request limit; a refusal marked retryable, such as usage_limit, is retried later under a new key. Only the owner changes the selected tools, in the dashboard.
Access and control
Scoped per worker, and scoped for Claude too.
| Layer | What it holds |
|---|---|
| Per-worker grant | You connect each account yourself and choose what the worker may do there: per-app operations, read-only by default, narrowed by rules such as contact blocks, label and folder rules, customer-domain limits, time windows and IP allowlists. An account-level ceiling caps what any worker can be granted. |
| The app firewall | Every tool call is checked against the grant and the rules, field-masked, scanned for sensitive data, redacted, rate-limited and logged with its outcome. The worker's model never sees what the rules removed. |
| Prompt injection | A worker steered by content it reads still cannot exceed its grant. Proposed memory waits for a human. Publishing a kit to the directory runs a supply-chain and prompt-safety scan that fails closed. |
| The assistant's own access | A manager key carries explicit scopes, is shown once and stored hashed. No scope gives it app credentials, but invokeActions returns an Action worker's tool results, so grant it only where an agent should call those tools. An agent reads its scopes before planning, and an admin can revoke the key at any time without touching a worker. |
A worker is only as trustworthy as the access behind it, so the access is yours to give, to narrow and to take back, one worker at a time. You delegate without handing over the kingdom.
How it connects
Connect WorkerKit to Claude.
Add the WorkerKit URL as a custom connector. Claude opens the WorkerKit consent page, where an account admin approves access. OAuth handles the credential; no key goes into chat.
Claude Code can do the same, or take a key directly on an Authorization header, which is the better fit for a terminal and for a key kept in an environment variable.
The whole procedure, written for the agent doing it, is the setup guide. The human's part is two steps and about a minute.
The same fleet answers from anywhere else you work: any other MCP client, the wk CLI in a terminal, and the REST API for hosts that speak plain HTTPS. The fleet outlives the choice of assistant.
Cost: WorkerKit has a Free plan with no card required. Runs bill model tokens at the provider list price with no markup, from a prepaid wallet or your own provider key, inside the budgets you set. Connecting Claude is not a paid feature, and the plans are on the pricing page.
Questions
Claude and WorkerKit, answered.
- Does Claude connect to WorkerKit over MCP? Yes. Start with WorkerKit at https://mcp.workerkit.ai/workers for fleet operations and kit discovery. Company Knowledge is optional at https://mcp.workerkit.ai/knowledge for published worker reports. Both support OAuth or a bearer key.
- Which Claude surface should I set this up on? claude.ai, Claude Desktop and Cowork add WorkerKit by URL and authorize through OAuth. Claude Code also accepts a manager key through --header. On Team and Enterprise, an Owner adds organization connectors.
- Do I have to paste a key into Claude? On the hosted surfaces, no. The fleet mount publishes OAuth discovery and accepts dynamic client registration, so Claude registers itself and sends you to workerkit.ai/mcpauth to approve; the key is chosen there, by an account admin, and never passes through a message. Pasting a key on a header is the alternative, and it is what Claude Code offers for a terminal-shaped setup.
- Can Claude read my email or CRM through WorkerKit? Only through workers you set up. The manager key Claude holds operates workers and has no app credentials, but run results (with readRuns) and an Action worker's tool results (with invokeActions) can include data from the apps that worker was granted. Choose the worker's app access and the key's scopes together; no prompt can widen either.
- What does Claude need to set this up? A WorkerKit account admin to approve access. OAuth needs no key created in advance. For a bearer connection in Claude Code, create a key at workerkit.ai/fleet-access. The setup guide covers access checks, the skill and a smoke test.
- My connector says it cannot reach the server. What now? Hosted Claude connects from Anthropic infrastructure; Claude Code connects from your device. Recheck the WorkerKit URL and authorization. Anthropic also documents IPv4 reachability, outbound IP allowlists and Authorization headers being dropped on cross-host redirects as causes of hosted connection failures.
- How does Claude get a worker's results? Two paths. Claude reads them with runs_feed and run_get: one connection watches every worker on the account, and each run's receipt carries the closing report, a typed digest when the run produced one, and the settled cost. People receive them through the worker's delivery channels: email, Slack, Teams, Telegram, Discord, Notion, SMS and WhatsApp, or a signed webhook.
- I connected it and the fleet is empty. What now? That is the expected state of a new account, and the connection is already proved. Install a kit to get the first worker: open any kit at workerkit.ai/kits and install it in one click, which needs no scope on the key at all, or, with installKits on the key, let Claude shortlist with kits_search, preview exactly what the new worker would be allowed to touch with kit_install_preview, and install it with kit_install once you approve. Then ask Claude to run it and read you the receipt.
- What does it cost? WorkerKit has a Free plan with no card required: 5 workers, 500 tool calls a day and the complete safety layer. Runs bill model tokens at the provider list price with no markup, from a prepaid wallet or your own provider key, inside the per-worker and fleet budgets you set. Connecting Claude is not a paid feature.
The setup guide is written for the agent doing the work, the MCP server page holds the surface behind it, and the wk CLI reaches the same fleet from a terminal.
To build a kit of your own, how to build a kit walks the procedure, and the kit-authoring skill is the file an agent keeps for it.