Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add skills/workast/mcp/add-mcp-methodnpx skills add workast/mcp --skill add-mcp-methodgit clone --depth 1 https://github.com/workast/mcpWhat it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00079 | $0.01742 |
| Opus 5 | $0.00039 | $0.00871 |
| Sonnet 5 | $0.00016 | $0.00348 |
| Haiku 4.5 | $0.00008 | $0.00174 |
Grade A, and why
add-mcp-method scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 112 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Add an MCP tool
Copy a nearby tool (for example src/tools/create-tasks.ts and test/tools/create-tasks.test.ts). One SDK method → one tool file + one test file. Explicit import in src/create-handler.ts — no auto-registry. Auth stays in src/auth/verify-api-key.ts; tools only read ctx.http?.authInfo?.token. Types and examples come from @workast/sdk / @workast/sdk/mock. Do not add OAuth, retries, or extra abstraction layers.
Canonical example: workast_create_tasks → workast.tasks.create(spaceId, body) via createWorkast in src/workast.ts. Tool args use UI names (spaceId, reportId); SDK paths stay /list, /search. Tool names always use the workast_ prefix.
Layout
| Piece | Path |
|---|---|
| Tool | src/tools/<tool-name>.ts |
| Test | test/tools/<tool-name>.test.ts |
| Register | src/create-handler.ts (call the register fn next to the other register* calls) |
| Route | app/mcp/route.ts — already mounts createHandler(); do not register tools here |
| Client | src/workast.ts — createWorkast(apiKey) |
| Auth | src/auth/verify-api-key.ts — do not change for a new tool |
| Run | src/run-tool.ts — runWorkast(token, fn) (missing token + ApiError) |
| Helpers | test/helpers.ts — setupWorkastMock, callTool, expectToolData, mcpRequest |
Tool name is the MCP name with a workast_ prefix: workast_list_spaces, workast_create_tasks, workast_retrieve_report. File slug uses hyphens: list-spaces.ts. Register fn is register + PascalCase tool: registerListSpaces. Every new tool must set title and annotations: readOnlyHint, destructiveHint, idempotentHint as appropriate, and openWorldHint: false.
1. Resolve the SDK method
In @workast/sdk (or the SDK skill / swagger Public operation), record: resource method, path ids, body/query type, success type. If the SDK method does not exist yet, add it in the SDK repo first — this MCP skill only wraps shipped SDK methods.
Map UI ids to SDK ids in the handler only: spaceId → list id, reportId → search id. Do not expose listId in the tool schema.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 2d ago First seen · 112 lines · 79 tokens per session scan A 42555aa6d559
add-mcp-method is a skill published in the GitHub repository workast/mcp (0 stars, last pushed 3d ago), licensed MIT. It adds 79 tokens to every session and 1,742 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
brainstorming
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
auto-perf-optimize
Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.
chat-perf
Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…