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/nulab/backlog-mcp-server/implement-backlog-api-toolnpx skills add nulab/backlog-mcp-server --skill implement-backlog-api-toolgit clone --depth 1 https://github.com/nulab/backlog-mcp-serverWhat 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 | $0.00067 | $0.00501 |
| Opus 5 | $0.00034 | $0.00251 |
| Sonnet 5 | $0.00013 | $0.00100 |
| Haiku 4.5 | $0.00007 | $0.00050 |
Grade A, and why
implement-backlog-api-tool 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.
Copies of this mod
1 near-identical copy found in the catalogue:
- implement-backlog-api-tool — 100% identical, 0 lines differ
What it actually says
Implement a Backlog API Tool
Overview
Implement a new MCP tool for the Backlog API endpoint documented at $ARGUMENTS.
Steps
1. Read the API spec
Fetch the documentation page using the fetch_webpage tool with the URL $ARGUMENTS and extract the following:
Identify:
- HTTP Method –
GET,POST,PATCH,DELETE, etc. - Endpoint path – e.g.
/api/v2/space - Parameters – name, type, required/optional, description
- Response fields – JSON structure returned by the API
2. Check the backlog-js client
Find the corresponding method in the backlog-js type definitions:
grep "methodName" node_modules/backlog-js/dist/types/backlog.d.ts
Replace methodName with the actual method name (e.g. getSpace, postIssue). If unsure of the name, read the full file to browse all available methods:
cat node_modules/backlog-js/dist/types/backlog.d.ts
Use the method's name and type signature as the basis for implementation.
3. Read an existing similar tool for reference
cat src/tools/getSpace.ts
cat src/handlers/builders/composeToolHandler.ts
4. Implement the tool
Create or update these files following the existing patterns:
src/tools/<toolName>.ts
- Define the tool name, description, and input schema using
zod - Map each API parameter to a zod field with an appropriate description
- Set
outputSchemato a Zod schema matching the API response shape (seesrc/types/zod/backlogOutputDefinition.ts) - Set
importantFieldsto the subset of fields that are most relevant to the user - Implement
handlerto call the correspondingbacklog-jsclient method
src/tools/tools.ts
- Register the new tool so it is picked up by the server
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 · 63 lines · 67 tokens per session scan A e23bcbffa322
implement-backlog-api-tool is a skill published in the GitHub repository nulab/backlog-mcp-server (230 stars, last pushed 9d ago), licensed MIT. It adds 67 tokens to every session and 501 once invoked, about $0.0003 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 2026-08-30.
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.
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…
agent-host-chat-contributions
Build and review cross-cutting agent-host chat behavior through lifecycle contributions. Use when adding turn lifecycle side effects, prompt or context injection, restored-history transformation, protocol-action observation, or when reviewing changes that add code to AgentSideEffects or AgentService.
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.