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/specsnl/agent-specs/implement-issuenpx skills add specsnl/agent-specs --skill implement-issuegit clone --depth 1 https://github.com/specsnl/agent-specsWhat 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 | $0.00117 | $0.00711 |
| Opus 5 | $0.00059 | $0.00356 |
| Sonnet 5 | $0.00023 | $0.00142 |
| Haiku 4.5 | $0.00012 | $0.00071 |
Grade A, and why
implement-issue 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 — 84 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Implement an issue
Turn an issue (GitHub or Linear) into a branch of clean, incremental commits — without opening a pull request. The user opens the PR when they decide it's ready; this skill deliberately stops just short of that.
Phase 1 — Read the issue
Fetch the full issue before touching git so you understand the actual requirement.
- GitHub — prefer a GitHub MCP tool (e.g.
get_issue) when one is available; otherwise use the CLI:gh issue view <number> --json title,body,labels,comments. - Linear — use the Linear MCP
get_issue(accepts the issue identifier such asABC-456).
Extract and note:
- The concrete requirement and scope.
- Acceptance criteria / definition of done.
- Any linked issues, designs, or discussion in comments that change the approach.
If the requirement is ambiguous, ask the user before implementing.
Phase 2 — Create a branch
Never implement directly on the base branch.
-
Confirm the working tree is clean (
git status) and note the current base branch (usuallymain). -
Create and switch to a new branch with a descriptive name derived from the issue id and a short slug of its title:
feat/<issue-id>-<slug>for new functionalityfix/<issue-id>-<slug>for bug fixeschore/<issue-id>-<slug>/docs/.../refactor/...as appropriate
git switch -c feat/GH-123-short-slug
Phase 3 — Implement
Implement the change following the repository's existing conventions and patterns. Match the surrounding code style; reuse existing utilities rather than adding new ones. Run the project's checks/tests as you go.
Phase 4 — Commit nicely
Commit as you complete logical units of work — not one large dump at the end.
- Small, self-contained commits, each leaving the tree in a working state.
- Clear, imperative subject lines that follow the repo's convention (e.g.
Conventional Commits when the repo uses them), referencing the issue where it
helps (e.g.
feat: add X (GH-123)orRefs ABC-456). - Keep unrelated changes out of a commit.
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 · 84 lines · 117 tokens per session scan A 02077d6039a7
implement-issue is a skill published in the GitHub repository specsnl/agent-specs (2 stars, last pushed 16d ago), licensed MIT. It adds 117 tokens to every session and 711 once invoked, about $0.0006 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.
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.