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/luanmorenommaciel/agentspec/github-cr-issuenpx skills add luanmorenommaciel/agentspec --skill github-cr-issuegit clone --depth 1 https://github.com/luanmorenommaciel/agentspecWhat 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 | $0.00166 | $0.02379 |
| Opus 5 | $0.00083 | $0.01189 |
| Sonnet 5 | $0.00033 | $0.00476 |
| Haiku 4.5 | $0.00017 | $0.00238 |
Grade A, and why
github-cr-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 yesterday.
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 — 158 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Create Issue (GitHub)
Draft the body of one well-formed, non-ADR issue as an ephemeral local file, ready to be reviewed and then published as a GitHub issue by github-post-issue.
A good issue records one topic in a self-contained way. GitHub is the project's state store, agent sessions are stateless workers, and the published issue is the complete spec — any future contributor or agent session must be able to read and act on it with zero private context.
This skill always operates on the repository it is invoked in — the repo is detected dynamically in step 1 and never assumed.
When to use
- The user asks to create, draft, or write an issue — a feature, component, task, bug, or spike.
- A discussion, idea, or defect report needs to become a tracked, actionable GitHub issue.
- A large initiative needs structuring as a parent issue with sub-issues.
Skip if
| Situation | Do instead | Why |
|---|---|---|
| Architecture decision (which option and why) | github-cr-adr |
Features and components link to decisions; they do not contain them. |
| A finished draft needs publishing, labels, or relationships | github-post-issue |
Publication has its own guardrails: dedup, self-containment, label validation. |
| Updating an issue that already exists | gh issue comment / gh issue edit |
The existing issue is the record; extend it instead of forking it. |
| Trivial, immediate change | Fix it directly | An issue that outlives the work it describes is pure overhead. |
Issue types
Pick exactly one type per issue.
| Type | Use for | Title format |
|---|---|---|
feature |
A capability to add, for users or developers | [FEATURE] … |
component |
A reusable building block or subsystem with a defined contract | [COMPONENT] … |
task |
A concrete unit of work, usually a child of a feature, component, or ADR | [TASK] … |
bug |
A defect, with reproduction steps and expected vs actual behavior | [BUG] … |
spike |
A time-boxed investigation: one question, one deliverable | [SPIKE] … |
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- yesterday First seen · 158 lines · 166 tokens per session scan A 27aa590fe32c
github-cr-issue is a skill published in the GitHub repository luanmorenommaciel/agentspec (244 stars, last pushed 2d ago), licensed MIT. It adds 166 tokens to every session and 2,379 once invoked, about $0.0008 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 2026-09-01.
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…