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/cpliakas/claude-code-engineering-leaders/write-bugnpx skills add cpliakas/claude-code-engineering-leaders --skill write-buggit clone --depth 1 https://github.com/cpliakas/claude-code-engineering-leadersWhat 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 | $0.00039 | $0.01781 |
| Opus 5 | $0.00019 | $0.00890 |
| Sonnet 5 | $0.00008 | $0.00356 |
| Haiku 4.5 | $0.00004 | $0.00178 |
Grade A, and why
write-bug 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 — 165 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Write Bug
Scaffold a complete, RIMGEN-validated bug report ready to file as an issue or ticket.
Input
$ARGUMENTS = description of the bug — what broke, what you were doing, what you expected.
Process
1. Handle Missing Input
If $ARGUMENTS is empty or contains no actionable description, prompt the author for the minimum information needed to begin scaffolding. Present these questions in a single consolidated prompt:
- What broke? — Describe the failure in one sentence.
- How do you reproduce it? — What steps lead to the failure?
- What did you expect to happen? — The correct behavior.
- What actually happened? — The incorrect behavior you observed.
- What is your environment? — Version, OS, browser or runtime if applicable.
- Who is affected? — Just you, or specific configurations or all users?
Do not proceed to draft until the author has provided at least: a failure description, at least one reproduction step, and both expected and actual behaviors.
2. Assess RIMGEN Completeness
Before drafting, evaluate whether the input provides enough information across all six RIMGEN dimensions:
| Dimension | Sufficient when | Prompt if underspecified |
|---|---|---|
| R — Reproducible | Steps are present and specific enough to follow independently | "What are the exact steps to reproduce this?" |
| I — Isolated | A single, specific failure is described — not a cluster of related issues | "Is this one specific failure, or are there multiple separate issues to report?" |
| M — Minimal | The reproduction path is not bloated with unnecessary setup | No prompt needed — trim during drafting |
| G — Generalizable | Scope of impact is stated (all users? specific role? specific config?) | "Who else sees this — all users, or only in specific configurations?" |
| E — Expected vs. Actual | Both expected and actual behaviors are present and distinct | "What did you expect to happen?" and/or "What actually happened?" |
| N — Necessary Context | At least one environment detail is present (version, OS, or configuration) | "What version and environment are you running?" |
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 · 165 lines · 39 tokens per session scan A 06495907b830
write-bug is a skill published in the GitHub repository cpliakas/claude-code-engineering-leaders (4 stars, last pushed 11d ago), licensed MIT. It adds 39 tokens to every session and 1,781 once invoked, about $0.0002 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…