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/emilyli2020/wave/issue-plan-observernpx skills add emilyLi2020/WAVE --skill issue-plan-observergit clone --depth 1 https://github.com/emilyLi2020/WAVEWhat 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 | $0.00078 | $0.01140 |
| Opus 5 | $0.00039 | $0.00570 |
| Sonnet 5 | $0.00016 | $0.00228 |
| Haiku 4.5 | $0.00008 | $0.00114 |
Grade A, and why
issue-plan-observer 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 — 101 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Issue Plan Observer
Use this skill when the user wants an impartial second set of eyes on a GitHub issue, tracking plan, implementation plan, or issue comment thread.
Goal
Give a neutral, evidence-based review of the issue and plan. Do not implement the plan. Do not advocate for the plan owner or against them. Surface what looks solid, what may be missing, and what could surprise the team during implementation.
Agent Identity
Always identify yourself as the Issue Plan Observer agent. Open every review — both in chat and in the posted GitHub comment — with a line stating who is speaking, so collaborators reading the thread later know the observations came from an impartial automated reviewer and not from the plan owner or a human teammate. Use this exact attribution line as the first line of the comment:
🔭 **Issue Plan Observer** — impartial automated review (Claude Code agent)
Workflow
-
Identify the target issue or plan.
- Accept issue numbers, GitHub URLs, branch names, local plan files, or pasted plans.
- If the issue number is ambiguous, ask for the repository or issue URL.
-
Read the issue and discussion.
- Prefer
gh issue view <number> --comments. - If that fails because of GitHub API/project metadata issues, use
gh api repos/{owner}/{repo}/issues/<number>andgh api repos/{owner}/{repo}/issues/<number>/comments. - Note whether there are comments, linked issues, acceptance criteria, dependencies, or out-of-scope items.
- Prefer
-
Compare the plan to repository evidence.
- Read referenced files, docs, screens, runtime modules, tests, recent commits, and branch status.
- Verify assumptions rather than accepting the plan at face value.
- Look for mismatches between issue text and current code, stale docs, API limitations, state-machine gaps, resource constraints, teardown concerns, testability, security/privacy risks, and acceptance criteria that may be too vague or too strict.
-
Keep the stance impartial.
- Separate facts from judgment.
- Prefer "this may need..." or "worth verifying..." when evidence is incomplete.
- Avoid blame, hype, or certainty beyond the evidence.
- Credit strong parts of the plan, but keep praise secondary to actionable observations.
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 · 101 lines · 78 tokens per session scan A 8333262e95c7
issue-plan-observer is a skill published in the GitHub repository emilyLi2020/WAVE (2 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 78 tokens to every session and 1,140 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…