Borrowing it
Nothing to install: this file belongs to emilyLi2020/WAVE. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/emilyLi2020/WAVE/main/.agents/skills/issue-plan-observer/SKILL.mdgit clone --depth 1 https://github.com/emilyLi2020/WAVEWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/emilyli2020/wave/issue-plan-observer)<a href="https://agentmods.dev/skills/emilyli2020/wave/issue-plan-observer"><img src="https://agentmods.dev/badge/skills/emilyli2020/wave/issue-plan-observer/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/emilyli2020/wave/issue-plan-observer"><img src="https://agentmods.dev/badge/skills/emilyli2020/wave/issue-plan-observer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What 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 5.1 | $0.00078 | $0.01140 |
| Opus 5.5 | $0.00031 | $0.00456 |
| Sonnet 5.5 | $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 1mo 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.
- 1mo 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 4mo ago), licensed Apache-2.0. It adds 78 tokens to every session and 1,140 once invoked, about $0.0003 per session on Opus 5.5. 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
autoreview
Structured code review through the shared OpenClaw agent-skills installation.
omh-code-review
This is an OMH code-review workflow skill, projected for Agent Skills hosts (Claude Code, Codex, Cursor, opencode, OpenClaw, pi).
revdiff-plan
Review the last Codex assistant message (plan, analysis, or proposal) with inline annotations in a TUI overlay. Extracts the most recent response from Codex rollout files and opens it in revdiff for review and annotation. Activates on "revdiff-plan", "review plan with revdiff", "annotate plan", "review last response"…
re0-merge
Review and land an external contribution the way this suite does: gate it against the thesis, land it with the author's credit intact, complete a new skill rather than merging it raw, then approve, credit, and explain before closing. Use when reviewing a pull request, as any collaborator or maintainer, not only the…
explore-unknowns
Guide the user through a quadrant walk that maps the unknowns of a task — open by listing the known knowns, then work through known unknowns, unknown knowns, and unknown unknowns one stage at a time, ending with a complete four-quadrant map in the user's hands. Use when a request is ambiguous or underspecified, the…
asplos-writing-style
Use when drafting or revising ASPLOS prose — engineering the first two pages that rapid review actually reads, stating the cross-layer insight as one quotable sentence, structuring per-layer mechanism sections, writing bounded claims, and fitting everything into 11 self-contained pages that include figures and…