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 skills add ABilenduke/copilot-developer --skill review-plangit clone --depth 1 https://github.com/ABilenduke/copilot-developerWrote 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/abilenduke/copilot-developer/review-plan)<a href="https://agentmods.dev/skills/abilenduke/copilot-developer/review-plan"><img src="https://agentmods.dev/badge/skills/abilenduke/copilot-developer/review-plan/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/abilenduke/copilot-developer/review-plan"><img src="https://agentmods.dev/badge/skills/abilenduke/copilot-developer/review-plan.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 | $0.00040 | $0.01015 |
| Opus 5.5 | $0.00016 | $0.00406 |
| Sonnet 5.5 | $0.00008 | $0.00203 |
| Haiku 4.5 | $0.00004 | $0.00102 |
Grade A, and why
review-plan 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 — 80 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Review Plan
Independently assess whether delivered behavior fulfills the current agreed plan. Produce actionable, evidence-backed findings and concise acceptance coverage. Accept a BRD, chat plan, ordinary Markdown, or usable split documents. No companion skill, connector, journal, or specific repository layout is required. A prior executor's success claim is evidence to inspect, not a conclusion to inherit.
Establish the review boundary
Use the explicitly supplied plan or the unambiguous plan in the conversation. Ask for its location or which candidate to use only when necessary. Read applicable repository instructions, current plan decisions, relevant source, tests, and any execution journal. Preserve requirement IDs; use stable section or step references if IDs are absent. A missing journal alone is not an implementation defect.
Identify the requested revision, comparison base, and included changes. For current-workspace reviews, inspect staged, unstaged, and relevant untracked files; record HEAD when available. For a supplied commit range or PR, honor that boundary. Do not silently choose a branch base or review a different revision. Ask if consequential ambiguity remains, while inspecting unambiguous context. Review actual resulting code and affected callers as well as the diff: missing implementation may have no changed line. Keep unrelated user changes outside findings unless they materially affect the requested work.
Resolve plan revisions using the latest explicit user decisions. Removed requirements stay removed; stale journal tasks do not restore scope. Distinguish a contradictory or underspecified acceptance criterion from a proven implementation failure. Ask only consequential questions evidence cannot settle.
Preserve the workspace
Review is read-only by default: do not fix source, edit plans or journals, write a report into the repository, stage, commit, push, publish comments, or change execution status. Return the review in chat. Honor explicit authorization to save a report when the active mode permits it; inspect any existing destination before writing. Authorization to review does not authorize remediation or external messages. Preserve authorization already given if the user separately requests those actions.
What ships with it
3 files 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.
- 1mo ago First seen · 80 lines · 40 tokens per session scan A 8bbe095a9da4
review-plan is a skill published in the GitHub repository ABilenduke/copilot-developer (4 stars, last pushed 1mo ago), licensed MIT. It adds 40 tokens to every session and 1,015 once invoked, about $0.0002 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 2026-09-16.
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"…
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…
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…
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…