Borrowing it
Nothing to install: this file belongs to Terry-Mao/AICodingFlow. 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/Terry-Mao/AICodingFlow/main/.agents/skills/review-pr-local/SKILL.mdgit clone --depth 1 https://github.com/Terry-Mao/AICodingFlowWrote 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/terry-mao/aicodingflow/review-pr-local)<a href="https://agentmods.dev/skills/terry-mao/aicodingflow/review-pr-local"><img src="https://agentmods.dev/badge/skills/terry-mao/aicodingflow/review-pr-local/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/terry-mao/aicodingflow/review-pr-local"><img src="https://agentmods.dev/badge/skills/terry-mao/aicodingflow/review-pr-local.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00028 | $0.00462 |
| Opus 5.5 | $0.00011 | $0.00185 |
| Sonnet 5.5 | $0.00006 | $0.00092 |
| Haiku 4.5 | $0.00003 | $0.00046 |
Grade A, and why
review-pr-local 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.
Copies of this mod
1 near-identical copy found in the catalogue:
- review-spec-local — 86% identical, 15 lines differ
What it actually says
review-pr-local
Use this skill after local implementation work and before pushing or creating a
PR. It prepares the same review inputs used by the GitHub review workflow, then
delegates review logic to review-pr.
Workflow
- From the repository root, prepare local review inputs. This prefers the
GitHub PR associated with the current branch for
pr_description.txt, then falls back to locally built PR metadata when the GitHub PR cannot be fetched. Thepr_diff.txtsnapshot is built from the local worktree diff. The command writes snapshots to a temporary directory and prints the selected review skill asskill=<path>plus exact file paths:python3 .github/scripts/prepare_local_review_inputs.py - Read the
skillpath printed by the command. - Follow the selected skill exactly. It will apply any referenced local companion guidance when present.
- Use only the printed snapshot paths as review inputs:
pr_description_pathpr_diff_pathspec_context_pathwhen non-empty
- Inspect repository files from the current repository root when the review skill needs source context.
- Write the review output only to the printed
review_path. - Validate the review output:
python3 .github/scripts/validate_review_json.py <pr_diff_path> <review_path> - Validate that the review phase did not mutate repository files:
python3 .github/scripts/validate_local_review_result.py \ --baseline-status <baseline_status_path>
Safety Rules
- After input preparation, do not run
git add,git commit,git push,gh, or GitHub API commands. - Do not post comments or mutate GitHub state.
- Do not modify source, workflow, tests, specs, or skill files.
- If review discovers issues, report them through
review.json; do not fix code during this skill.
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 · 51 lines · 28 tokens per session scan A a4c4d12d2db2
review-pr-local is a skill published in the GitHub repository Terry-Mao/AICodingFlow (169 stars, last pushed today), licensed MIT. It adds 28 tokens to every session and 462 once invoked, about $0.0001 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 2026-08-30.
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…