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 TonyWu20/fortran-dev-pipeline --skill review-prgit clone --depth 1 https://github.com/TonyWu20/fortran-dev-pipelineWrote 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/tonywu20/fortran-dev-pipeline/review-pr)<a href="https://agentmods.dev/skills/tonywu20/fortran-dev-pipeline/review-pr"><img src="https://agentmods.dev/badge/skills/tonywu20/fortran-dev-pipeline/review-pr/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/tonywu20/fortran-dev-pipeline/review-pr"><img src="https://agentmods.dev/badge/skills/tonywu20/fortran-dev-pipeline/review-pr.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 | $0.00044 | $0.03630 |
| Opus 5 | $0.00022 | $0.01815 |
| Sonnet 5 | $0.00009 | $0.00726 |
| Haiku 4.5 | $0.00004 | $0.00363 |
Grade A, and why
review-pr scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 11d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 352 lines — stays where its author put it; the contents beside it link to each section on GitHub.
PR Review Skill
Reviews a branch against main, checks plan/spec/style compliance, rates the PR, and produces a fix document for the author.
Trigger
/review-pr [branch-name]
If no branch is given, compare the current branch against main.
Command-line Tools
- use
fdinstead offind - use
rginstead ofgrep
Process
Step 1: Load Context
Read these three things — nothing else:
-
Project memory (always):
Derive the memory directory from the current working directory:
MEMORY_DIR="$HOME/.claude/projects/$(pwd | sd '/' '-')/memory"- Read
$MEMORY_DIR/MEMORY.md(the index). If it exists, read every memory file linked in the index. - If
MEMORY.mddoes not exist but the directory does, read all*.mdfiles in the directory directly. - If the directory is missing or empty, note that no project memory is available and proceed with the diff alone.
- Read
-
Phase plan (always):
Locate the authoritative spec for this branch. Try in order:
- Parse the branch name for a phase identifier (e.g.,
phase-4-density-mixing→ look for4). Search:fd -e md -e toml . plans/ | rg -i 'phase.?{N}' - If a
plans/directory exists and contains exactly one plan file, use it. - If the
notes/plan-reviews/directory exists, check for adecisions.mdfile that names the plan path. - If no plan is found: note "No phase plan found — scope gating disabled; all issues treated as [Correctness]." and proceed without a spec.
When found, read the full plan. This is the authoritative scope spec — issues must be justified against it.
- Parse the branch name for a phase identifier (e.g.,
-
Branch status snapshot (if it exists):
notes/pr-reviews/{branch}/status.mdThe snapshot contains the post-fix diff, changed-file list, build/test results, and outstanding issues — it is the complete picture of the branch state.
If the snapshot exists: stop reading here. Do not read any source files, run any git commands, or call any LSP tools. Proceed directly to Step 2 with the plan and snapshot in context.
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.
- 11d ago First seen · 352 lines · 44 tokens per session scan A e500e2b5f3bf
review-pr is a skill published in the GitHub repository TonyWu20/fortran-dev-pipeline (5 stars, last pushed 4mo ago), licensed MIT. It adds 44 tokens to every session and 3,630 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
autoreview
Pre-commit/ship code review: Codex default; optional Claude or Pi.
omh-code-review
This is a Hermes-native code-review workflow skill.
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"…
code-reviewer
Code review specialist focused on patterns, bugs, security, and performance.
full-repo-review
Comprehensive four-wave review of all repo source files, producing a prioritized issue backlog.
agent-teams-simplify-and-harden
Implementation + audit loop using parallel agent teams with structured simplify, harden, and document passes. Spawns implementation agents to do the work, then audit agents to find complexity, security gaps, and spec deviations, then loops until code compiles cleanly, all tests pass, and auditors find zero issues or…