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/mthines/agent-skills/review-changesnpx skills add mthines/agent-skills --skill review-changesgit clone --depth 1 https://github.com/mthines/agent-skillsWrote 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/mthines/agent-skills/review-changes)<a href="https://agentmods.dev/skills/mthines/agent-skills/review-changes"><img src="https://agentmods.dev/badge/skills/mthines/agent-skills/review-changes.svg" alt="Measured on agentmods" 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 | $0.00065 | $0.01428 |
| Opus 5 | $0.00032 | $0.00714 |
| Sonnet 5 | $0.00013 | $0.00286 |
| Haiku 4.5 | $0.00006 | $0.00143 |
Grade A, and why
review-changes scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 6d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 94 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Routing
Choose the path based on the argument shape:
| Argument shape | Path | Reason |
|---|---|---|
no arg / --report |
Skill("review-loop", "<pr-url> [--critical|--no-ci|--external-review|--interval S]") on the current branch's open PR, or pr-reviewer directly if --report (one-shot, no apply) |
Own PR convergence loop, or one-shot report. |
PR URL or #<n> |
Skill("review-loop", "<pr-url> [--critical|--no-ci|--external-review|--interval S]") — runs the bounded review-apply-simplify loop |
Converges the PR regardless of who authored it (pr-reviewer detects REVIEW_RELATION itself). |
--no-ci, --external-review and --interval S are pass-throughs: this skill never
sets them itself, it only forwards what the user passed (see the note below).
# --report routes straight to pr-reviewer, which --external-review exists to avoid.
# Refuse the pair rather than accepting a flag this path cannot honour, mirroring
# review-loop's refusal of --no-feedback --external-review.
case "$ARGUMENTS" in
*--report*) case "$ARGUMENTS" in
*--external-review*)
echo "--report needs pr-reviewer; drop --external-review or drop --report."
exit 1 ;;
esac ;;
esac
# Resolve the current branch's PR whenever no PR was named. Test for the ABSENCE of a
# PR reference, never for an exact flag string: every flag in the table above is
# combinable, so `= "--report"` left `--external-review`, `--critical`, `--no-ci`, and
# `--interval S` with no PR to act on.
case "$ARGUMENTS" in
*github.com/*/pull/*|*\#[0-9]*) ;; # a PR was named; use it
*) CURRENT_PR=$(gh pr view --json url -q .url 2>/dev/null) ;;
esac
review-changes passes no --no-ci — unlike create-pr and autonomous-workflow
Phase 7, it owns no CI phase of its own, so the loop's CI sub-step is exactly what
keeps a standalone run from converging on a red build instead of a
green-threads-red-build one. Forward --no-ci, --external-review, and --interval
through when the user passes them.
It converges on not red, not on green. review-loop's ci_is_settled() treats
pending as settled — the loop reads check state, never waits for it — so a run can
converge with checks still in flight. Wait for the checks yourself before merging, or
give CI to a caller that owns a watch (create-pr Step 9, phase-7-ci-gate.md) and
pass --no-ci here.
# Default — convergence loop on own or specified PR
Skill("review-loop", "<pr-url-or-number> [--critical|--no-ci|--external-review|--interval S if passed]")
# Report-only (no apply) — one-shot review.
# pr-reviewer is an AGENT — dispatch via the Task tool, NOT Skill():
Task(subagent_type="pr-reviewer", prompt="<pr-url-or-number> [--critical if passed]")
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.
- 6d ago First seen · 94 lines · 65 tokens per session scan A 70f4be55381a
review-changes is a skill published in the GitHub repository mthines/agent-skills (12 stars, last pushed yesterday), licensed MIT. It adds 65 tokens to every session and 1,428 once invoked, about $0.0003 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
ego-browser
Skill "ego-browser" from citrolabs/ego-lite, covering ego-browser, quick start, common helpers, task spaces and control handoff.
temporal-developer
Develop, debug, and manage Temporal applications across Python, TypeScript, Go, Java, .NET, Ruby, and Rust. Use when the user is building workflows, activities, or workers with a Temporal SDK, debugging issues like non-determinism errors, stuck workflows, or activity retries, using Temporal CLI, Temporal Server, or…
x-algorithm
Write X (Twitter) posts that the For You algorithm actually rewards. Grounded in the open-sourced X recommendation system — the Grok-based transformer ranker, Phoenix retrieval, Thunder in-network store, and Grox content-understanding pipeline. Use when the user wants to write a post, thread, reply, or quote; plan a…
opencode-memory
Browse local OpenCode history: sessions, messages, plans, prompt history, and prior decisions. Use when the user says history, previous session, last time, remember, recall, plans, prior work, or when resuming/debugging repeated work where earlier OpenCode context may help. Do not use for fresh tasks or when current…
creating-explainers
Use when creating an interactive explainer - a single self-contained HTML page with hand-built Canvas figures. Handles source-file explainers, topic-driven research explainers, and mixed intake where files provide the spine and research adds support. Trigger phrases include "make an explainer", "turn this paper into…
custom-icons
Create or refine custom icon assets as native or traced SVGs and transparent PNG/WebP files. Use when the user asks for a bespoke icon or cohesive icon set, wants an image traced into a clean vector, or needs a detailed or 3D icon with transparency.