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 kunalsuri/ai-fication-kit --skill review-changegit clone --depth 1 https://github.com/kunalsuri/ai-fication-kitWrote 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/kunalsuri/ai-fication-kit/review-change)<a href="https://agentmods.dev/skills/kunalsuri/ai-fication-kit/review-change"><img src="https://agentmods.dev/badge/skills/kunalsuri/ai-fication-kit/review-change/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/kunalsuri/ai-fication-kit/review-change"><img src="https://agentmods.dev/badge/skills/kunalsuri/ai-fication-kit/review-change.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 | $0.00060 | $0.00481 |
| Opus 5 | $0.00030 | $0.00241 |
| Sonnet 5 | $0.00012 | $0.00096 |
| Haiku 4.5 | $0.00006 | $0.00048 |
Grade A, and why
review-change 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 12d 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.
What it actually says
Review a change
The contract: review in a session that did NOT write the change; check with evidence, not assertions; re-run the suites yourself; the written verdict is the deliverable — the human merges, not you.
1. Fresh-context gate
A reviewer sharing the implementer's context inherits the implementer's blind spots. If this session wrote the change, stop and hand the review to a fresh session that did not implement it.
2. Pin the scope
Identify the exact diff (commits / branch / files) and the spec or bugfix doc in
ai/lab/specs/ that authorized it. No spec ⇒ that is finding #1, severity blocker:
unspecced work.
3. Open the review
Copy ai/lab/reviews/REVIEW_TEMPLATE.md → ai/lab/reviews/REVIEW_<work-id>.md.
4. Check with evidence
For each check in the template — spec conformance, surgical diff, Stability respected, tests, conventions, knowledge updated, provenance clean — record where you looked and what you saw. Re-run the suites the spec names yourself; do not trust the implementer's report.
5. File findings by severity
Any blocker or major ⇒ verdict request-changes; hand the list back to the
implementer. Minor / nit findings can ship with notes.
6. Verdict and hand-off
Fill "what the human should double-check" — the judgement calls a mechanical check
cannot make. The review itself is [inferred]; the human's merge decision is the
real approval, and this document is its evidence.
7. Record
Link the review from the work's row in ai/lab/WORKLOG.md (Review column) and set
that row's Status to in-review.
What ships with it
1 file 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.
- 12d ago First seen · 44 lines · 60 tokens per session scan A 64ac55b4bf57
review-change is a skill published in the GitHub repository kunalsuri/ai-fication-kit (3 stars, last pushed 9d ago), licensed Apache-2.0. It adds 60 tokens to every session and 481 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
doubt-driven-development
Subjects every non-trivial decision to a fresh-context adversarial review before it stands. Use when you want every assumption cross-examined before proceeding, when stress-testing a plan for hidden failure modes, when correctness matters more than speed, when working in unfamiliar code, when stakes are high…
address-github-comments
Use when you need to address review or issue comments on an open GitHub Pull Request using the gh CLI.
hunk-extensions
Maps the hunkdiff/extension authoring surface for Hunk, the terminal diff viewer — hiding or reordering reviewed files, docked panes, alternate file views, commands and key bindings, dialogs, workspace writes, themes, syntax languages, VCS backends, lifecycle events. Use when writing, debugging, or installing a Hunk…
hunk-launch-video
Produces Hunk videos by driving the real TUI headlessly in a PTY, compositing captioned 1080p frames in Chromium, and encoding with ffmpeg. Use for feature demos, workflow explainers, announcements, launch videos, and full-release roundups.
check
Reviews code diffs, PRs, issue queues, release readiness, commits, pushes, publishing, and project audits. Use when users ask in any language for code review, issue or PR triage, release gates, publishing follow-through, or project audits. Not for debugging root causes or prose review.
mantis-critic
Assesses the production viability of findings, filtering out debug-only features and assertion traps. Use when findings have been validated and you need to confirm they are triggerable in production release builds (with assertions disabled). Don't use for writing reproduction scripts or patches.