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 mickeyyaya/evolve-loop --skill diff-reviewgit clone --depth 1 https://github.com/mickeyyaya/evolve-loopWrote 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/mickeyyaya/evolve-loop/diff-review)<a href="https://agentmods.dev/skills/mickeyyaya/evolve-loop/diff-review"><img src="https://agentmods.dev/badge/skills/mickeyyaya/evolve-loop/diff-review/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/mickeyyaya/evolve-loop/diff-review"><img src="https://agentmods.dev/badge/skills/mickeyyaya/evolve-loop/diff-review.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 | $0.00081 | $0.01640 |
| Opus 5.5 | $0.00032 | $0.00656 |
| Sonnet 5.5 | $0.00016 | $0.00328 |
| Haiku 4.5 | $0.00008 | $0.00164 |
Grade A, and why
diff-review 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 10d 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 — 135 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Diff Review — precise, budget-capped, two lenses in one pass
Why this skill exists: two generic review agents (go-reviewer + code-simplifier) spent 197k + 136k tokens and 97 + 58 tool calls reviewing ONE staged diff (2026-07-27). The measured waste had four parts:
- a second derivation of the repo context that the caller already had;
- a second run of the test suites that the caller already ran;
- unbounded whole-tree consumer sweeps;
- two separate contexts that each loaded the same diff.
This skill keeps the review QUALITY disciplines (evidence-first, adversarial, file:line findings) and deletes the waste structurally.
Scope contract (RIGID)
The unit of review is the STAGED DIFF: git diff --cached. Nothing else is in
scope unless a hunk drags it in.
The caller's prompt MUST declare, and you MUST trust without re-running:
- Already verified: which test suites/lints/gates ran and their results. Re-running any of them is budget theft — CI re-proves them anyway.
- Intent: what the change is supposed to do, in 1-3 sentences.
- Known constraints: pinned contracts, protected surfaces, prior review findings already applied.
If the caller declared nothing, spend ONE tool call asking the diff itself
(git diff --cached --stat) and proceed — never block on missing context.
Budgets (RIGID)
- ≤ 20 tool calls total. Count them. At 20, stop and report with what you have.
- ≤ 15 file reads, and reads are TARGETED:
Readwith offset/limit around the hunk, never whole large files; the diff already shows the change. - One hop of coupling, found by grep. For each changed/added exported
symbol and each changed behavior (for example a return-shape change): ONE
grep -rnfor its call sites. Read only the call sites the grep surfaces. NEVER sweep docs/, .evolve/runs/, or knowledge-base/ unless a hunk edits them. - Run nothing the caller declared green. You can run at most ONE cheap
compile/probe (
go build ./pkg, a 5-line script). Use it only to settle a finding that a read cannot settle, and only for a finding that you report.
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.
- 10d ago Changed · +20 lines 6505481b117f
- 2mo ago First seen · 115 lines · 81 tokens per session scan A 17612279eda6
diff-review is a skill published in the GitHub repository mickeyyaya/evolve-loop (6 stars, last pushed today), licensed Apache-2.0. It adds 81 tokens to every session and 1,640 once invoked, about $0.0003 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 2026-09-03.
diff-review compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| diff-reviewmickeyyaya/evolve-loop | Skill | 6 | today | Apache-2.0 | A | 81 | Claude Code |
| releasehyhmrright/brooks-lint | Skill | 1.6k | yesterday | MIT | A | 135 | Claude Code, Codex |
| procoderazrtydxb/procoder | Skill | 211 | 11d ago | Apache-2.0 | A | 101 | Claude Code |
| pr-feedbackjjanczur/tyran | Skill | 79 | yesterday | Apache-2.0 | A | 57 | Claude Code |
| bump-versionhyhmrright/logic-lens | Skill | 25 | 7d ago | MIT | A | 52 | Claude Code |
| reviewgreglas75/zuvo | Skill | 7 | 3d ago | MIT | A | 70 | Claude Code |
| incidentgreglas75/zuvo | Skill | 7 | 3d ago | MIT | A | 64 | Claude Code |