Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/imisic/claude-marketplacenpx agentmods add skills/imisic/claude-marketplace/a-review-optimizerWrote 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/imisic/claude-marketplace/a-review-optimizer)<a href="https://agentmods.dev/skills/imisic/claude-marketplace/a-review-optimizer"><img src="https://agentmods.dev/badge/skills/imisic/claude-marketplace/a-review-optimizer/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/imisic/claude-marketplace/a-review-optimizer"><img src="https://agentmods.dev/badge/skills/imisic/claude-marketplace/a-review-optimizer.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 | $0.00022 | $0.07886 |
| Opus 5 | $0.00011 | $0.03943 |
| Sonnet 5 | $0.00004 | $0.01577 |
| Haiku 4.5 | $0.00002 | $0.00789 |
Grade A, and why
a-review-optimizer scanned grade A with 1 finding 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 7d 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.
Runs shell commandslowCapability
Expected in a hook, worth knowing in a rule or an instructions file.
- src/cli.py:622: subprocess.run() without timeout (similar calls may exist elsewhere) How it starts
The opening of the file, as written. The whole thing — 501 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Review Skill Optimizer
Takes an existing review skill and makes it sharper by deeply analyzing the actual codebase. The approach is surgical: keep everything that works, fix what doesn't, add what's missing. The user built that skill with real experience. Don't throw it away.
Input: optional path to a review skill's SKILL.md (e.g., .claude/skills/example-review/SKILL.md)
If no path given, auto-detect: scan .claude/skills/*/SKILL.md for review-related skills (look for "review" in name, description, or content mentioning agents/preflight/findings). If exactly one found, use it. If multiple found, list them and ask which one. If none found, create a new review skill from scratch.
Core Principle: Preserve First, Improve Surgically
The existing skill reflects real project knowledge: conventions the user discovered, false positives they already solved, agent scopes they tuned through experience. Treat it as the baseline, not a rough draft.
Default behavior: Keep every section of the existing skill unless the gap analysis gives a concrete reason to change it. When you do change something, the change must be traceable to a specific gap, overlap, or false positive you found.
What gets preserved:
- Agent names and their general scope (unless overlaps are found)
- Known-correct pattern whitelists (these are hard-won project knowledge)
- Output format structure (unless it lacks fix readiness fields)
- Existing preflight checks that still work
- Project-specific context sections and conventions documentation
- Anything the user invested effort into getting right
What gets changed (with justification):
- Gaps: missing checks the project needs but the skill doesn't cover
- False positives: patterns the skill flags that are actually correct in this project
- Overlaps: two agents checking the same thing (tighten scopes)
- Stale references: file:line examples pointing to code that no longer exists
- Missing preflight: deterministic checks that should exist but don't
- Missing fix readiness: findings without file:line + current code + proposed fix + why
What ships with it
11 files 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.
- agents/openai.yaml 157 B
- benchmarks/corpus.json 21 KB
- benchmarks/test-guards.sh 6.1 KB runs code
- references/_shared.md 953 B
- references/benchmark.md 14 KB
- references/output-template.md 7.4 KB
- references/pattern-detection.md 30 KB
- references/preflight-template.md 24 KB
- references/review-dimensions.md 9.3 KB
- references/skill-scaffold.md 24 KB
- scripts/seed-defects.py 26 KB runs code
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.
- 7d ago Changed · +6 lines 89dd6cda1f69
- 11d ago First seen · 495 lines · 22 tokens per session scan A c37b5bd64353
a-review-optimizer is a skill published in the GitHub repository imisic/claude-marketplace (2 stars, last pushed 9d ago), licensed MIT. It adds 22 tokens to every session and 7,886 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 1 finding (runs shell commands). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
agentic-review
Deep multi-agent code review for local changes. Inspired by AmpCode's agentic review. Use when you want comprehensive analysis of staged changes, unstaged changes, specific commits, or branch differences. Spawns parallel specialized agents (security, performance, patterns, architecture) and synthesizes actionable…
qa
Full QA on all session changes using Codex as a second pair of eyes. Use when user says "QA", "full QA", "QA my changes", "QA all your changes", or "use codex to review". Runs git diff, sends changes to Codex for thorough review, and synthesizes findings.
review-responder
Use when receiving feedback on code you implemented, responding to reviewer comments, deciding which review suggestions to implement, or pushing back on incorrect review feedback.
pr-sweep
Use when you want to sweep all open pull requests across all repos, triage their status, run code reviews on unreviewed PRs, merge what's ready, fix quick blockers, and produce a full status report. Trigger when the user says "check my PRs", "close out open PRs", "what's the status of my PRs", "sweep my PRs", "PR…
rubber-ducky
Use when you've planned a non-trivial change and are about to implement it, finished a complex or multi-file piece of work, just wrote tests, or are stuck on repeated failures — and any time the user says "rubber duck this", "rubber ducky", "get a second opinion", "sanity-check my plan", "poke holes in this", "what am…
open-pr
Use when wrapping up a development task and getting a PR ready — runs local tests, creates a PR (if one doesn't exist) with a structured description template, conducts a code review via the review skill, and checks CI status with quick fixes. Trigger when the user says they're done with a feature, want to open a PR…