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 figitaki/reviews --skill reviews-overviewgit clone --depth 1 https://github.com/figitaki/reviewsWrote 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/figitaki/reviews/reviews-overview)<a href="https://agentmods.dev/skills/figitaki/reviews/reviews-overview"><img src="https://agentmods.dev/badge/skills/figitaki/reviews/reviews-overview/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/figitaki/reviews/reviews-overview"><img src="https://agentmods.dev/badge/skills/figitaki/reviews/reviews-overview.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 | $0.00085 | $0.00935 |
| Opus 5 | $0.00043 | $0.00467 |
| Sonnet 5 | $0.00017 | $0.00187 |
| Haiku 4.5 | $0.00009 | $0.00093 |
Grade A, and why
reviews-overview 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 — 77 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Reviews Overview
Use this skill to understand Reviews as a code-review platform and decide when to use it in an agent workflow. This is not a repo implementation guide.
What Reviews Is
Reviews is a review tool for arbitrary code diffs, not only GitHub pull requests. It lets an agent or developer push a diff to a shareable review URL, optionally attach a structured review packet, and iterate through revisions as patchsets.
The core value is making a diff understandable to a human reviewer before, during, or outside a public PR process.
What Reviews Provides
- Link-based review pages for uploaded diffs.
- Patchsets for iterating on the same review as the work changes.
- Review packets that organize a diff into human-readable sections with prose and hunk references.
- Lazy hunk rendering so large diffs can be reviewed without eagerly mounting every diff.
- Explicit hunk viewed state for signed-in reviewers.
- Section decisions such as approve, deny, or ignore for packet sections.
- Comment drafting and publishing so reviewers can batch feedback.
- Changes view for direct file/hunk review outside the packet narrative.
When To Use Reviews
Use Reviews after a few turns of human-in-the-loop or agent-driven development when there is a coherent diff ready for human review.
Good moments:
- The agent has implemented a feature and wants a human to inspect the result before public PR creation.
- The user asks for a review packet, local review, or shareable review link.
- The work has grown large enough that raw
git diffis hard to review. - The agent wants to explain the review order, risk areas, and tradeoffs alongside the code.
- The team wants a pre-PR review pass before committing to a public GitHub PR.
- A project has another review process, but Reviews can provide the structured packet and hunk progress layer.
Avoid using Reviews when:
- There is no concrete diff yet.
- The user only wants brainstorming or planning.
- The change is tiny enough that inline explanation is sufficient.
- The diff contains secrets or local-only artifacts that should not be uploaded.
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.
- 10d ago First seen · 77 lines · 85 tokens per session scan A 9a4427ad9545
reviews-overview is a skill published in the GitHub repository figitaki/reviews (6 stars, last pushed 5d ago), licensed MIT. It adds 85 tokens to every session and 935 once invoked, about $0.0004 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
elixir-phoenix-review
Review Phoenix changes with parallel specialists before commit or PR.
elixir-phoenix-pr-review
Handle Phoenix PR review comments: inspect feedback, draft replies, and fix code.
elixir-phoenix-triage
Triage review findings after $elixir-phoenix-review before fixing.
elixir-phoenix-runtime-durability-review
Elixir/Phoenix: Review lifecycle, state-machine, Oban, persistence, pause/resume, retry, and restart-sensitive changes before commit, push, or PR. Use for concurrency-sensitive runtime work to produce explicit blocking vs optional findings, require durability checks, and verify smoke plus restart resilience when…
elixir-phoenix-techdebt
Assess Phoenix technical debt, duplication, cleanup, and refactor targets.
elixir-review
Review Elixir/Phoenix code: OTP patterns, GenServer, LiveView, fault tolerance and concurrency.