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/figitaki/reviewsnpx agentmods add skills/figitaki/reviews/using-reviews-locallyWrote 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/using-reviews-locally)<a href="https://agentmods.dev/skills/figitaki/reviews/using-reviews-locally"><img src="https://agentmods.dev/badge/skills/figitaki/reviews/using-reviews-locally/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/using-reviews-locally"><img src="https://agentmods.dev/badge/skills/figitaki/reviews/using-reviews-locally.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 | $0.00082 | $0.00877 |
| Opus 5 | $0.00041 | $0.00439 |
| Sonnet 5 | $0.00016 | $0.00175 |
| Haiku 4.5 | $0.00008 | $0.00088 |
Grade A, and why
using-reviews-locally 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.
How it starts
The opening of the file, as written. The whole thing — 104 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Using Reviews Locally
Use this skill for local Reviews workflows from a checkout of this repo.
Start the Server
Use the project script:
lsof -iTCP:4000 -sTCP:LISTEN
./bin/server
Do not run mix phx.server directly unless you know OAuth/env loading is unnecessary. ./bin/server sources .env.local and runs Phoenix on http://localhost:4000.
Local CLI Config
The CLI reads ~/.config/reviews/config.toml and currently uses [default].
Expected shape:
[default]
server_url = "http://localhost:4000"
api_token = "rev_..."
If the user's real default points to Fly, avoid editing it casually. For one-off local pushes, create a temporary home/config:
mkdir -p /private/tmp/reviews-local-home/.config/reviews
# write /private/tmp/reviews-local-home/.config/reviews/config.toml
HOME=/private/tmp/reviews-local-home cli/target/release/reviews push --update <slug>
Mint Local Tokens
Preferred path:
- Open
http://localhost:4000/settings. - Sign in locally.
- Generate an API token.
- Use it in the CLI config.
Fallback for Codex when the local signed-in user exists and direct DB access is appropriate:
POSTGRES_HOST=localhost POSTGRES_PORT=<port> mix run -e 'user = Reviews.Repo.get_by!(Reviews.Accounts.User, username: "local-codex"); {:ok, _token, raw} = Reviews.Accounts.mint_token(user, %{"name" => "codex-local-push"}); IO.puts(raw)'
Find the DB port by inspecting the running BEAM process connections if needed:
lsof -nP -iTCP:4000 -sTCP:LISTEN
lsof -p <beam-pid> | rg "localhost:.*->localhost:"
Local and hosted tokens are not interchangeable.
Push Reviews and Revisions
Create a new review:
cli/target/release/reviews push --packet /path/to/packet.md
Append a patchset:
cli/target/release/reviews push --update <slug> --packet /path/to/packet.md
Push current uncommitted work:
cli/target/release/reviews push --update <slug> --range HEAD --packet /path/to/packet.md
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 · 104 lines · 82 tokens per session scan A 61d8a9c74b78
using-reviews-locally is a skill published in the GitHub repository figitaki/reviews (6 stars, last pushed 7d ago), licensed MIT. It adds 82 tokens to every session and 877 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.