Borrowing it
Nothing to install: this file belongs to Kahtaf/OpenCandle. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/Kahtaf/OpenCandle/main/.agents/skills/autoreview/SKILL.mdgit clone --depth 1 https://github.com/Kahtaf/OpenCandleWrote 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/kahtaf/opencandle/autoreview)<a href="https://agentmods.dev/skills/kahtaf/opencandle/autoreview"><img src="https://agentmods.dev/badge/skills/kahtaf/opencandle/autoreview.svg" alt="Measured on agentmods" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Excessive Agency · line 27 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
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 | $0.00055 | $0.01334 |
| Opus 5 | $0.00028 | $0.00667 |
| Sonnet 5 | $0.00011 | $0.00267 |
| Haiku 4.5 | $0.00006 | $0.00133 |
Grade A, and why
autoreview 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 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.
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 — 103 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Auto Review
Run the bundled structured review helper as an advisory closeout check for OpenCandle PRs and local branches.
Default PR branch review (base auto-detects from the open PR via gh, falling back to origin/main; pass --base only to override — stacked PRs often target a feature branch, and a wrong base reviews the whole stack):
.agents/skills/autoreview/scripts/autoreview --mode branch --prompt-file .agents/skills/autoreview/references/opencandle-review.md
The npm alias is equivalent and additionally gates on typecheck + unit tests run in parallel with the review:
npm run review:pr
Contract
- Treat output as advisory. Verify every finding by reading the real code path before fixing or reporting it.
- Review the full branch diff, not just the latest commit, unless the user explicitly asks for a commit-only review.
- Prefer small fixes at the right ownership boundary. Do not refactor unrelated code.
- GUI React changes automatically run React Doctor (pinned
[email protected],--scope changedagainst the review base) against changedgui/web/srcReact files and include the structured output in the review bundle. By default, React Doctorerrordiagnostics fail the helper. - Keep Codex as the default engine. Use
--reviewers codex,claudeonly when explicitly requested or when the risk justifies the extra cost. - Do not push just to review. Push only when the user requested push, ship, or PR update.
- Over-budget diffs are split into per-file review batches automatically (
--batch auto, budget--batch-budget 180000chars) so nothing is silently truncated; each batch shares the full diffstat header and results merge into one report. With a panel, cost multiplies (reviewers x batches).--batch offrestores single-bundle truncation, which is reported loudly as a notice. - Deterministic diff signals (
--diff-signals auto) inject advisory trip-wires into the reviewer prompt for recurring OpenCandle regression classes (unguarded GUI routes, direct provider fetches, sqlite schema bumps without migration tests, prompt/routing changes without fixtures, missing changelog). Signals never affect the exit code; the reviewer must confirm or dismiss each. Disable with--diff-signals off. - The final report prints three advisory sections when non-empty:
pre-check signals(diff signals found),notices(truncation or coverage warnings), andout-of-scope advisory findings(reviewer findings on files outside the diff — kept for blast-radius review instead of silently dropped; they never affect the exit code).--json-outputincludes them assignals,notices, andout_of_scope_findings.
What ships with it
4 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.
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 First seen · 103 lines · 55 tokens per session scan A d930c0ae4a25
autoreview is a skill published in the GitHub repository Kahtaf/OpenCandle (22 stars, last pushed 2d ago), licensed MIT. It adds 55 tokens to every session and 1,334 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 2026-08-30.
Other skills, from other repositories
autoreview
Pre-commit/ship code review: Codex default; optional Claude or Pi.
rework-rate
Measure and interpret PR rework rate — the emerging 5th DORA metric.
omh-code-review
This is a Hermes-native code-review workflow skill.
revdiff-plan
Review the last Codex assistant message (plan, analysis, or proposal) with inline annotations in a TUI overlay. Extracts the most recent response from Codex rollout files and opens it in revdiff for review and annotation. Activates on "revdiff-plan", "review plan with revdiff", "annotate plan", "review last response"…
code-reviewer
Code review specialist focused on patterns, bugs, security, and performance.
agent-teams-simplify-and-harden
Implementation + audit loop using parallel agent teams with structured simplify, harden, and document passes. Spawns implementation agents to do the work, then audit agents to find complexity, security gaps, and spec deviations, then loops until code compiles cleanly, all tests pass, and auditors find zero issues or…