Borrowing it
Nothing to install: this file belongs to mmnto-ai/totem. 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/mmnto-ai/totem/main/.agents/skills/review-loop/SKILL.mdgit clone --depth 1 https://github.com/mmnto-ai/totemWrote 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/mmnto-ai/totem/review-loop)<a href="https://agentmods.dev/skills/mmnto-ai/totem/review-loop"><img src="https://agentmods.dev/badge/skills/mmnto-ai/totem/review-loop/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/mmnto-ai/totem/review-loop"><img src="https://agentmods.dev/badge/skills/mmnto-ai/totem/review-loop.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 2 findings, up to high
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 →
- high Prompt Injection · line 6 Hidden instructions were detected in comments or invisible text. These could contain malicious directives. Manual review is recommended.Fix: Audit all comments and invisible characters. Remove any instructions that direct the agent to perform unauthorized actions. Use plain, reviewable content.
- medium Excessive Agency · line 20 Skill allows unbounded resource consumption (API calls, storage, compute). Without rate limits or quotas, a compromised or misbehaving agent can cause denial-of-service or cost overruns.Fix: Set explicit rate limits, timeouts, and resource quotas for API calls, file operations, and compute. Implement circuit breakers for runaway loops.
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 | $0.01298 |
| Opus 5 | $0.00011 | $0.00649 |
| Sonnet 5 | $0.00004 | $0.00260 |
| Haiku 4.5 | $0.00002 | $0.00130 |
Grade A, and why
review-loop 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 5d 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 — 43 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Drive the LOCAL pre-push review loop to convergence: run the review, absorb its findings, re-run, and repeat until the CLI reports the round settled — before any external bot pass. The loop state (round chaining, the settle computation, lane coverage) is entirely CLI-owned; this skill is a thin driver. Do not reimplement settle logic or count rounds yourself — read what the CLI reports.
This is NOT the external-bot triage skill. /review-reply handles bot comments on a PR; do NOT invoke external review bots (CodeRabbit, Gemini Code Assist, Greptile) from here. This loop settles local findings first.
The loop
-
Run the review.
totem reviewruns the repo's configured lanes. Do NOT pass--modelunless the user explicitly asked for a one-lane run — an explicit--modelselects a single-lane invocation and never joins the configured fan. Ifreview.lanesis not configured,totem reviewruns the legacy single-lane path and emits NO verdict artifact orlocal-lane:line — this loop's contract requires the verdict artifact, so configurereview.lanesfirst (a single entry suffices). -
Read the reported outcome. The CLI reports the findings, the lane coverage (completed / attempted), the settled state, and the round number. Take them as reported — do not derive
settledyourself. -
If not settled: apply fixes, then re-run. Fix the actionable findings — WARN and CRITICAL are actionable; INFO is cosmetic and can be skipped. Then re-run
totem review; the CLI chains the next round automatically from the prior verdict. An explicit--continues <verdict-hash>override exists for the rare case where the CLI reports a lineage fork you know is wrong (e.g. a rebase it mis-linked) — otherwise let it chain on its own. -
Repeat until settled — or stop honestly. Loop until the CLI reports the round settled. Stop and report if the CLI's max-rounds advisory fires, or a finding is disputed. Never loop forever, and never silently override a disputed finding — a dispute goes to the human.
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.
- 5d ago Changed · +1 lines 85a93c1bb585
- 9d ago First seen · 42 lines · 22 tokens per session scan A 40331a4a7d7c
review-loop is a skill published in the GitHub repository mmnto-ai/totem (17 stars, last pushed today), licensed Apache-2.0. It adds 22 tokens to every session and 1,298 once invoked, about $0.0001 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
cn-check
Install and run the Continue CLI (cn) to execute AI agent checks on local code changes. Use when asked to "run checks", "lint with AI", "review my changes with cn", or set up Continue CI locally.
printing-press-output-review
Internal sub-skill: agentic review of a printed CLI's sampled command output for plausibility issues that rule-based checks can't encode (substring-match relevance, format bugs, silent source drops, ranking failures). Invoked via the Skill tool by the main printing-press skill at Phase 4.85 and printing-press-polish…
rework-rate
Measure and interpret PR rework rate — the emerging 5th DORA metric.
review
Validate plans, execution, or PRs against wish criteria — returns SHIP / FIX-FIRST / BLOCKED with severity-tagged gaps.
review
Adversarial fresh-context review of an increment before it ships. Every finding cites path:line and is re-verified. Use when saying "review", "grill this", or "critique the implementation".
genie-orca-review
Independent, read-only review of a group, a wish, or a PR on Orca — SHIP / FIX-FIRST / BLOCKED with severity-tagged findings. Council and retro are this skill with a different input.