audit-loop

Name: audit-loop
Author: minghinmatthewlam

34stars4forks

How to install audit-loop?

minghinmatthewlam/agent-guards/audit-loop

$npx -y skills add minghinmatthewlam/agent-guards --skill audit-loop

Installs into the current project.

Summary

Lightweight read-only audit. Use host-appropriate review coverage for evidence and findings. Iterate on disagreement or low confidence. No code changes.

Files · 1

View on GitHub

SKILL.md

1	# Audit Loop
2
3	Read-only audit with review coverage appropriate to the current host. No code changes.
4
5	Planning before implementation → use `plan-loop` instead.
6	Reviewing completed code changes → use `review-loop` instead.
7
8	## Prerequisites
9
10	Read `~/dev/agent-guards/AGENTS.md` before starting — the safety and workflow conventions that govern all agent work.
11
12	## How It Works
13
14	1. Investigate the question. Collect evidence (files, commands, source material).
15	2. Review your findings per `references/review-protocol.md`. Spin up all review agents in parallel using the host-specific coverage rules. Pre-warm any deferred tools only when the selected host path actually needs them.
16	3. Iterate if reviewers disagree, confidence is low, or key claims lack evidence.
17	4. Write a final verdict: scope reviewed, evidence basis, findings, residual risks, next steps.
18
19	Every meaningful claim must cite specific files, commands, or source material.
20
21	## Round Sizing
22
23	- Claude host:
24	- R1: 1 native + 1 Codex cross-model.
25	- R2+ only when triggered: confidence below 85, reviewer disagreement, or high-impact finding lacks evidence. Focus on previous round's findings and unresolved gaps — not a fresh re-review.
26	- Escalate to 3+1 for high-risk or persistent disagreement.
27	- Codex host:
28	- R1: 1-2 native reviewers only.
29	- R2+ only when triggered: confidence below 85, reviewer disagreement, or high-impact finding lacks evidence. Focus on previous round's findings and unresolved gaps — not a fresh re-review.
30	- Escalate to 3 native reviewers for high-risk or persistent disagreement.
31
32	## Confidence
33
34	After each round, assess confidence 0-100 with top unknowns and what evidence is still missing:
35	- Below 85: consider another round.
36	- 85+: eligible to close.

People who liked this also viewed

6 picks

Type

hyperframes-cliUse the HyperFrames CLI development loop: init, add, catalog, capture, lint, check, snapshot, compare, grade-compare, preview, play, present, beats, keyframes, single or batch render, publish, cloud, SkillsJul 2026262k37k
request-refactor-planSkills for Real Engineers. Straight from my .agents directory.SkillsJul 2026165k181k
analyze-projectRigor Analyze / Rigor Audit read-only skill for deep learning research repositories. Use when the user wants to read and understand a repository, inspect model structure and training or inference entrSkillsMay 2026161k507
explore-codeRigor Improve implementation leaf skill for auditable candidate implementation in deep learning research repositories. Use when the researcher explicitly authorizes exploratory work on an isolated braSkillsMay 2026161k507
ubiquitous-languageSkills for Real Engineers. Straight from my .agents directory.SkillsJul 2026160k181k
scaffold-exercisesSkills for Real Engineers. Straight from my .agents directory.SkillsJul 2026149k181k

audit-loop

34stars4forks

View on GitHub

How to install audit-loop?

minghinmatthewlam/agent-guards/audit-loop

$npx -y skills add minghinmatthewlam/agent-guards --skill audit-loop

Installs into the current project.

Summary

Lightweight read-only audit. Use host-appropriate review coverage for evidence and findings. Iterate on disagreement or low confidence. No code changes.

Files · 1

View on GitHub

SKILL.md

1	# Audit Loop
2
3	Read-only audit with review coverage appropriate to the current host. No code changes.
4
5	Planning before implementation → use `plan-loop` instead.
6	Reviewing completed code changes → use `review-loop` instead.
7
8	## Prerequisites
9
10	Read `~/dev/agent-guards/AGENTS.md` before starting — the safety and workflow conventions that govern all agent work.
11
12	## How It Works
13
14	1. Investigate the question. Collect evidence (files, commands, source material).
15	2. Review your findings per `references/review-protocol.md`. Spin up all review agents in parallel using the host-specific coverage rules. Pre-warm any deferred tools only when the selected host path actually needs them.
16	3. Iterate if reviewers disagree, confidence is low, or key claims lack evidence.
17	4. Write a final verdict: scope reviewed, evidence basis, findings, residual risks, next steps.
18
19	Every meaningful claim must cite specific files, commands, or source material.
20
21	## Round Sizing
22
23	- Claude host:
24	- R1: 1 native + 1 Codex cross-model.
25	- R2+ only when triggered: confidence below 85, reviewer disagreement, or high-impact finding lacks evidence. Focus on previous round's findings and unresolved gaps — not a fresh re-review.
26	- Escalate to 3+1 for high-risk or persistent disagreement.
27	- Codex host:
28	- R1: 1-2 native reviewers only.
29	- R2+ only when triggered: confidence below 85, reviewer disagreement, or high-impact finding lacks evidence. Focus on previous round's findings and unresolved gaps — not a fresh re-review.
30	- Escalate to 3 native reviewers for high-risk or persistent disagreement.
31
32	## Confidence
33
34	After each round, assess confidence 0-100 with top unknowns and what evidence is still missing:
35	- Below 85: consider another round.
36	- 85+: eligible to close.

People who liked this also viewed

6 picks

Type