tiered-audit
Runs a three-tier codebase audit (git history, targeted scans, full review) with gating. Use when auditing a codebase before release or after incidents.
How do I install this agent skill?
npx skills add https://github.com/athola/claude-night-market --skill tiered-auditIs this agent skill safe to install?
- Gen Agent Trust Hubpass
The 'tiered-audit' skill is a code quality and security review tool that uses git history and targeted file analysis. It includes built-in safety gates for expensive operations and uses a verification script to ensure all findings are grounded in actual source code. No malicious behavior, obfuscation, or safety bypass attempts were detected.
- Socketpass
No alerts
- Snykpass
Risk: LOW · No issues
What does this agent skill do?
Tiered Audit
When To Use
- Auditing codebase quality, patterns, or problems
- Reviewing what changed on a branch before merge
- Investigating areas of instability or churn
- Pre-PR quality assessment
When NOT to Use
- Reviewing a specific file (use pensive:code-reviewer)
- Architecture-only review (use pensive:architecture-review)
- Single-commit review (use imbue:diff-analysis)
Tier 1: Git History Audit
Always runs first. Analyzes git log, diff stats, and blame to identify areas of concern without reading any source files.
What Tier 1 Analyzes
Run the Tier 1 script for the target commit range (default: current branch against the trunk):
python3 "${CLAUDE_PLUGIN_ROOT}/scripts/tiered_audit.py" --base {base}
python3 "${CLAUDE_PLUGIN_ROOT}/scripts/tiered_audit.py" --base {base} --json
It runs four git queries (file churn, fix-on-fix commit
subjects, per-commit diff size, newly added files), applies
the thresholds in pensive.skills.tiered_audit (3+ files in
a module with one changed more than twice, 200+ changed lines
in one commit, 5+ new files in a module), and prints each
flag beside the [E{n}] Command: that produced it, so the
findings file can cite the evidence verbatim. --json adds
escalation_targets and an escalate verdict for Tier 2.
Verification: an empty report on a branch you know is
busy means the range is wrong. Check that {base} resolves
with git merge-base {base} HEAD before trusting a quiet
result.
Tier 1 Output Format
Write findings to .coordination/agents/tier1-audit.findings.md:
---
agent: tier1-audit
tier: 1
evidence_count: {N}
---
## Summary
{1-2 sentence overview of what the git history reveals}
## Churn Hotspots
{top 10 most-changed files with change counts}
For each flagged file, include:
- Location: path/to/file.py:line (most-changed function or block)
- Anchor: `verbatim source text at that line`
[E1] Command: git log --format="" --name-only ...
Output: {relevant output}
## Fix-on-Fix Patterns
{commits that fix previous commits in the same area}
[E2] Command: git log --oneline ... | grep -iE ...
Output: {relevant output}
## New File Clusters
{modules with 5+ new files}
## Large Diffs
{commits with 200+ line changes}
## Escalation Recommendation
{list of areas flagged for Tier 2, or "no escalation needed"}
Escalation Decision
After Tier 1 completes, check findings against the
escalation criteria in modules/escalation-criteria.md.
If NO criteria are met: audit is complete. Report findings.
If criteria ARE met: list flagged areas and proceed to Tier 2 for each area sequentially.
Tier 2: Targeted Area Audit
Runs only for areas flagged by Tier 1. Each flagged area is audited sequentially, one at a time.
What Tier 2 Analyzes
For each flagged area:
- Read the source files in the area
- Check for patterns, anti-patterns, bugs
- Verify test coverage exists
- Check documentation currency
- Assess architectural fit
Tier 2 Output Format
One findings file per area:
.coordination/agents/tier2-{area-name}.findings.md
Each file follows the output contract for audits (see imbue:proof-of-work/modules/output-contracts).
Tier 3: Full Codebase Audit
Requires explicit user approval. See
modules/escalation-criteria.md for the gate protocol.
Tier 3 should use dedicated sessions (one per area) with file-based coordination. Do not dispatch parallel subagents for it.
Output Contract
All tiers use this contract:
output_contract:
required_sections:
- summary
- evidence
min_evidence_count: 3 # Tier 1
# min_evidence_count: 8 # Tier 2
expected_artifacts: []
retry_budget: 1
strictness: normal
Tier 2 raises the minimum evidence count to 8 because it reads source files and should produce deeper analysis.
Verification: After each tier completes, verify the
findings file exists and contains at least the minimum
evidence count ([E1], [E2], etc.) before proceeding
to the next tier or reporting results.
Verify Findings Are Grounded (tiered-audit:findings-verified)
Write findings to .review/findings.json, run the citation verifier
(Skill(imbue:review-core) Step 5), and drop or label UNVERIFIED any
the verifier rejects.
Exit Criteria
- Tier 1 findings file exists at
.coordination/agents/tier1-audit.findings.mdand contains at least 3 evidence entries ([E1]–[E3]). - Tier 2 is only started for areas explicitly flagged by Tier 1 escalation criteria.
- Every reported finding carries a
Location+ verbatimAnchorconfirmed bycitation_verifier.py(exit0), or unverified findings were dropped or labeledUNVERIFIED.
How can the creator link this skill?
Add the canonical catalog link to the repository README so users can inspect current installs and available audits. The publishing guide covers the complete discovery path.
<a href="https://skillzs.dev/skills/athola/claude-night-market/tiered-audit">View tiered-audit on skillZs</a>