Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add commands/naimkatiman/continuous-improvement/auditgit clone --depth 1 https://github.com/naimkatiman/continuous-improvementWhat 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 | $0.00046 | $0.00441 |
| Opus 5 | $0.00023 | $0.00220 |
| Sonnet 5 | $0.00009 | $0.00088 |
| Haiku 4.5 | $0.00005 | $0.00044 |
Grade A, and why
audit 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 3d 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.
What it actually says
/audit — Confirm Recent Commits Before You Trust Them
Run the audit-driven loop over recent work: a merged commit with green CI is a claim, not a proof.
What it does
Takes a commit window, hunts for real defects one concern at a time, proves each finding against the actual code (false positives die before any edit), fixes on a branch with the smallest diff, verifies every surface the fix touches, and reports honestly. Backed by the audit skill.
The loop
1. Scope git log to pick the window (e.g. HEAD~10..HEAD, or main since last release)
2. Find one pass per dimension: value/economy drift, concurrency, surface coverage, type/contract
3. Confirm read the actual lines; state in one sentence why it is real, or dismiss it
4. Fix one concern per commit; prefer a failing test first, then green
5. Verify exercise EVERY surface (backend, frontend, admin, cache, migration), not just the edited one
6. Report confirmed (with the proof), dismissed (with why), no-op (in scope, nothing to change)
Default skeptical
Findings are hypotheses. Default each to a false positive until the code proves the bug — defaulting to "real" is how plausible-but-wrong fixes ship. For a thorough audit, fan the find pass out across dimensions with parallel reviewers, then verify each survivor adversarially.
Pairs with
auditskill — the discipline this command runs.code-review/security-review— the per-dimension passes.reconcile— the safe branch→PR path once the audit produces a fix.recall— check whether a finding was already hit and fixed before.
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.
- 3d ago First seen · 35 lines · 46 tokens per session scan A c644266dc4ea
audit is a command published in the GitHub repository naimkatiman/continuous-improvement (7 stars, last pushed 8d ago), licensed MIT. It adds 46 tokens to every session and 441 once invoked, about $0.0002 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 commands, from other repositories
coder-eval-implement-plan
Implement an approved codereval plan phase by phase with risk-scaled per-phase review, then a final code review.
OPSX: Bulk Archive
Archive multiple completed changes at once.
VibeGuard: Cross Review
Dual-model adversarial review — Claude generates review reports, Codex does adversarial verification, and iterates until convergence.
safe-build
Build the application for development or production.
auto-run
PitWay: Manage auto-run authorization for automatic task continuation.
task-integrate
PitWay: Apply a dispatched task's worktree commit to the main tree.