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/ohswedd/praxis/auditgit clone --depth 1 https://github.com/Ohswedd/praxisWrote 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/commands/ohswedd/praxis/audit)<a href="https://agentmods.dev/commands/ohswedd/praxis/audit"><img src="https://agentmods.dev/badge/commands/ohswedd/praxis/audit.svg" alt="Measured on agentmods" height="20"></a>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 | $0.00018 | $0.00390 |
| Opus 5 | $0.00009 | $0.00195 |
| Sonnet 5 | $0.00004 | $0.00078 |
| Haiku 4.5 | $0.00002 | $0.00039 |
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
Two scopes, one command. Read ${ARGUMENTS} and pick:
Blank, staged, or a narrow focus goes to the quality-rubric skill on the
current change. Scope it with scope.py (never git diff alone: on a branch
that has committed anything it is empty), then dispatch every vertical auditor
(doc-reference,
duplication, regression, adversarial, edge-case, performance, completeness, plus
accessibility and design-consistency whenever the change touches user-facing
surface) and the horizontal consistency pass. Record each verdict with its
evidence as its auditor finishes (report.py vertical <name> --verdict pass --summary "..." --evidence "file:line", which refuses a citation that does not
resolve). Fix every FAIL, re-run the affected auditor, and record the green
report once all pass. End with a compact verdict table.
repo, all, or a path goes to the repo-audit skill over the whole
codebase or that subtree. Run the full pipeline: inventory and shard ledger
(repo_scan.py init), starting report, forward audit of every shard against every
vertical dimension, reverse audit of each finding via @praxis:finding-verifier,
fixes applied in audited change-sets (defer architectural and breaking items with
a remediation plan; --report-only skips fixing entirely), then the
coverage-honest final report and the living-knowledge updates.
Coverage comes from the ledger, not from memory: no shard skipped, no dimension sampled, no finding acted on unverified, and any gap stated explicitly.
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 · 30 lines · 18 tokens per session scan A c844e6ec5f41
audit is a command published in the GitHub repository Ohswedd/praxis (1 stars, last pushed 1mo ago), licensed MIT. It adds 18 tokens to every session and 390 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 2026-08-31.
Other commands, from other repositories
anti-slop-designer
Use when a UI looks machine-made rather than decided. Violet gradients, glassmorphism everywhere, identical cards in a grid, untouched shadcn or Material defaults, emoji bullets, or copy stuffed with seamless and unlock.
design-enforce
Use when code has drifted off the design system. Raw hex values and pixel numbers written where a token already exists, one-off components, library defaults left untouched. Finds every bypass and fixes it.
design-grill
Use when a design keeps getting reinvented every session. Interviews you until you share one understanding, then writes the vocabulary and the binding decisions into the repo so they survive the next context window.
design-triage
Use when a dwic audit report is full of findings and there is no plan. Ranks them into an order someone can work through, then works through it.
wp-init
Scaffold a new WordPress project — copies starter theme, replaces placeholders, generates .claude/CLAUDE.md.
debug-helper
Use when something is broken and you need it diagnosed. A build failure, a runtime crash, a blank page, an unreadable error message, or behaviour that is simply wrong. Gives one exact fix, not a list of things to try.