Getting it into your agent
This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.
/plugin marketplace add Ohswedd/praxis/plugin install 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/skills/ohswedd/praxis/repo-audit)<a href="https://agentmods.dev/skills/ohswedd/praxis/repo-audit"><img src="https://agentmods.dev/badge/skills/ohswedd/praxis/repo-audit/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/ohswedd/praxis/repo-audit"><img src="https://agentmods.dev/badge/skills/ohswedd/praxis/repo-audit.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00138 | $0.02969 |
| Opus 5 | $0.00069 | $0.01484 |
| Sonnet 5 | $0.00028 | $0.00594 |
| Haiku 4.5 | $0.00014 | $0.00297 |
Grade A, and why
repo-audit scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 10d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 218 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Repo Audit: the whole-codebase scanner
/praxis:audit reviews a change. This skill reviews the repository: an
already-developed project with no fresh diff to anchor on. It applies the same
praxis doctrine (vertical auditors, adversarial verification, completeness,
no silent scope cuts) to the entire codebase, and it is built around one rule:
Coverage is claimed by the ledger, never by memory. Every file is assigned to a shard; every shard × dimension pass is recorded; every finding has a tracked lifecycle. If the ledger says a shard wasn't audited, the final report says so. Laziness is structurally impossible, not just discouraged.
The scan is a pipeline: inventory → starting report → forward audit → reverse audit → fix → final report. Run the phases in order.
Phase 0: Preflight & inventory
- Open a praxis task so the Stop gate self-drives the scan to completion
(size
--maxby shard count; a scan is a large task: 40+ turns):python3 "${CLAUDE_PLUGIN_ROOT}/scripts/task_state.py" open "Repo scan: <repo>" \ --criteria "every shard audited on every dimension" \ "every finding verified" "confirmed findings fixed or explicitly deferred" \ "final report delivered" --max 50 - Check for an existing ledger:
repo_scan.py status. If a scan is already underway, resume it (skip to whichever phase has pending work) instead of re-initialising. - Initialise the ledger (inventory + shard plan):
(Everypython3 "${CLAUDE_PLUGIN_ROOT}/scripts/repo_scan.py" init [--scope <path>]repo_scan.py …below is shorthand forpython3 "${CLAUDE_PLUGIN_ROOT}/scripts/repo_scan.py" ….) It inventories tracked files (pruned of vendored/binary/lock/oversize noise, each exclusion counted), groups them by subsystem, and splits them into shards capped by file/line count.--shard-files/--shard-linestune shard size for very large repos. - Baseline. Note whether the working tree is clean (recommend committing
first so fixes stay separable). Detect the test command (session audit or
common.detect_test_command), run it once now, and record the result in the ledger so the final report can show before/after:
Pre-existing failures are findings in their own right: record them (repo_scan.py baseline --tests "<command>" --exit <observed exit code>regressiondimension) rather than blaming them on later fixes. - Very large repos.
initrefuses to build a silently-truncated inventory: above--max-files(default 20000) it stops and asks you to narrow--scopeor raise the cap. Never work around this by scanning "the important parts" unstated: split into several scoped scans and say so in the report.
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.
- 10d ago First seen · 218 lines · 138 tokens per session scan A b1b01f1784aa
repo-audit is a skill published in the GitHub repository Ohswedd/praxis (1 stars, last pushed 1mo ago), licensed MIT. It adds 138 tokens to every session and 2,969 once invoked, about $0.0007 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 skills, from other repositories
g-review
Run the review gate on the current branch diff. Runs the test suite, captures the diff, and dispatches code-lead, which verifies done conditions and reviews the diff itself. Issues MERGE READY or HOLD.
g-audit
Full-codebase or targeted code quality audit. Detects SOLID violations, code smells, architectural drift, dead code, and test coverage gaps. Targeted scope produces an inline report. Whole-codebase scope produces a prioritised roadmap milestone.
g-refactor
Guided refactor workflow — identify target, pre-analyse, spec, approve, execute, review. Accepts a scope path, an audit milestone file, or runs interactively. Safe-by-default: checks test coverage before execution and runs the full review gate after.
g-blast-radius
Analyse the blast radius of a planned change. Inputs a file path, feature name, or list of paths from a plan. Outputs the set of dependent files (forward and reverse references), a per-file volatility score (commit frequency proxy), and a total blast-radius rating (low / moderate / wide). Read-only.
refine-loop
Runs a safe, resumable refinement loop over a working repository. It discovers behavior-preserving improvements through four evidence-based lenses, ranks them by ROI, applies one small change at a time, verifies independently, and stops deterministically at diminishing returns or a safety limit. Use when explicitly…
no-mistakes
Validate committed feature-branch changes through the no-mistakes pipeline: intent, rebase, review, test, docs, lint, push, PR, and CI. Use when the user asks to run no-mistakes, ship safely, validate before pushing, or gate a change before it reaches upstream.