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 AleksandarBisevac/claude-plugins/plugin install auditWrote 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/aleksandarbisevac/claude-plugins/audit-codebase)<a href="https://agentmods.dev/skills/aleksandarbisevac/claude-plugins/audit-codebase"><img src="https://agentmods.dev/badge/skills/aleksandarbisevac/claude-plugins/audit-codebase/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/aleksandarbisevac/claude-plugins/audit-codebase"><img src="https://agentmods.dev/badge/skills/aleksandarbisevac/claude-plugins/audit-codebase.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 | $0.00088 | $0.00493 |
| Opus 5.5 | $0.00035 | $0.00197 |
| Sonnet 5.5 | $0.00018 | $0.00099 |
| Haiku 4.5 | $0.00009 | $0.00049 |
Grade A, and why
audit-codebase 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 1mo 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
Auditing a codebase with the audit plugin
This skill exists to be found, not to explain anything. Everything it knows is one of three files; read the one that matches and follow it exactly.
Do not use this for
A one-shot review of the working diff or a pull request. /review, /security-review and
the native code-review tooling are the right answer there, and reaching for a manifest to
look at ten changed lines is pure overhead. This is for work that spans sessions and has to
survive being interrupted.
Route
Check for a manifest first — docs/audit/audit-plan.json by default, or manifestPath in
.claude/audit.config.json.
| Situation | Command |
|---|---|
| No manifest yet | /audit:init — generates one from the codebase |
| A manifest exists, and the question is "where are we" | /audit:status |
| A manifest exists, and the question is "what now" | /audit:next |
| Run the next phase end to end | /audit:phase <id> |
| Something is not working and it is not obvious why | /audit:doctor |
Read ${CLAUDE_PLUGIN_ROOT}/commands/<name>.md and do what it says. Those files are the
source of truth; nothing here restates their procedure, because two copies of a procedure
is one copy and one lie.
The one thing worth knowing before starting
/audit:init spawns several agents and is the most expensive command here. If the person
has not committed to the pipeline yet, /audit:usage --backfill costs nothing, reads
transcripts already on disk, and shows them what their existing work has cost — see the
audit-spend skill. That is a better first move than a manifest they did not ask for.
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.
- 1mo ago First seen · 41 lines · 88 tokens per session scan A f172f3a68dfd
audit-codebase is a skill published in the GitHub repository AleksandarBisevac/claude-plugins (4 stars, last pushed 3d ago), licensed MIT. It adds 88 tokens to every session and 493 once invoked, about $0.0004 per session on Opus 5.5. 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
apex-review
Cross-cutting review of recent work — catches gaps between specialists. Use when asked to "review what we built", "check the work", "pre-launch review", or after completing a significant chunk of work.
touch-audit
Mobile audit — app size, startup time, crash reporting, store compliance, accessibility, offline behavior. Use when asked for "mobile review", "app store readiness", "mobile performance", or "crash analysis".
prism-audit
Frontend audit — bundle size, dependencies, accessibility, performance, component quality. Use when asked for "frontend review", "performance audit", "accessibility check", or "bundle size".
lsp-investigate
Investigate code using LSP tools. Register a project, then use definitions, references, call hierarchies, type hierarchies, hover, and diagnostics to understand code structure, trace bugs, and assess change impact.
trace-incident
Traces a production symptom to its cause and produces a minimal hotfix plan at .workflow/incident- /sdd.json with a timeline. Use when something is broken in production now.
improve
Use after /audit flags problem areas, or directly on a smell/antipattern/family, to apply the smallest corrective refactor and verify it with the project's own detected commands. The FIX action reached from the audit report's Recommended Actions handoff (/fix-risks ). Resolves the selection against the glossary and…