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 skills add Jamie-BitFlight/claude_skills --skill codebase-auditorgit clone --depth 1 https://github.com/Jamie-BitFlight/claude_skillsWrote 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/jamie-bitflight/claude_skills/codebase-auditor)<a href="https://agentmods.dev/skills/jamie-bitflight/claude_skills/codebase-auditor"><img src="https://agentmods.dev/badge/skills/jamie-bitflight/claude_skills/codebase-auditor/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/jamie-bitflight/claude_skills/codebase-auditor"><img src="https://agentmods.dev/badge/skills/jamie-bitflight/claude_skills/codebase-auditor.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00085 | $0.01920 |
| Opus 5.5 | $0.00034 | $0.00768 |
| Sonnet 5.5 | $0.00017 | $0.00384 |
| Haiku 4.5 | $0.00009 | $0.00192 |
Grade A, and why
codebase-auditor 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.
How it starts
The opening of the file, as written. The whole thing — 179 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Codebase Auditor
One research angle in a multi-angle technical research system. Singular focus: local codebase analysis — reading actual source files to extract behavioral contracts, coding conventions, workflow insertion points, and data availability maps.
Runs independently. Returns all findings as content to the caller.
Input
Audit target received from orchestrator:
$ARGUMENTS
Plugin Context Check
Before running any sub-mode, check whether the target path is inside a plugin directory.
If the target path contains plugins/ as a path component — apply the zip-and-move test to every design decision in this audit:
If this plugin directory were zipped, moved to a new machine, and unzipped at an arbitrary path — would the change still work?
Read plugins/development-harness/docs/plugin-deployment-model.md for the full gotchas and constraints. Key points:
- Plugin scripts cannot reach outside their bundle after installation — no
.claude/utilities/, no sibling plugins, no repo root paths - Any
sys.path.insertthat navigates above the plugin directory breaks after installation - Shared utilities must live inside the plugin bundle or be declared as installable package dependencies
- If the audit covers scripts spanning both
.claude/andplugins/, flag the cross-boundary constraint explicitly in findings
Record the result: plugin-context: YES | NO at the top of your findings output.
Tool Discovery
Before running any sub-mode, identify the best available tools for code exploration. Run these checks once and record the results — do not repeat them per sub-mode.
# Relationship graph (most powerful for traversal — check first)
test -f graphify-out/graph.json && echo "graphify-graph:available" || echo "graphify-graph:absent"
which graphify 2>/dev/null && echo "graphify-cli:available" || echo "graphify-cli:absent"
# Semantic search
which ccc 2>/dev/null && echo "ccc:available" || echo "ccc:absent"
# Faster text search
which rg 2>/dev/null && echo "rg:available" || echo "rg:absent"
# AST-aware search
which ast-grep 2>/dev/null && echo "ast-grep:available" || echo "ast-grep:absent"
which semgrep 2>/dev/null && echo "semgrep:available" || echo "semgrep:absent"
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 · 179 lines · 85 tokens per session scan A 347979978005
codebase-auditor is a skill published in the GitHub repository Jamie-BitFlight/claude_skills (67 stars, last pushed 4d ago), licensed MIT. It adds 85 tokens to every session and 1,920 once invoked, about $0.0003 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 2026-09-03.
Other skills, from other repositories
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…