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 skills/jhostalek/dotclaude/audit-patternsnpx skills add JHostalek/dotclaude --skill audit-patternsgit clone --depth 1 https://github.com/JHostalek/dotclaudeWrote 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/jhostalek/dotclaude/audit-patterns)<a href="https://agentmods.dev/skills/jhostalek/dotclaude/audit-patterns"><img src="https://agentmods.dev/badge/skills/jhostalek/dotclaude/audit-patterns.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 | $0.00066 | $0.02323 |
| Opus 5 | $0.00033 | $0.01162 |
| Sonnet 5 | $0.00013 | $0.00465 |
| Haiku 4.5 | $0.00007 | $0.00232 |
Grade A, and why
audit-patterns scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 3d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 131 lines — stays where its author put it; the contents beside it link to each section on GitHub.
!cat "${CLAUDE_SKILL_DIR}/../shared/audit-workflow.md"
Run as the patterns dimension. Find inconsistent solutions that make behavior, change, or operation unpredictable; do not optimize for textual sameness.
Work top-down
Reconstruct the system before comparing syntax:
- Identify intended behavior, architecture, module and ownership boundaries, domain concepts, public contracts, data and control flows, runtime/deployment variants, extension points, and lifecycle paths. Derive the invariants that equivalent operations must preserve.
- Map each recurring concern to its implementations and consumers. Compare their semantics, failure behavior, side effects, observability, concurrency, performance, and compatibility—not only their names or shapes.
- Establish candidate conventions from repository evidence: authoritative docs and configuration, public contracts, architecture decisions, supported framework idioms for the exact version, maintained shared abstractions, tests that assert intended behavior, and prevalence. No source is conclusive alone.
- Find wide across every applicable baseline area before applying noise filters. Then classify each divergence as defect, worthwhile convergence, intentional variant, migration state, generated/vendor constraint, or unresolved question.
- Trace consequential candidates through exact call paths and across components. Look for emergent inconsistency where individually reasonable implementations compose into incompatible states, retries, identities, formats, or operational behavior.
Do not infer that a pattern is correct because it is the majority, old, new, named conventionally, wrapped in a helper, supplied by a framework, or covered by tests. Prevalence estimates migration cost and expected familiarity; it does not establish intent or safety. A local pattern may be the better authority when it implements a newer contract or fixes a flaw in the majority. Verify the exact context before choosing a target.
Consistency is subordinate to correct domain boundaries. Do not collapse distinct concepts merely because their code looks similar, or force one abstraction across different ownership, latency, transaction, security, platform, or compatibility constraints.
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 · 131 lines · 66 tokens per session scan A 6e6b100b8849
audit-patterns is a skill published in the GitHub repository JHostalek/dotclaude (11 stars, last pushed 29d ago), licensed CC0-1.0. It adds 66 tokens to every session and 2,323 once invoked, about $0.0003 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
hook-template
Generate hook script from template. Use when adding a new hook, wiring a PreToolUse/PostToolUse/Stop/Notification hook, or scaffolding hook config for settings.json.
prompt-sensei
Stage-aware prompt coaching, prompt improvement, lookback analysis, prompting habit feedback, and local reports about prompt quality for AI coding agents such as Claude Code or Codex.
agent-check
Validate custom agent file format and structure. Use after creating or editing an agent, before committing agent changes, or when an agent fails to load.
skill-check
Validate skill/command file format and structure. Use after creating or editing a skill, before committing skill changes, or when a skill fails to load or trigger.
agent-template
Generate custom agent from template. Use when creating a new subagent from scratch, or scaffolding an agent file with correct frontmatter.
session-relay
Continue real repository work between Claude Code, Codex CLI, and Grok Build with a privacy-bounded, drift-aware handoff packet. Use for cross-vendor takeover, context-limit checkpoints, multi-hop Claude→Codex→Grok relays, or receiving an existing Director packet. Use native resume commands for same-CLI history; never…