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-complexitynpx skills add JHostalek/dotclaude --skill audit-complexitygit 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-complexity)<a href="https://agentmods.dev/skills/jhostalek/dotclaude/audit-complexity"><img src="https://agentmods.dev/badge/skills/jhostalek/dotclaude/audit-complexity.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 | $0.00029 | $0.02673 |
| Opus 5 | $0.00015 | $0.01337 |
| Sonnet 5 | $0.00006 | $0.00535 |
| Haiku 4.5 | $0.00003 | $0.00267 |
Grade A, and why
audit-complexity scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 4d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 141 lines — stays where its author put it; the contents beside it link to each section on GitHub.
!cat "${CLAUDE_SKILL_DIR}/../shared/audit-workflow.md"
Run as the complexity dimension. Reduce the effort and risk required to understand, change, operate, and remove the scoped system while preserving its legitimate behavior. Net LOC reduction is useful evidence, not the objective: a smaller diff can still make state, coupling, or failure behavior harder to reason about.
Work top-down
Reconstruct what the system must do before deciding what is unnecessary:
- Identify intended behavior, users and callers, domain invariants, public and internal contracts, trust and ownership boundaries, state transitions, lifecycle paths, operational constraints, and failure consequences from code, configuration, schemas, manifests, tests, docs, and history.
- Map the architecture and change surface: components, dependencies, data/control flow, sources of truth, extension mechanisms, generated or reflective behavior, concurrency, deployment modes, and where one concept is represented or decided more than once.
- Find architecture-wide complexity first: unclear ownership, scattered policy, duplicated state, cyclic or long dependency paths, leaky layers, mode interactions, and special cases whose combined behavior cannot be predicted locally. Then trace representative end-to-end paths, including failure, retry, startup, shutdown, migration, rollback, and compatibility paths when relevant.
- Apply the baseline to every applicable component and boundary. Derive extra probes for the actual domain rather than forcing the system into the named examples.
Do not infer simplicity or necessity from a framework, familiar pattern, abstraction name, helper, test presence, static reference count, file size, or superficially concise construct. Verify the exact call path, runtime registration, configuration, lifecycle, and consequence. Conversely, do not remove an abstraction merely because it has one implementation: it may encode a real boundary, policy, substitution seam, generated contract, or ownership constraint.
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.
- 4d ago First seen · 141 lines · 29 tokens per session scan A 9258025d000f
audit-complexity is a skill published in the GitHub repository JHostalek/dotclaude (11 stars, last pushed 1mo ago), licensed CC0-1.0. It adds 29 tokens to every session and 2,673 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 skills, from other repositories
auto-loop
TDD-based autonomous development loop with checkpoint recovery and observability changelog.
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.