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-testsnpx skills add JHostalek/dotclaude --skill audit-testsgit 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-tests)<a href="https://agentmods.dev/skills/jhostalek/dotclaude/audit-tests"><img src="https://agentmods.dev/badge/skills/jhostalek/dotclaude/audit-tests.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 | $0.00080 | $0.02969 |
| Opus 5 | $0.00040 | $0.01484 |
| Sonnet 5 | $0.00016 | $0.00594 |
| Haiku 4.5 | $0.00008 | $0.00297 |
Grade A, and why
audit-tests scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 5d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 159 lines — stays where its author put it; the contents beside it link to each section on GitHub.
!cat "${CLAUDE_SKILL_DIR}/../shared/audit-workflow.md"
Run as the tests dimension. Determine whether the suite gives proportionate, trustworthy evidence that the system preserves intended behavior through change. The goal is not more tests or higher coverage; it is strong defect detection with the smallest maintainable suite.
Work top-down
Start from the system's obligations, not test filenames or coverage reports:
- Reconstruct intended behavior and architecture from production code, schemas, configuration, interfaces, migrations, docs, incidents, and tests. Identify critical user journeys, domain invariants, state machines, component and trust boundaries, external contracts, lifecycle transitions, operational modes, and the consequences of failure.
- Map each material risk to the cheapest test level that can falsify the relevant claim with realistic collaborators. Trace evidence across unit, component, contract, integration, end-to-end, and production-validation layers rather than assuming one layer is inherently superior.
- Evaluate the suite as a system: whether its oracles can detect meaningful defects, its environments exercise the real path, failures are attributable, state is isolated, and important cross-component or temporal behavior survives composition.
- Apply the baseline across every applicable boundary and lifecycle. Expand it for domain-specific risks such as financial ledgers, authorization, safety-critical control, distributed workflows, data pipelines, UI accessibility, mobile/offline behavior, infrastructure, or AI systems.
Do not infer protection from a test's name, existence, passing status, coverage line, framework, fixture, mock, snapshot, helper abstraction, or familiar pattern. Verify that the exact production path runs, the oracle would fail for a plausible defect, and the test environment preserves the conditions on which the behavior depends. Collect candidates widely before applying any noise filter.
Mandatory test review baseline
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.
- 5d ago First seen · 159 lines · 80 tokens per session scan A c9a04ffe6c4e
audit-tests is a skill published in the GitHub repository JHostalek/dotclaude (11 stars, last pushed today), licensed CC0-1.0. It adds 80 tokens to every session and 2,969 once invoked, about $0.0004 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.
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-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-template
Generate custom skill/command from template. Use when creating a new skill or slash command from scratch, or scaffolding a skill file with correct frontmatter.
workflow
Run the complete 5-step development workflow: focus problem → prevent over-development → test-first (TDD) → document → smart commit. Use when starting a new feature, or when the user runs /workflow or asks for the full development flow.