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/conn-castle/agent-layer/audit-testsnpx skills add conn-castle/agent-layer --skill audit-testsgit clone --depth 1 https://github.com/conn-castle/agent-layerWrote 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/conn-castle/agent-layer/audit-tests)<a href="https://agentmods.dev/skills/conn-castle/agent-layer/audit-tests"><img src="https://agentmods.dev/badge/skills/conn-castle/agent-layer/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 | $0.00027 | $0.00618 |
| Opus 5 | $0.00014 | $0.00309 |
| Sonnet 5 | $0.00005 | $0.00124 |
| Haiku 4.5 | $0.00003 | $0.00062 |
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 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 — 73 lines — stays where its author put it; the contents beside it link to each section on GitHub.
audit-tests
Audit tests and fix clear negative-value or mechanical problems.
Scope
- Default to all tests; accept paths, modules, repository-defined tiers, and a report limit that does not reduce coverage.
- Derive tiers from repository configuration. If ambiguous, audit concrete tests without tiers and report the limitation.
Write .agent-layer/tmp/audit-tests.<run-id>.report.md, using
YYYYMMDD-HHMMSS-<short-rand> for run-id.
Contract
- Findings identify concrete tests, behavior, and evidence; coverage percentage alone is not a finding.
- Delete tautological, self-confirming, dead, rubber-stamp, or duplicate tests, preserving the strongest behavioral coverage.
- Make mechanical assertion, naming, tier, helper, and fixture repairs when the intended behavior is established.
- Add behavior-focused tests for material gaps when the expected behavior is established.
- Do not delete partially valuable tests or change production for testability without a user decision. Replace false coverage only for a clear behavior contract.
- Ignore framework conventions and style preferences that do not affect value.
Workflow
Read COMMANDS.md before selecting commands. Identify the test runner, configuration, conventions, fixtures, helpers, and tiers. Inventory the scope. For large scopes, parallelize non-overlapping read-only investigations; the owning agent validates candidates, reconciles gaps/duplication, and edits.
Review:
- duplicate scenarios, setup, assertions, helpers, and fixtures
- false, fragile, dead, misleading, or misplaced tests
- unexpected I/O, network, sleeps, or other tier violations
- material gaps in failures, boundaries, interactions, or critical workflows
Use coverage when documented and useful, reusing results until edits invalidate them. Apply safe deletions, consolidation, and mechanical fixes. Leave judgment-dependent work untouched. Fix material gaps with behavior-focused tests; report only gaps that require a user decision.
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 · 73 lines · 27 tokens per session scan A bf74af5bd187
audit-tests is a skill published in the GitHub repository conn-castle/agent-layer (10 stars, last pushed yesterday), licensed MIT. It adds 27 tokens to every session and 618 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
gtplanner
使用 GTPlanner 生成项目规划和技术架构文档。当用户需要： (1) 生成 PRD 或产品需求文档 (2) 规划项目架构 (3) 技术选型和推荐 (4) 创建详细设计文档 (5) 分析项目可行性 时触发此 skill。支持中英日西法五种语言。 触发词："PRD"、"项目规划"、"架构设计"、"技术方案"、"设计文档"。.
dividend-analysis
Comprehensive capital allocation analysis: dividends, buybacks, M&A, debt management, and FCF deployment.
position-ladder
Plan a staged position — entry ladder, share-count floor/ceiling, and the trim/re-add cycle that lowers average cost — with lot accounting, wash-sale checks, total-return honesty, and a thesis-break exit gate.
report-generator
Generate professional HTML/PDF investment reports with interactive visualizations.
stock-eval
Evaluate US stocks with comprehensive fundamental and valuation analysis.
stock-valuation
Multi-method stock valuation using DCF, comparable company analysis, EV multiples, and residual income models.