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-securitynpx skills add JHostalek/dotclaude --skill audit-securitygit 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-security)<a href="https://agentmods.dev/skills/jhostalek/dotclaude/audit-security"><img src="https://agentmods.dev/badge/skills/jhostalek/dotclaude/audit-security.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 | $0.00090 | $0.03810 |
| Opus 5 | $0.00045 | $0.01905 |
| Sonnet 5 | $0.00018 | $0.00762 |
| Haiku 4.5 | $0.00009 | $0.00381 |
Grade A, and why
audit-security scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 4d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 168 lines — stays where its author put it; the contents beside it link to each section on GitHub.
!cat "${CLAUDE_SKILL_DIR}/../shared/audit-workflow.md"
Run as the security dimension. This is defensive review of software the user authorized. Find how the system can violate confidentiality, integrity, availability, privacy, tenant isolation, or control of privileged actions; do not reduce the task to matching a vulnerability checklist.
Work top-down
Start with the system, not grep patterns:
- Reconstruct the security model from code, configuration, infrastructure, schemas, manifests, lockfiles, tests, and docs: assets, sensitive data, actors, identities, privileges, trust boundaries, entry and egress points, data/control flows, tenants, dependencies, deployment/runtime, administrative paths, recovery paths, and security assumptions.
- Derive likely attacker goals and abuse paths. Include unauthenticated, ordinary-user, cross-tenant, compromised dependency/integration, malicious insider, and operational-misconfiguration perspectives when relevant. Invent additional actors and paths the system implies.
- Inspect architecture-wide controls and dangerous compositions first. Then trace concrete paths from controllable source through transformations and checks to security-sensitive sink or state change. Review both missing controls and controls that exist but can be bypassed, raced, confused, downgraded, or misconfigured.
- Apply the mandatory baseline across every applicable component and boundary. Expand it for domain-specific surfaces such as payments, healthcare, identity providers, browsers, mobile, desktop, cloud, Kubernetes, embedded/OT, cryptography, or AI agents.
Do not assume safety from a framework, UUID, ORM, managed service, “internal” route, environment variable, client-side restriction, or security-looking helper. Verify the exact version, configuration, call path, deployment boundary, and failure mode. Look for emergent flaws between individually reasonable components.
Mandatory security review baseline
This is minimum coverage, not an exhaustive checklist. Apply every relevant lens, add any weakness class suggested by the system or current threat intelligence, and inspect interactions between lenses. “Not listed” never means “out of scope.”
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 · 168 lines · 90 tokens per session scan A 0ef9d6d8165f
audit-security is a skill published in the GitHub repository JHostalek/dotclaude (11 stars, last pushed 1mo ago), licensed CC0-1.0. It adds 90 tokens to every session and 3,810 once invoked, about $0.0005 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.
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.
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.
agent-template
Generate custom agent from template. Use when creating a new subagent from scratch, or scaffolding an agent file with correct frontmatter.