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/ractive/hyalo/security-auditnpx skills add ractive/hyalo --skill security-auditgit clone --depth 1 https://github.com/ractive/hyaloWrote 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/ractive/hyalo/security-audit)<a href="https://agentmods.dev/skills/ractive/hyalo/security-audit"><img src="https://agentmods.dev/badge/skills/ractive/hyalo/security-audit.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 | $0.00150 | $0.01720 |
| Opus 5 | $0.00075 | $0.00860 |
| Sonnet 5 | $0.00030 | $0.00344 |
| Haiku 4.5 | $0.00015 | $0.00172 |
Grade B, and why
security-audit scanned grade B with 1 finding 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.
Reaches for credential filesmediumPrivilege escalation
SSH keys, cloud credentials, git-credentials, .npmrc, /etc/shadow: reading these is how a config file becomes a credential leak.
- Can download commands write to arbitrary paths? (overwriting ~/.ssh/authorized_keys, etc.) Downgraded: this mod is about security review, or the phrase is quoted, so it is likely naming the pattern rather than instructing it.
How it starts
The opening of the file, as written. The whole thing — 137 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Security Audit
You are performing a security audit of a Rust codebase. Your goal is to find real, actionable security issues — not to generate a long list of theoretical concerns. Prioritize findings by actual risk: a leaked API key in a fixture is more urgent than a theoretical timing attack on a string comparison.
Audit Structure
Produce a report with these sections. For each section, only include findings — skip "PASS" items unless they are genuinely surprising or counterintuitive. A lean report focused on what needs fixing is more useful than one padded with confirmations of good practices. However, always check and report on dependencies (section 2) even if they look clean — dependency vulnerabilities are silent and a "no issues found" confirmation is valuable there.
1. Secrets & Sensitive Data Scan
This is often the highest-impact finding category because leaked secrets can be exploited immediately, unlike code vulnerabilities that require an attack vector. Scan systematically — open and read every non-binary file, don't just check whether directories are gitignored.
Where to look (read the actual files, don't just check if they exist):
- Test fixtures (JSON, YAML, TOML in
tests/orfixtures/dirs) — open each one and check for real-looking values - Documentation and knowledgebase files — read every
.mdfile in anydocs/,knowledgebase/, or similar directory. Look for infrastructure details, account references, "production" mentions, internal project names, and internal URLs. These files are easily overlooked but often contain the most revealing information about the real infrastructure behind the project - Agent memory and config (
.claude/directory tree) — check committed agent definitions, skill files, and memory indexes for private paths or personal details - Config files (
.env,.env.example,settings.json,settings.local.json) - OpenAPI specs or API reference files — these often contain example data copied from real responses
- Cargo.toml metadata (author emails, repository URLs)
- CI/CD configs
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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 · 137 lines · 150 tokens per session scan B 8fe49cf18d8b
security-audit is a skill published in the GitHub repository ractive/hyalo (24 stars, last pushed today), licensed MIT. It adds 150 tokens to every session and 1,720 once invoked, about $0.0007 per session on Opus 5. A static security scan graded it B with 1 finding (reaches for credential files). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
setup
Scaffold a complete knowledge system. Detects platform, conducts conversation, derives configuration, generates everything. Validates against 15 kernel primitives. Triggers on "/setup", "/setup --advanced", "set up my knowledge system", "create my vault".
reduce
Extract structured knowledge from source material. Comprehensive extraction is the default — every insight that serves the domain gets extracted. For domain-relevant sources, skip rate must be below 10%. Zero extraction from a domain-relevant source is a BUG. Triggers on "/reduce", "/reduce [file]", "extract…
rethink
Challenge system assumptions against accumulated evidence. Triages observations and tensions, detects patterns, generates proposals. The scientific method applied to knowledge systems. Triggers on "/rethink", "review observations", "challenge assumptions", "what have I learned".
verify
Combined verification — recite (description quality via cold-read prediction) + validate (schema compliance) + review (health checks). Use as a quality gate after creating notes or as periodic maintenance. Triggers on "/verify", "/verify [note]", "verify note quality", "check note health".
architect
Research-backed evolution advice for your knowledge system. Analyzes health reports, friction patterns, and derivation history to propose specific changes with research justification. Never auto-implements — proposals require your approval.
ask
Query the bundled research knowledge graph for methodology guidance. Routes questions through a 3-tier knowledge base — WHY (research claims), HOW (guidance docs), WHAT IT LOOKS LIKE (domain examples) — plus structured reference documents. Returns research-backed answers grounded in specific claims with practical…