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 skills add thewaltero/mythos-router --skill security-reviewgit clone --depth 1 https://github.com/thewaltero/mythos-routerWrote 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/thewaltero/mythos-router/security-review)<a href="https://agentmods.dev/skills/thewaltero/mythos-router/security-review"><img src="https://agentmods.dev/badge/skills/thewaltero/mythos-router/security-review/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/thewaltero/mythos-router/security-review"><img src="https://agentmods.dev/badge/skills/thewaltero/mythos-router/security-review.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 5.1 | $0.00014 | $0.00328 |
| Opus 5 | $0.00007 | $0.00164 |
| Sonnet 5 | $0.00003 | $0.00066 |
| Haiku 4.5 | $0.00001 | $0.00033 |
Grade A, and why
security-review 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 12d 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.
What it actually says
security-review Skill
Purpose
Use this skill when a task touches command execution, package scripts, CI, deploy files, authentication, secrets, receipts, memory, or user-controlled paths.
Read First
If present, review these before making security-sensitive edits:
- SECURITY.md
- package.json
- .github/workflows/
- src/security-policy.ts
- src/commands/verify.ts
- any file that defines command execution, receipts, secrets, auth, or writable paths
Rules
- Treat install scripts, lifecycle hooks, shell commands, workflows, Docker files, and deploy files as high-risk surfaces.
- Never expose secret values in logs, receipts, docs, tests, or examples.
- Prefer allowlists and structured parsing over broad string matching for security decisions.
- Do not weaken SWD verification, receipt integrity, dry-run behavior, or command review prompts.
- When a change introduces a new writable path, explain how it is constrained.
Verification
- Check that sensitive outputs are redacted before storage.
- Check that command-affecting changes still require explicit human confirmation.
- Prefer read-only verification for CI-facing checks.
Output
When finished, summarize:
- what security-sensitive files changed
- what risks were checked
- what verification was run
- any remaining assumptions or unverified areas
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.
- 12d ago First seen · 48 lines · 14 tokens per session scan A 07bdbdeb15aa
security-review is a skill published in the GitHub repository thewaltero/mythos-router (300 stars, last pushed yesterday), licensed MIT. It adds 14 tokens to every session and 328 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 2026-08-30.
Other skills, from other repositories
code-review
A code-review workflow that sends local changes to a separate reviewer for checks on correctness, style, performance, security, tests, and design.
atomic-review
Compressed code review comments. Cuts noise from PR feedback while preserving the actionable signal. Each comment is one line: location, problem, fix. Use when user says "review this PR", "code review", "review the diff", or invokes /atomic-review. Auto-triggers when reviewing pull requests.
ralphctl-code-review-and-quality
Multi-phase code-quality skill — primary frame for the evaluator role in Execute, the architecture axis in Plan, and correctness/readability in Refine. Multi-axis code review with severity vocabulary. Use when acting as the evaluator assessing a generator's output, and when reviewing any change before signalling…
code-review-helper
A safe skill that helps with code review tasks.
strengthen
Upgrade a vigiles spec's guidance() rules to enforce() — scan the guidance rules in a CLAUDE.md/AGENTS.md spec and find existing linter rules (ESLint, Ruff, Clippy, Pylint, RuboCop, Stylelint) that back them. Use when asked to strengthen, harden, or make vigiles rules enforceable; NOT for general linting or fixing…
refactoring-assistant
A guide for deciding how to improve existing code, including when to refactor it gradually or replace it with a rewrite. Refactoring changes code structure without changing what it is meant to do.