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 richfrem/agent-plugins-skills --skill l5-red-team-auditorgit clone --depth 1 https://github.com/richfrem/agent-plugins-skillsWrote 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/richfrem/agent-plugins-skills/l5-red-team-auditor)<a href="https://agentmods.dev/skills/richfrem/agent-plugins-skills/l5-red-team-auditor"><img src="https://agentmods.dev/badge/skills/richfrem/agent-plugins-skills/l5-red-team-auditor/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/richfrem/agent-plugins-skills/l5-red-team-auditor"><img src="https://agentmods.dev/badge/skills/richfrem/agent-plugins-skills/l5-red-team-auditor.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Data Exfiltration · line 59 Code scans file system directories looking for sensitive files. This could be reconnaissance for credential theft.Fix: Remove unnecessary filesystem scanning. If file access is needed, use explicit, scoped paths. Avoid reading ~/.ssh, ~/.aws, or credential directories.
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 | $0.00062 | $0.01166 |
| Opus 5 | $0.00031 | $0.00583 |
| Sonnet 5 | $0.00012 | $0.00233 |
| Haiku 4.5 | $0.00006 | $0.00117 |
Grade A, and why
l5-red-team-auditor 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 — 101 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Dependencies
This skill requires Python 3.8+ and standard library only. No external packages needed.
To install this skill's dependencies:
pip-compile ./requirements.in
pip install -r ./requirements.txt
See ./requirements.txt for the dependency lockfile (currently empty — standard library only).
You are acting as an aggressive Enterprise Red Team Security & Architecture Auditor, assessing agent plugins.
Objective: Perform an uncompromising L5 Enterprise Red Team Audit against the 39-point architecture matrix.
Your mission: Find L5 maturity gaps, bypass vectors, determinism failures, Negative Constraint violations, and architectural drift. Do not soften findings. Every gap is a potential production failure.
Context Required
Before analyzing the target plugin, you MUST understand these foundational principles:
plugins reference/agent-scaffolders/skills/analyze-plugin/references/maturity-model.mdplugins reference/agent-scaffolders/skills/analyze-plugin/references/security-checks.mdplugins reference/agent-scaffolders/references/pattern-decision-matrix.md(CRITICAL: Read the 39 architectural constraints)- Architectural Standards (CRITICAL: Evaluate against these universal principles):
- Self-Contained Isolation: Each plugin is fully portable. Zero runtime dependencies on sibling plugins or repo-specific paths.
- Hub-and-Spoke Scripts: Shared scripts live at plugin root; skills use symlinks, never duplicate files.
- File-Level Symlinks Only: No directory-level symlinks; installers resolve to hard copies.
- Loose Coupling: Cross-plugin work flows through natural-language agent skill delegation, never hardcoded imports.
- Portable Frontmatter:
namematches directory slug; description is third-person active; evals useshould_trigger: bool.
Escalation Trigger Taxonomy
If any of the following conditions are met, STOP immediately and flag before proceeding:
shell=Truedetected in any script → CRITICAL: Command Injection Vector- Hardcoded credentials or tokens detected → CRITICAL: Credential Exposure
authorinplugin.jsonis a string or invalid object → CRITICAL: Marketplace Schema Rejection- Duplicate top-level keys in
plugin.json→ CRITICAL: Manifest Parsing Collision - SKILL.md exceeds 500 lines → HIGH: Progressive Disclosure Violation
namefield in frontmatter has spaces or uppercase → HIGH: Naming Standard Violation- No
evals/evals.jsonpresent → MEDIUM: Missing Benchmarking Loop - No
references/fallback-tree.mdpresent → MEDIUM: Missing Fallback Procedures
What ships with it
5 files 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 Changed · +5 lines 4723c2c27515
- 8d ago First seen · 96 lines · 62 tokens per session scan A 2cf8a49ea5c9
l5-red-team-auditor is a skill published in the GitHub repository richfrem/agent-plugins-skills (6 stars, last pushed today), licensed MIT. It adds 62 tokens to every session and 1,166 once invoked, about $0.0003 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 2026-09-03.
Other skills, from other repositories
akirule
Aki's contextual rule router — invoke BEFORE acting whenever the task touches any of - .md/.vue/.css/.tsx/.rs/.sql files; docs, plan, README, CHANGELOG; UI, component, CSS, tailwind; SEO, schema, sitemap; release, version, commit, push, deploy; DB schema, migration; Tauri; i18n, UI copy; pricing, biz; UX review…
report
Something went wrong or made the work harder — recorded where it belongs, and if it is the skill's own defect, packaged into a file you can send.
akithink
Structured deep-thinking session between agent and human for important decisions — restate the problem, excavate the goal chain to the ultimate goal, first-principles decomposition (facts/constraints/assumptions), mandatory critique (steelman, inversion, pre-mortem), then converge into a decision record. For big /…
quick
One job, no company: three questions, one or two agents, build then review.
bug
The urgent lane that jumps the queue — a defect, recall or correction, reproduced before it is fixed.
ship
The go-live step, whatever live means here: gates green, release notes, tag, announce, ledger.