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/richfrem/agent-plugins-skills/audit-plugin-l5npx skills add richfrem/agent-plugins-skills --skill audit-plugin-l5git 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/audit-plugin-l5)<a href="https://agentmods.dev/skills/richfrem/agent-plugins-skills/audit-plugin-l5"><img src="https://agentmods.dev/badge/skills/richfrem/agent-plugins-skills/audit-plugin-l5.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 5.1 | $0.00029 | $0.00505 |
| Opus 5 | $0.00015 | $0.00253 |
| Sonnet 5 | $0.00006 | $0.00101 |
| Haiku 4.5 | $0.00003 | $0.00051 |
Grade A, and why
audit-plugin-l5 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 2d 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 — 57 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).
Audit Plugin L5
This skill abstracts the execution of the L5 Enterprise Red Team Auditor. By using this skill, you trigger an uncompromising architecture and security review against the 39-point pattern matrix.
Discovery Phase
Before executing this skill, ensure you know the exact path or name of the plugin you wish to audit (e.g., plugins/oracle-legacy-system-analysis/xml-to-markdown).
Execution
This skill delegates immediately to the l5-red-team-auditor sub-agent.
Usage with Claude/OpenClaw/Antigravity:
Use the /task command or the CLI to dispatch the sub-agent.
# If using the CLI directly:
claude -p l5-red-team-auditor "Please deeply assess the plugin located at: plugins/[INSERT_PLUGIN_NAME_HERE]"
Output
The sub-agent is instructed to output a structured markdown artifact titled [Plugin_Name]_Red_Team_Audit.md containing:
- L5 Maturity gaps (including
authordictionary schema compliance and zero duplicate manifest keys). - Bypass vectors and injection paths.
- Determinism failures.
- Priority Remediation Checklists.
Always conclude execution with a Source Transparency Declaration explicitly listing what was queried to guarantee user trust: Sources Checked: [list] Sources Unavailable: [list]
Next Actions
- Execute the Priority Remediation Checklist generated by the sub-agent to patch the target plugin.
References
- Architectural Decision Records (ADRs) located at
references/*.md. The L5 Red Team Auditor MUST use these ADRs (especially ADR 001-006) as primary evidence when evaluating architectural maturity and loose coupling. Any deviation from these standards must be flagged as an L4/L5 maturity gap.
What ships with it
17 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.
- acceptance-criteria.md 167 B
- assets/resources/audit-plugin-l5-flow.mmd 52 B
- evals/evals.json 1.3 KB
- evals/results.tsv 301 B
- fallback-tree.md 1.4 KB
- references/acceptance-criteria.md 42 B
- references/ADRs/001_cross_plugin_script_dependencies.md 62 B
- references/ADRs/002_multi_skill_script_centralization.md 63 B
- references/ADRs/003_plugin_skill_resource_sharing_via_mirrored_folder_structure_and_file_level_symlinks.md 113 B
- references/ADRs/004_self_contained_plugins_no_cross_plugin_dependencies.md 81 B
- references/ADRs/005_plugin_separation_of_concerns_and_loose_coupling.md 78 B
- references/ADRs/006_python_native_plugin_bootstrap_installer.md 70 B
- references/architecture.md 35 B
- references/diagrams/audit-plugin-l5-flow.mmd 56 B
- references/fallback-tree.md 36 B
- requirements.txt 22 B
- scripts/execute.py 43 B runs code
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.
- 2d ago First seen · 57 lines · 29 tokens per session scan A a99842a26e21
audit-plugin-l5 is a skill published in the GitHub repository richfrem/agent-plugins-skills (6 stars, last pushed 2d ago), licensed MIT. It adds 29 tokens to every session and 505 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 2026-09-03.
Other skills, from other repositories
composio
Use Composio from Agent Swarm through the agent-swarm x composio CLI route, the swarmx MCP tool, or a registered ctx.api.composio script connection. Trigger when a task needs connected third-party app tools such as Gmail, Google Calendar, Google Docs, Google Drive, GitHub, Slack, Notion, or HubSpot through Tool Router…
close-issue
Close a GitHub or GitLab issue with a summary comment.
soul
Embody this digital identity. Read SOUL.md first, then STYLE.md, then examples/. Become the person—opinions, voice, worldview.
implement-issue
Implement a GitHub issue or GitLab issue and create a PR/MR.
bbc-skill
Fetch Bilibili (哔哩哔哩) video comments for UP主 self-analysis. Use when the user asks to collect, download, export, or analyze comments on a Bilibili video (BV号 / URL / UID). Produces JSONL + summary.json suitable for further Claude Code analysis (sentiment, keywords, audience trends). Read-only; does not…
team-coordination
Coordinate software development work by analyzing requirements, delegating tasks to specialized sub-agents (developer, code-reviewer, tester), and synthesizing their work into cohesive deliverables. Use this for complex projects that require multiple specialized perspectives.