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-pluginnpx skills add richfrem/agent-plugins-skills --skill audit-plugingit 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)<a href="https://agentmods.dev/skills/richfrem/agent-plugins-skills/audit-plugin"><img src="https://agentmods.dev/badge/skills/richfrem/agent-plugins-skills/audit-plugin.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 | $0.00135 | $0.03637 |
| Opus 5 | $0.00068 | $0.01818 |
| Sonnet 5 | $0.00027 | $0.00727 |
| Haiku 4.5 | $0.00014 | $0.00364 |
Grade A, and why
audit-plugin scanned grade A 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 yesterday.
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.
Reads MCP configurationlowAgent snooping
mcp.json carries server URLs and auth tokens; reading it lets a mod discover and abuse other integrations.
| `hooks.json`/`lsp.json`/`.mcp.json` has literal `\n` chars | `Unrecognized token '\'` | Python `json.dump` wrote escaped newlines; file must have real newlines | 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 — 404 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).
Plugin Auditor
Performs comprehensive validation of a Claude Code plugin against structure standards, naming conventions, component requirements, and security best practices.
Step 1: Locate the Plugin
Establish the plugin root:
- Look for
../../../../.claude-plugin/plugin.json-- this is the definitive marker - If user didn't specify a path, check current directory and common locations
- Confirm with user if ambiguous
Step 2: Run Component Validation Scripts
Run the scripts bundled in this plugin (all in scripts/):
# Validate agent files
python ${CLAUDE_PLUGIN_ROOT}/scripts/validate_agent.py agents/my-agent.md
# Validate hooks.json schema
python ${CLAUDE_PLUGIN_ROOT}/scripts/validate_hook_schema.py hooks/hooks.json
# Lint hook scripts
python ${CLAUDE_PLUGIN_ROOT}/scripts/hook_linter.py hooks/
Checks performed: frontmatter structure, required fields (name/description/model/color),
<example> blocks in agent descriptions, hook event names, matcher + hooks array structure.
Validation report format:
## Plugin Validation Report
### Plugin: [name] | Location: [path]
### Summary: [PASS/FAIL with stats]
### Critical Issues ([count]) -- file path + issue + fix
### Warnings ([count]) -- file path + recommendation
### Component Summary -- counts of each type
### Positive Findings
### Overall Assessment: [PASS/FAIL + reasoning]
Step 2b: Auto-Fix Claude Code Load Errors
Before deep validation, run the load-error fixer to catch issues that prevent
Claude Code from loading the plugin at all. These are silent failures — the plugin
simply doesn't load with no useful error until you run /doctor.
What ships with it
60 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 626 B
- assets/templates/agent.md.jinja 43 B
- assets/templates/command.md.jinja 45 B
- assets/templates/execute.py.jinja 45 B
- assets/templates/README.md.jinja 44 B
- assets/templates/SKILL.md.jinja 43 B
- evals/evals.json 1.2 KB
- evals/results.tsv 301 B
- fallback-tree.md 1.4 KB
- plugin.json 32 B
- 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/fallback-tree.md 36 B
- references/hitl-interaction-design.md 46 B
- references/pattern-decision-matrix.md 46 B
- references/patterns/action-forcing-output-with-deadline-attribution.md 82 B
- references/patterns/adversarial-objectivity-constraint.md 69 B
- references/patterns/anti-pattern-vaccination.md 59 B
- references/patterns/anti-symptom-triage.md 54 B
- references/patterns/artifact-embedded-execution-audit-trail.md 74 B
- references/patterns/artifact-generation-xss-compliance-gate.md 74 B
- references/patterns/artifact-lifecycle.md 53 B
- references/patterns/artifact-state-interrogative-routing.md 71 B
- references/patterns/asynchronous-benchmark-metric-capture.md 72 B
- references/patterns/audience-segmented-information-filtering.md 75 B
- references/patterns/category-calibrated-benchmark-anchoring.md 74 B
- references/patterns/category-semantic-deferred-tool-binding.md 74 B
- references/patterns/chained-command-invocation.md 61 B
- references/patterns/chained-commands.md 51 B
- references/patterns/client-side-compute-sandbox-constraint.md 73 B
- references/patterns/complexity-tiered-output.md 59 B
- references/patterns/conditional-step-inclusion.md 61 B
- references/patterns/connector-placeholders.md 57 B
- references/patterns/cyclical-state-propagation-contract.md 70 B
- references/patterns/delegated-constraint-verification-loop.md 73 B
- references/patterns/dual-mode-degradation.md 56 B
- references/patterns/dual-mode-meta-skill.md 55 B
- references/patterns/dual-register-communication-enforcement.md 74 B
- references/patterns/dynamic-specification-fetching.md 65 B
- references/patterns/embedded-deterministic-scoring-formula.md 73 B
- references/patterns/escalation-taxonomy.md 54 B
- references/patterns/evals.json 42 B
- references/patterns/explicit-seed-anchored-determinism.md 69 B
- references/patterns/graduated-autonomy.md 53 B
- references/patterns/graduated-source-attributed-elicitation.md 74 B
- references/patterns/highly-procedural-fallback-trees.md 67 B
- references/patterns/iteration-directory-isolation.md 64 B
- references/patterns/lifecycle-aware-knowledge.md 60 B
- references/patterns/local-interactive-output-viewer-loop.md 71 B
- references/patterns/mandatory-counterfactual-scenario-templating.md 79 B
- references/patterns/mode-invariant-compliance-gate.md 65 B
- references/patterns/multi-actor-operational-coordination-manifest.md 80 B
- references/patterns/multi-dimensional-tone.md 57 B
- references/patterns/multi-modal-routing.md 54 B
- references/patterns/multi-source-synthesis.md 57 B
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.
- yesterday First seen · 404 lines · 135 tokens per session scan A 422e14b52b10
audit-plugin is a skill published in the GitHub repository richfrem/agent-plugins-skills (6 stars, last pushed yesterday), licensed MIT. It adds 135 tokens to every session and 3,637 once invoked, about $0.0007 per session on Opus 5. A static security scan graded it A with 1 finding (reads mcp configuration). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.
Other skills, from other repositories
kapso-whatsapp
How to interact with Kapso WhatsApp from the swarm — read inbound webhook payloads (text AND media), fetch message history, send free-form messages within the 24h session window (and template messages outside it), mark-as-read, show the typing indicator, send reactions, download media, verify webhook signatures, and…
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…
swarm-scripts
Bulk, repeat, fan-out, or data-heavy work: write and run swarm scripts (inline script-run, named script-upsert, durable launch-script-run). Covers the script-vs-tool rubric, the authoring contract (args first, ctx second), the seed catalog, connections and secrets, dbquery, and exposing a script as an API.
attio-interaction
Generic Attio CRM REST API v2 recipes for querying records, upserting companies/people/deals, writing notes/tasks/comments, managing lists, and handling webhooks.
scheduled-task-resilience
Guardrails for polling, scheduled jobs, and long-running external operations. Use whenever a task waits on CI, builds, deploys, browser jobs, or another asynchronous API so work survives heartbeat checks without duplicate delivery.
user-management
How to manage the user registry — creating users for new Slack/GitHub/GitLab/Linear identities, managing aliases, resolving users across platforms. Use when a new human interacts with the swarm or when user identity needs updating.