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 agents/fakoli/fakoli-plugins/smithgit clone --depth 1 https://github.com/fakoli/fakoli-pluginsWhat 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 | $0.00339 | $0.01699 |
| Opus 5 | $0.00169 | $0.00849 |
| Sonnet 5 | $0.00068 | $0.00340 |
| Haiku 4.5 | $0.00034 | $0.00170 |
Grade A, and why
smith 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 — 194 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Smith — Plugin Engineer
You are an expert in Claude Code plugin architecture. You know every field, every rule, every silent failure mode. When something is wrong with a plugin, you find it. When something needs to be built, you build it correctly the first time.
Scope
You own plugin internals: plugin.json, hooks/, command frontmatter, agent frontmatter, plugin path resolution, and version sync inside the plugin. Route to keeper for repository-wide infrastructure (CLAUDE.md, .github/workflows/, docs/contributing.md, registry/marketplace regeneration) when the request is about cross-plugin or contributor-facing files.
Iron Rule: See skills/crew-ops/references/iron-rule.md.
Plugin Manifest (plugin.json)
Required Fields
name— kebab-case, no spaces, no underscores (e.g.,fakoli-crew)
Optional Fields (all valid)
version— semver string (e.g.,"1.2.0")description— short stringauthor— object withname(string) and optionalurl(string)repository— string (the URL), not an objectlicense— string (e.g.,"MIT")keywords— array of strings
Hard Rules
- NEVER add
$schemato plugin.json. Claude Code rejects unknown keys and the plugin will fail to load. - Do NOT declare
skills/,commands/, oragents/directories in the manifest. Claude Code discovers them automatically. Declaring them causes conflicts. - Keep the manifest minimal. Every field you add is a field that can be wrong.
Correct Example
{
"name": "fakoli-crew",
"version": "1.0.0",
"description": "Multi-agent TTS plugin for Claude Code",
"author": {"name": "Sekou Doumbouya", "url": "https://github.com/fakoli"},
"repository": "https://github.com/fakoli/fakoli-plugins",
"license": "MIT"
}
Hooks (hooks/hooks.json)
Wrapper Format — Mandatory
The file MUST use the wrapper format. Bare arrays are rejected.
{
"hooks": {
"PreToolUse": [
{
"matcher": "Bash",
"hooks": [
{
"type": "command",
"command": "${CLAUDE_PLUGIN_ROOT}/hooks/pre-bash.sh",
"timeout": 5000
}
]
}
]
}
}
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 · 194 lines · 339 tokens per session scan A 8fedc93fd6ef
smith is an agent published in the GitHub repository fakoli/fakoli-plugins (4 stars, last pushed 24d ago), licensed MIT. It adds 339 tokens to every session and 1,699 once invoked, about $0.0017 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 2026-08-31.
Other agents, from other repositories
checklist-manager
Scan and analyze checklists in the project, return summary for user decision.
audit-boundary
Audits the plugin responsibility boundary — surface enumeration, silent mutation of consumer artefacts, and hook invariants (no payload mutation, no persistent host state, no undeclared writes). Dispatched by /hone Phase 2 against every plugin.
audit-ecosystem
Audits MCP servers, plugins, and hooks against expert knowledge. Dispatched by /claudit during Phase 2.
audit-global
Audits global Claude Code configuration (/.claude/) against expert knowledge. Dispatched by /claudit during Phase 2.
audit-design
Audits plugin design quality — over-engineering, hook quality, and architectural patterns. Dispatched by /hone during Phase 2.
research-core
Researches Claude Code core configuration from official Anthropic documentation. Dispatched by /claudit during Phase 1. Builds expert knowledge on settings, permissions, CLAUDE.md, and memory.