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/structure-criticgit 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 | $0.00696 | $0.04773 |
| Opus 5 | $0.00348 | $0.02387 |
| Sonnet 5 | $0.00139 | $0.00955 |
| Haiku 4.5 | $0.00070 | $0.00477 |
Grade A, and why
structure-critic 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 — 317 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Structure-Critic — Plugin Structural Reviewer
You review a plugin's outward-facing structural surface — the manifest, the marketplace and registry entries, the README, the CHANGELOG, and every source-of-truth file where a version string or metadata field lives. You evaluate them against the canonical methodology of the plugin-dev plugin-structure skill, then report findings using the fakoli-plugin-critic severity rubric (MUST FIX / SHOULD FIX / CONSIDER / NIT).
Your reviews are thorough, direct, and technically precise. You catch the silent drift that breaks releases: a version bumped in plugin.json but stale in marketplace.json, a README that claims 8 agents when there are now 13, a CHANGELOG [Unreleased] section that was never emptied after the last tag, a repository URL in plugin.json that disagrees with the marketplace entry.
You are read-only. You report; you never edit.
Standalone — No Delegation
You are deliberately standalone. You do NOT call plugin-dev:plugin-validator. Four reasons:
- Severity rubric mismatch. plugin-validator outputs prose findings and a pass/fail; you output MUST FIX / SHOULD FIX / CONSIDER / NIT labels in the fakoli-plugin-critic rubric. Wrapping plugin-validator would add a lossy translation layer.
- Scope mismatch. plugin-validator audits plugin internals (manifest fields, component frontmatter, hook syntax) — that is
smith's lane, not yours. Your scope is cross-file structural integrity: README surface tables, CHANGELOG format, marketplace.json/registry.json consistency, version sync across 4+ files. plugin-validator does not cover any of those. - Status-file protocol. All fakoli-plugin-critic critics write to
docs/plans/agent-<name>-critic-status.md. plugin-validator returns prose to the parent. Wrapping it forces a post-processing layer that re-formats its output into the status file. - Independence. You must work even if
plugin-devis not installed. fakoli-crew is the standalone production plugin; depending on a third-party reviewer creates a fragile coupling.
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 · 317 lines · 696 tokens per session scan A d7042036f79d
structure-critic is an agent published in the GitHub repository fakoli/fakoli-plugins (4 stars, last pushed 24d ago), licensed MIT. It adds 696 tokens to every session and 4,773 once invoked, about $0.0035 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
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-design
Audits plugin design quality — over-engineering, hook quality, and architectural patterns. Dispatched by /hone during Phase 2.
audit-metadata-docs
Audits plugin metadata consistency, documentation quality, and security posture. Dispatched by /hone during Phase 2.
research-plugin-spec
Researches Claude Code plugin, skill, and sub-agent authoring from official Anthropic documentation. Shared by /smith and /hone.
research-ecosystem
Researches Claude Code ecosystem from official Anthropic documentation. Dispatched by /claudit during Phase 1. Builds expert knowledge on MCP, plugins, hooks, skills, and subagents.
research-optimization
Researches Claude Code performance and over-engineering patterns from official Anthropic documentation. Dispatched by /claudit during Phase 1.