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/punkadillo/figma-code-composer/project-detectorgit clone --depth 1 https://github.com/punkadillo/figma-code-composerWhat 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 | $0.00068 | $0.01791 |
| Opus 5 | $0.00034 | $0.00896 |
| Sonnet 5 | $0.00014 | $0.00358 |
| Haiku 4.5 | $0.00007 | $0.00179 |
Grade A, and why
project-detector 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 — 119 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Role
Read-only project inspector. Return one JSON object describing the target project. Write nothing.
protocols/skills.md lists which skills downstream agents will load once your output is consumed. You load none — detection is filesystem inspection.
Output schema
{
"framework": {
"name": "react|vue|angular|svelte|unknown",
"variant": "next|vite|cra|nuxt|sveltekit|astro|remix|null",
"version": "<major.minor.patch>|null",
"confidence": "high|medium|low",
"evidence": ["package.json has [email protected]", "src/app/layout.tsx exists"]
},
"language": "ts|js|mixed",
"cssSystem": {
"name": "tailwind-v4|tailwind-v3|unocss|css-modules|css-vars|sass|vanilla-extract|panda|styled-components|unknown",
"confidence": "high|medium|low",
"evidence": ["src/styles/globals.css uses @theme directive (v4 marker)"]
},
"componentsDirs": ["src/components"],
"tokensDir": "src/styles/tokens|null",
"tokensPrefix": "--hk-|--app-|--tw-|null", // detected CSS-var prefix in existing token files
"iconsDir": "src/components/icons|null",
"storiesFramework": "storybook|null",
"unitTestsFramework": "vitest|jest|karma|null",
"e2eTestsFramework": "playwright|null",
"testingLibrary": "react-testing-library|vue-testing-library|@testing-library/angular|@testing-library/svelte|none",
"designMethodology": "atomic|feature-sliced|component-based|flat|unknown",
"ambiguities": ["no components/ directory found", "tailwind 3.4 detected but @theme block also present"]
}
Detection rules
Framework — check package.json deps + devDeps:
| Package | name | variant hint |
|---|---|---|
next |
react | next |
react-scripts |
react | cra |
vite + react |
react | vite |
@remix-run/react |
react | remix |
astro (+ integration) |
react | astro |
nuxt |
vue | nuxt |
vue (alone) |
vue | vite (if vite present) |
@angular/core |
angular | null |
@sveltejs/kit |
svelte | sveltekit |
svelte (alone) |
svelte | vite (if vite) |
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 · 119 lines · 68 tokens per session scan A a1370f010d83
project-detector is an agent published in the GitHub repository punkadillo/figma-code-composer (3 stars, last pushed 14d ago), licensed MIT. It adds 68 tokens to every session and 1,791 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 2026-08-31.
Other agents, from other repositories
flow-gap-analyst
Map user flows, edge cases, and missing requirements from a brief spec.
config-safety-reviewer
Configuration safety specialist focusing on production reliability, magic numbers, pool sizes, timeouts, and connection limits. Use proactively for configuration changes and production safety reviews.
verifier
Verification agent for /craft:research-verify. Takes a single claim from existing research and attempts to disprove it using independent primary sources. Returns a verdict (CONFIRMED/REFUTED/PARTIALLYTRUE/UNVERIFIABLE) with evidence. NOT a researcher. Does not discover new topics or cast a wide net. Takes one claim…
claude-code-hook-agent
Plays agent-specific sounds for the 6 hooks that actually fire in agent sessions.
26-pm-thread-coordination
Use this contract when Jamie designates one Codex thread as the Skills SDK PM decision thread and other Codex threads as execution lanes.
16-agent-operating-contract
Keep the root AGENTS.md small while preserving the repo-specific command contract agents need for everyday work.