From greppable
REQUIRED before ANY .gdlc, .gdlm, .gdld, .gdls, .gdla, or .gdl file operation. Also triggers on structural questions about code, past decisions, service architecture, or data: 'what did we decide about X', 'how is Y structured', 'what depends on Z', 'what endpoints does W expose', exploring unfamiliar code areas, or choosing between implementation alternatives. This project has pre-indexed knowledge that answers these in one grep. NOT for pure implementation tasks like writing functions, fixing bugs, or styling.
npx claudepluginhub greppable/greppable-cc-pluginThis skill is limited to using the following tools:
Artifact inventory (live): !`bash -c 'source "${CLAUDE_PLUGIN_ROOT}/lib/session-context.sh" 2>/dev/null && gdl_scan_artifacts docs/gdl 2>/dev/null || echo "total:0"'`
Provides UI/UX resources: 50+ styles, color palettes, font pairings, guidelines, charts for web/mobile across React, Next.js, Vue, Svelte, Tailwind, React Native, Flutter. Aids planning, building, reviewing interfaces.
Fetches up-to-date documentation from Context7 for libraries and frameworks like React, Next.js, Prisma. Use for setup questions, API references, and code examples.
Calculates TAM/SAM/SOM using top-down, bottom-up, and value theory methodologies for market sizing, revenue estimation, and startup validation.
Artifact inventory (live): !bash -c 'source "${CLAUDE_PLUGIN_ROOT}/lib/session-context.sh" 2>/dev/null && gdl_scan_artifacts docs/gdl 2>/dev/null || echo "total:0"'
This project has pre-indexed knowledge. Indexed artifacts answer in one tool call what raw exploration takes 10+.
You MUST check the index before reaching for Glob, Grep, or Read to explore. Not after. Before. The index exists so you don't have to traverse the filesystem to answer structural questions.
| When you're about to | Stop. Check this first |
|---|---|
| Explore code — "what's in src/", "where is X defined", "what depends on Y" | grep the .gdlc code map. File paths, exports, imports, dependencies — already indexed. |
| Investigate history — "what did we decide", "why was X built this way", "any prior context on Y" | grep the .gdlm memory files. Decisions, observations, errors from prior sessions — indexed by concept. |
| Trace connections — "how does X talk to Y", "what's the request flow", "blast radius of changing Z" | grep the .gdld diagrams. Architecture flows, sequences, topology — already mapped. |
| Check API shapes — "what endpoints exist", "what auth does Y need", "request/response for Z" | grep the .gdla contracts. Endpoints, schemas, parameters, auth — already extracted. |
| Scan database — "what tables exist", "what's the schema for X" | grep the .gdls schema maps. Tables, columns, PKs, FKs — already indexed. |
Invoke the format-specific skill for detailed grep patterns, tool functions, and write formats.
If you catch yourself doing any of these, you skipped the index:
.gdlc already has every file path, export, and import dependency. One grep on the code map replaces a 30+ tool-call agent. Only use agents after the index proves insufficient.ls or Glob to map directory structure — the .gdlc already has every file path, language, and export. You're duplicating work that's done.Grep across dozens of files to find a function — the .gdlc indexes exports. One grep on the code map, not a codebase-wide search..gdlm memory files exist specifically for this. Grep by topic or anchor before assuming you're starting cold..gdld diagrams map these relationships. Check before you trace..gdlm first.bash -c 'source scripts/... && ...' — zsh has bash incompatibilities