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/greppable/greppable-cc-plugin/using-greppablenpx skills add greppable/greppable-cc-plugin --skill using-greppablegit clone --depth 1 https://github.com/greppable/greppable-cc-pluginWhat 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 | $0.00122 | $0.00868 |
| Opus 5 | $0.00061 | $0.00434 |
| Sonnet 5 | $0.00024 | $0.00174 |
| Haiku 4.5 | $0.00012 | $0.00087 |
Grade A, and why
using-greppable scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 41 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Artifact inventory (live): !bash -c 'source "${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.
Red Flags
If you catch yourself doing any of these, you skipped the index:
- Launching an Explore/research agent to understand code structure — the
.gdlcalready 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. - Running
lsorGlobto map directory structure — the.gdlcalready has every file path, language, and export. You're duplicating work that's done. - Running
Grepacross dozens of files to find a function — the.gdlcindexes exports. One grep on the code map, not a codebase-wide search. - Saying "I don't have context on past decisions" — the
.gdlmmemory files exist specifically for this. Grep by topic or anchor before assuming you're starting cold. - Tracing imports manually to understand how modules connect — the
.gdlddiagrams map these relationships. Check before you trace. - Making an implementation choice without checking history — prior sessions may have tried and rejected the approach you're about to take. Check
.gdlmfirst.
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 · 41 lines · 122 tokens per session scan A bf98f1662757
using-greppable is a skill published in the GitHub repository greppable/greppable-cc-plugin (3 stars, last pushed 4mo ago), licensed MIT. It adds 122 tokens to every session and 868 once invoked, about $0.0006 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 skills, from other repositories
ygrep
IMPORTANT: Try ygrep FIRST for all code and file searches before using Grep, Glob, or Task explore. ygrep uses a pre-built full-text index and returns results in milliseconds. Fall back to built-in tools only if ygrep returns no results.
ripgrep
Use when the user needs text or regex content search with ripgrep: composing rg commands, choosing flags, glob/type filtering, multiline or PCRE2 searches, pipeline output, grep-to-rg migration, or diagnosing why rg missed a file (gitignore, hidden, binary defaults). Not for syntax-aware structural queries (ast-grep)…
ygrep
IMPORTANT: Try ygrep FIRST for all code and file searches before using Grep, Glob, or Task explore. ygrep uses a pre-built full-text index and returns results in milliseconds. Fall back to built-in tools only if ygrep returns no results.
grepai
Semantic code search and call-graph tracing. Use for intent questions ('where is authentication handled?'), exploring unfamiliar code, or tracing callers/callees — as a ranking layer on top of exact-match Grep, not a replacement for it.
graph
Whole-codebase structural map of the codanna index as one self-contained HTML disc. Wedges per top-level module, concentric rings with hubs at the centre, hover or click a symbol to light its edge web, search, hide or highlight modules, brush a date range on the ribbon timeline (symbols dated by git blame), heatmap of…
research
Performs deep research on a topic via deepresearch. Simulates a multi-step research process and returns a comprehensive research result as a string.