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 commands/greppable/greppable-cc-plugin/aboutgit 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 | $0.00026 | $0.00637 |
| Opus 5 | $0.00013 | $0.00318 |
| Sonnet 5 | $0.00005 | $0.00127 |
| Haiku 4.5 | $0.00003 | $0.00064 |
Grade A, and why
about scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured yesterday.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 69 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/greppable:about — Cross-Layer Search
Search across all 7 GDL layers for a topic. Returns formatted results grouped by layer.
Usage
/greppable:about TOPIC [directory] [--layer=LAYER] [--exclude-layer=LAYERS] [--summary] [--regex] [--ignore-case]
Implementation
Source the tools and call gdl_about:
source "${CLAUDE_PLUGIN_ROOT}/scripts/gdl-tools.sh"
gdl_about "$TOPIC" "${DIR:-.}" ${SUMMARY:+--summary} ${REGEX:+--regex} ${IGNORE_CASE:+--ignore-case} ${EXCLUDE_LAYER:+--exclude-layer=$EXCLUDE_LAYER}
Arguments
TOPIC(required): The search term — literal string by default, regex pattern with--regexdirectory(optional): Search scope, defaults to current directory--layer=LAYER: Filter to specific layer (gdl, gdls, gdlc, gdla, gdld, gdlm, gdlu)--exclude-layer=LAYERS: Skip comma-separated layers (e.g.,--exclude-layer=gdlm,gdlu). Complement of--layer.--summary: Compact output with counts only--regex/-E: Use extended regex instead of literal matching (enables patterns like(auth|security),^@T.*TOPIC,type:decision)--ignore-case/-i: Case-insensitive search (findsGL_ACCOUNTwhen searchinggl_account)
Progressive Disclosure
- First show summary (which layers matched, count per layer)
- If user asks for more detail, show full matching records
- If user asks about a specific layer, drill into that layer's tool functions
Examples
/greppable:about GL_ACCOUNT
/greppable:about authentication --layer=gdlc
/greppable:about GL_ACCOUNT --summary
Pattern Recipes
# Find entities matching a prefix
/greppable:about 'GL_[A-Z]+' . --regex
# Multi-keyword search (OR)
/greppable:about '(auth|security|access)' . --regex --ignore-case
# Filter to specific record types
/greppable:about '^@T.*Customer' . --regex --layer=gdls
# Find field values across layers
/greppable:about 'type:decision' . --regex --layer=gdlm
# Case-insensitive entity lookup
/greppable:about parser . --ignore-case
# Search everything except memory and diagrams
/greppable:about 'Customer' . --exclude-layer=gdlm,gdld
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.
- yesterday First seen · 69 lines · 26 tokens per session scan A 0bb7cac71642
about is a command published in the GitHub repository greppable/greppable-cc-plugin (3 stars, last pushed 4mo ago), licensed MIT. It adds 26 tokens to every session and 637 once invoked, about $0.0001 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 commands, from other repositories
rb-ask
Ask a question about the current project's codebase via the repobrain knowledge hub. / 通过 repobrain 知识库询问当前项目代码。.
rb-refresh
Rebuild the repobrain project knowledge base after significant changes. / 在重要改动后重建 repobrain 项目知识库。.
performance-review
You goal is to measure and improve performance.
rp-build-cli
Build with rp-cli context builder → chat → implement.
call-graph
Trace callers, callees, or paths using the call graph.
index
Index the codebase for semantic search.