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 skills add rlemaigre/docpack --skill docpack-querygit clone --depth 1 https://github.com/rlemaigre/docpackWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/rlemaigre/docpack/docpack-query)<a href="https://agentmods.dev/skills/rlemaigre/docpack/docpack-query"><img src="https://agentmods.dev/badge/skills/rlemaigre/docpack/docpack-query/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/rlemaigre/docpack/docpack-query"><img src="https://agentmods.dev/badge/skills/rlemaigre/docpack/docpack-query.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What 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 5.1 | $0.00068 | $0.04099 |
| Opus 5.5 | $0.00027 | $0.01640 |
| Sonnet 5.5 | $0.00014 | $0.00820 |
| Haiku 4.5 | $0.00007 | $0.00410 |
Grade A, and why
docpack-query 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 1mo 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 — 366 lines — stays where its author put it; the contents beside it link to each section on GitHub.
docpack Knowledge Base Query
Query a docpack knowledge base -- a portable SQLite database built from a directory of documents. Two files: docpack.db (SQLite) and docpack.yaml (manifest).
Access methods
| Method | When to use |
|---|---|
CLI (npx @rlemaigre/docpack) |
Quick one-shot queries, scripting |
TypeScript library (query()) |
Programmatic access in code |
MCP server (docpack serve --mcp) |
Multi-turn agent sessions, long-lived access |
Token budget guide
Output scales with KB size. These relative orderings hold across KBs. Use chunkCount and totalBytes from toc output to gauge actual sizes.
| Command | Relative cost | Use for |
|---|---|---|
manifest |
tiny | Always start here. KB stats + home slug. |
toc <slug> --depth 1 |
small | Scout structure. Children show chunkCount and totalBytes. |
toc <home> --depth 2 |
medium | Detailed overview of top sections. Usually safe. |
toc <section> --depth 2 |
medium | Check depth 1 first. Scales with section size. |
search "<q>" --limit 5 |
small | Snippet excerpts (~30 tokens per hit). Use --limit 3-10. |
search "title:q" --limit 5 |
tiny | Title-only search. 3–5x smaller than regular search. |
get <leaf> |
small | Single section (depth=0). Best value for content. |
get --slug a --slug b |
small (batch) | Fewer API calls, shared XML wrapper. Skips missing slugs. |
get <internal> |
large | Full subtree. ~10x larger than toc --depth 2 on the same node. |
get <root> |
huge | Avoid. Use toc + targeted get calls instead. |
Rule of thumb: toc for structure, search for discovery, get for content. Never get a root document.
Phase 0: Always start with manifest
npx @rlemaigre/docpack manifest ./mykb
Output (YAML):
version: 0.7.0
totalChunks: 6496
totalBytes: 7436104
home: powerbuilder-2019-users-guide-for-pb-2019
description: null
url: null
exportedAt: 2026-06-23T07:13:56.538Z
Returns version, totalChunks, totalBytes, home (slug of the primary entry file), description, url, and exportedAt.
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.
- 1mo ago First seen · 366 lines · 68 tokens per session scan A 85ec3bcb0f61
docpack-query is a skill published in the GitHub repository rlemaigre/docpack (1 stars, last pushed 4mo ago), licensed MIT. It adds 68 tokens to every session and 4,099 once invoked, about $0.0003 per session on Opus 5.5. 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
orbit-notion
Open Orbit briefing skill — selected by the Orbit pipeline when Notion is the user's only connected connector, or when the user explicitly scopes their daily digest to Notion. Pulls the past 24 hours of document edits, comments, mentions, and database row changes from the user's authenticated Notion connection and…
instrument-data-to-allotrope
Convert laboratory instrument output files (PDF, CSV, Excel, TXT) to Allotrope Simple Model (ASM) JSON format or flattened 2D CSV. Use this skill when scientists need to standardize instrument data for LIMS systems, data lakes, or downstream analysis. Supports auto-detection of instrument types. Outputs include full…
apify-youtube-transcript-scraper
Get YouTube captions, timestamped quotations, SRT/VTT and translated transcripts for videos, channels and playlists through the harshmaur/youtube-transcript-scraper Apify Actor.
legal-hold
Issue, refresh, release, or report on legal holds — drafts the hold notice as .docx, updates legalhold fields in log.yaml, and calendars the next refresh. Use when the user says "issue a hold", "refresh hold", "release hold", or asks for a portfolio-wide hold status report.
baoyu-youtube-transcript
A tool for downloading the written captions, subtitles, chapter information, speaker labels, and cover image from a YouTube video using its URL or ID.
feishu
Work with Feishu or Lark bots, docs, sheets, bitables, approval flows, and OpenAPI/MCP setup without hardcoding credentials.