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/anthonysuherli/br8n/docsnpx skills add anthonysuherli/br8n --skill docsgit clone --depth 1 https://github.com/anthonysuherli/br8nWrote 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/anthonysuherli/br8n/docs)<a href="https://agentmods.dev/skills/anthonysuherli/br8n/docs"><img src="https://agentmods.dev/badge/skills/anthonysuherli/br8n/docs.svg" alt="Measured on agentmods" 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 | $0.00084 | $0.00715 |
| Opus 5 | $0.00042 | $0.00358 |
| Sonnet 5 | $0.00017 | $0.00143 |
| Haiku 4.5 | $0.00008 | $0.00072 |
Grade A, and why
docs scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 3d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 63 lines — stays where its author put it; the contents beside it link to each section on GitHub.
br8n — Docs (browse the living doc tree)
br8n distills the per-KB session notes (see /br8n:notes and
../_shared/session-note.md) into a curated documentation
tree at <project_path>/.br8n/docs/. Notes are the source; docs are the synthesis.
This skill reads that tree and presents it; --rebuild forces a refresh. The tree is
git-ignored and regenerated — never hand-edit it; to change what it says, edit the notes
or the note policy and re-distill.
Step 0 — Resolve target
project = git repo basename, kb = git branch, project_path = repo root
(see ../_shared/preamble-first.md):
basename "$(git rev-parse --show-toplevel)" # project
git branch --show-current # kb
git rev-parse --show-toplevel # project_path
No prior tap needed — the docs are plain files in the working tree.
Step 1 — Read the tree
The curated docs are markdown files on disk under <project_path>/.br8n/docs/. Read
them with your own file tools — they're in the working tree, no MCP call needed:
-
Globfor<project_path>/.br8n/docs/**/*.mdto enumerate the tree. -
Readthe files that matter (all of them if small; the relevant subset if large). -
Present a concise map — folders → files — then surface the most relevant doc(s) for the user's query or current intent:
Living docs —
<project>/<kb><folder>/—<file>,<file><file>(top level)
Most relevant:
<path>—<one-line gist>
If the tree is empty or missing, say so and offer --rebuild (Step 2) to generate
it from the notes.
Step 2 — --rebuild (force a refresh)
Trigger when the user passes --rebuild, or when the tree is empty/stale. Call:
mcp__plugin_br8n_br8n__br8n_distill(
project, kb, project_path, force=true
)
It returns {distilled, forced, doc_count, folders, ...}. Report doc_count and
folders so the user sees what was (re)built, then re-read the tree (Step 1) and
present the refreshed map.
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.
- 3d ago First seen · 63 lines · 84 tokens per session scan A 4de403ac9cc0
docs is a skill published in the GitHub repository anthonysuherli/br8n (1 stars, last pushed 1mo ago), licensed MIT. It adds 84 tokens to every session and 715 once invoked, about $0.0004 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
book-to-skill
Converts books and documents (PDF, EPUB, DOCX, HTML, Markdown, plain text, RTF, MOBI/AZW with Calibre) into structured agent skills, extracting frameworks, mental models, principles, techniques, and anti-patterns. Use when the user wants to study a document through GitHub Copilot CLI, Amp, Claude Code, or Hermes…
acontext-installer
Install Acontext, Login & Init Acontext Project, Add Skill Memory to Agent.
doc-translator
将 PDF 格式或 Web Page 格式的源文档转换成保持原排版格式的 Markdown 格式精译中文文档。.
batch-processor
Manage large document processing by splitting into batches and coordinating the full translation workflow (extraction, translation, formatting). Use when handling documents larger than 30 pages, 60 paragraphs, or 6000 words.
markdown-formatter
Format and optimize Markdown content, with special support for post-translation processing. Use when fixing Markdown syntax, adjusting layout, ensuring formatting consistency, or optimizing translated documents.
pdf-reader
Extract text, images, tables, and formulas from PDF documents and convert them to Markdown format while preserving original structure. Use when processing PDF files, extracting content, or converting PDF to Markdown.