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/activitynpx skills add anthonysuherli/br8n --skill activitygit 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/activity)<a href="https://agentmods.dev/skills/anthonysuherli/br8n/activity"><img src="https://agentmods.dev/badge/skills/anthonysuherli/br8n/activity.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 5.1 | $0.00083 | $0.00545 |
| Opus 5 | $0.00042 | $0.00272 |
| Sonnet 5 | $0.00017 | $0.00109 |
| Haiku 4.5 | $0.00008 | $0.00055 |
Grade A, and why
activity 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 5d 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.
What it actually says
br8n — Activity
The cross-repo lens. While /br8n:pickup replays one repo+branch, activity
answers "what have I been doing, everywhere" — backed by a knowledge graph that
accumulates automatically on every br8n_capture. Nothing to build; just query.
The graph's ontology: repo, branch, file, session, task nodes, related by
on_repo, on_branch, in_repo, edited, viewed, pursued.
Step 1 — Query the graph
Call mcp__plugin_br8n_br8n__br8n_activity:
- A natural-language
queryseeds a semantic subgraph ("what touches the store layer", "the KG work"). Omit it for the whole (capped) graph. - Optional
reponarrows to one repository.
It returns {nodes, edges, summary} — summary is a ready-to-show natural-language
rollup; nodes/edges are the graph slice for anything more detailed.
Step 2 — Answer
Lead with the summary (repos, tasks, files in view). Then, if the user wants
specifics, read the nodes/edges:
- Tasks (
type: task) — the intents pursued, distilled from hypotheses. - Sessions (
type: session) — individual captures;propertiescarrycaptured_at,repo,branch,hypothesis. - Files (
type: file) — what was edited vs. viewed (the edgerelation). - Follow
edited/pursued/on_repoedges to connect a file or task back to the repos and sessions that touched it.
When to reach elsewhere
- Single repo+branch "where was I" →
/br8n:pickup(richer card for the here-and-now). - A question needing external knowledge →
/br8n:search(grounds + fills the gap).
The activity graph is read-only here — it grows on its own as captures happen.
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.
- 5d ago First seen · 44 lines · 83 tokens per session scan A 18e8f8e142fc
activity is a skill published in the GitHub repository anthonysuherli/br8n (1 stars, last pushed 1mo ago), licensed MIT. It adds 83 tokens to every session and 545 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…
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。.
acontext-installer
Install Acontext, Login & Init Acontext Project, Add Skill Memory to Agent.
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.
web-translator
Extract web page content and convert to Markdown format while preserving structure, images, tables, and links. Use when converting web pages to Markdown for further processing.