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 anthonysuherli/br8n --skill journalgit 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/journal)<a href="https://agentmods.dev/skills/anthonysuherli/br8n/journal"><img src="https://agentmods.dev/badge/skills/anthonysuherli/br8n/journal.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 | $0.00093 | $0.00955 |
| Opus 5 | $0.00046 | $0.00477 |
| Sonnet 5 | $0.00019 | $0.00191 |
| Haiku 4.5 | $0.00009 | $0.00096 |
Grade A, and why
journal scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 7d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 78 lines — stays where its author put it; the contents beside it link to each section on GitHub.
br8n — Journal (cross-project, write-anytime, searchable)
The journal is your global notebook, separate from session notes. Session
notes are bound to the current repo+branch and written automatically at session
end; a journal entry is written whenever you choose and is searchable
across every project. Both live in the same ~/.br8n/brain.db; the journal
just uses a reserved, repo-independent scope.
Step 0 — Resolve optional context
The journal itself is global, so a write needs no project. But it's useful to
stamp where you were when you journaled, and scope=project|both searches
need the current repo+branch:
basename "$(git rev-parse --show-toplevel)" # project (optional context)
git branch --show-current # kb
git rev-parse --show-toplevel # project_path
If not in a git repo, omit them (writes still work; scope=project is then N/A).
Mode select — branch on the args
| Invocation | Mode | Do |
|---|---|---|
/br8n:journal <text> |
Write | Step A — save an entry |
/br8n:journal search <query> [--scope both|journal|project] [--type T] |
Search | Step B — recall by meaning |
/br8n:journal recent [N] |
Recent | Step C — list latest entries |
If the first arg is search or recent, use that mode; otherwise treat the
whole input as the text to journal.
Step A — Write an entry
From the user's text, infer a type (one of insight, reflection,
reference, decision) and any obvious tags; when unclear, leave type
empty. Then call:
mcp__plugin_br8n_br8n__br8n_journal(text, type, tags, title, project, project_path)
text— the entry (required).type/tags— your inferred label + keywords (optional).project/project_path— the resolved repo context, if any (optional).
On success it returns {finding_id, entry_path, scope}. Confirm briefly: echo
the one-line title and the type, e.g. "Journaled (decision): prefer scope
filters over separate corpora." Do not paste the whole entry back.
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.
- 7d ago First seen · 78 lines · 93 tokens per session scan A dd00f1a3f019
journal is a skill published in the GitHub repository anthonysuherli/br8n (1 stars, last pushed 1mo ago), licensed MIT. It adds 93 tokens to every session and 955 once invoked, about $0.0005 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
learn
Diagnose and fix agent behavioral surfaces when the user corrects a mistake — connects to Claude native memory.
keep-the-why
Extract and preserve the reasoning code cannot explain - decisions, rejected alternatives, workarounds, incidents, constraints - plus project setup and maintainer interviews. Not for what changed (see Keep a Changelog) - only why.
search
Search the gnosis-mcp knowledge base. Keyword (default), hybrid semantic+keyword (--semantic), or git commit history (--git). Includes sanity checks and a reranker warning.
context
Load usage-weighted context from Gnosis MCP. Surfaces most-accessed docs for session startup or topic primers.
remember
Routes user requests containing "remember", "recall", "checkpoint", "session", "todo", or "where were we" to the correct OpenEmpiric (OEM) MCP tool. Use when the user wants to persist, retrieve, or contextualize knowledge from project memory.
acontext-installer
Install Acontext, Login & Init Acontext Project, Add Skill Memory to Agent.