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 IAbhishekJhaI/brain --skill brain-docsgit clone --depth 1 https://github.com/IAbhishekJhaI/brainWrote 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/iabhishekjhai/brain/brain-docs)<a href="https://agentmods.dev/skills/iabhishekjhai/brain/brain-docs"><img src="https://agentmods.dev/badge/skills/iabhishekjhai/brain/brain-docs/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/iabhishekjhai/brain/brain-docs"><img src="https://agentmods.dev/badge/skills/iabhishekjhai/brain/brain-docs.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 | $0.00162 | $0.02126 |
| Opus 5.5 | $0.00065 | $0.00850 |
| Sonnet 5.5 | $0.00032 | $0.00425 |
| Haiku 4.5 | $0.00016 | $0.00213 |
Grade A, and why
brain-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 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 — 174 lines — stays where its author put it; the contents beside it link to each section on GitHub.
brain-docs — a living project memory
Chat sessions end; the reasoning behind code shouldn't. This skill maintains a
brain/ folder of three documents that together act as the project's memory:
| File | Holds | Answers |
|---|---|---|
brain/decisions.md |
Dated decision log (newest first) | "Why is it built this way?" |
brain/flow.md |
Whole-system execution flow | "What calls what, in what order?" |
brain/todo.md |
Tagged action items, caveats, ideas | "What's known-broken, known-limited, or worth doing?" |
The system only works if the docs are updated incrementally, as you work — not in a batch when someone remembers to ask. A future session (or a future maintainer) relies on them being current.
There are two modes. Check whether brain/ exists in the project root:
- No
brain/folder, or the user asks to set one up → Setup mode. brain/exists → Maintain mode.
Setup mode
-
Create
brain/in the project root and seed the three files fromassets/templates/(in this skill's folder). Adapt each file's title line to the project's name; keep the maintenance blockquotes — they remind future sessions of the rules even if this skill doesn't load. -
Ask whether
brain/should be git-ignored. Don't assume — this is a real tradeoff the user owns:- Git-ignored (local): the notes can be candid — honest tradeoffs, "this is a hack", API-billing gripes — because nobody else reads them. But they live on one machine and won't reach teammates or CI.
- Committed: the whole team (and every future clone) shares the memory,
at the cost of writing for an audience.
Apply their choice (add
brain/to.gitignore, or not).
-
Install the standing rule into the project's
CLAUDE.md(create the file if it doesn't exist) by inserting the block fromassets/claude-md-snippet.md. This step is what makes the system work:CLAUDE.mdis loaded every session unconditionally, while a skill only loads when triggered — so the always-on update discipline must live there. If aCLAUDE.mdexists, add the block near the top and adapt its wording to sit naturally in the file; don't duplicate it if a version is already present.
What ships with it
5 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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 Changed · +11 lines 635f110afc33
- 1mo ago First seen · 163 lines · 162 tokens per session scan A d9b895ef4182
brain-docs is a skill published in the GitHub repository IAbhishekJhaI/brain (3 stars, last pushed 1mo ago), licensed MIT. It adds 162 tokens to every session and 2,126 once invoked, about $0.0006 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
agent-log
Use this skill to maintain an agent log in .agents/log, a decision journal shared by the developer and agents. Trigger when the user explicitly asks to use agent-log or record/update an agent log entry; when planning, implementing, or finalizing a significant feature in a repo with an existing .agents/log; or before…
paired-session
Use in exactly four cases - the user explicitly asks for paired-session, the review-loop entry hands off because .review-loop/config.md sets entry: paired-session, the review-loop entry hands off because that key is absent or invalid (the default entry), or the review-pr skill hands off on its paired route; with…
reorganize
Reorganize code file structure: rearrange modules, extract reuse, remove redundancy, add section comments. Preserves all functionality and logic.
review-loop
Codex review-loop entry. Resolves the entry key and hands a work item (fresh work, an existing plan, or a review of existing code) to the Codex paired-session skill, which drives plan → review → implement → CR up to acceptance.
code-quality-loop
Iterative review-fix loop on the uncommitted change: with lifecycle on, reviews, fixes, simplifies and consolidates tests, as a paired-session review-only run (run --review-only). The legacy loop was removed in v2.13.0: entry: legacy, --legacy and --reorganize are refused.
guide
Codex guide for review-loop - the paired-session entry, review-pr and the shared .review-loop/config.md.