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 instructions/hamchowderr/braynee/claude-mdgit clone --depth 1 https://github.com/hamchowderr/brayneeWhat 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 | $0.01933 | $0.01933 |
| Opus 5 | $0.00966 | $0.00966 |
| Sonnet 5 | $0.00387 | $0.00387 |
| Haiku 4.5 | $0.00193 | $0.00193 |
Grade A, and why
braynee CLAUDE.md 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 yesterday.
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 — 133 lines — stays where its author put it; the contents beside it link to each section on GitHub.
braynee — project instructions
braynee is an Obsidian second-brain Claude Code plugin (TypeScript/Node, hooks +
skills + agents). It is installed as a local CC plugin; the live install runs from
~/.claude/plugins/cache/braynee/braynee/<version>/, the source is this repo.
Hooks: never gate with the if field — self-gate in JS
The Claude Code hook if field (permission-rule syntax like
"if": "Bash(bd create *) || Bash(bd close *)") is version-unreliable and must
not be used. Verified live on 2026-05-24 (cp-068):
- CC 2.1.143: any
if-bearing hook never fires — even a single-pattern"if": "Bash(bd *)". This silently broke the three-way task mirror (beads-todo-remindernever emitted its reminder) and would disable the no-push-to-main guard. - Older CC: the
iffield is ignored, so the hook fires on every Bash command (and duplicated registrations fire N times).
Rule: register Bash hooks with only "matcher": "Bash" (no if) and gate
inside the hook's JS — match the command with a regex and process.exit(0) early
on a non-match, before any side effect. Every gated hook here already does this
(beads-todo-reminder, beads-status-sync, commit-cadence-nudge,
beads-claim-to-branch, beads-dashboard-refresh, mtn-to-beads-sync,
check-no-main-push, branch-name-check).
Testing hooks — two layers
Hook bugs split into "JS logic" and "the CC↔hooks.json boundary" (firing,
additionalContext delivery). The boundary class is invisible to any test that
pipes synthetic stdin into a hook — that's how the if-field bug shipped. So use
both layers:
1. Headless assertions — bin/braynee-self-test (CI)
node bin/braynee-self-test runs in CI (Ubuntu/macOS/Windows, Node 20/22).
Section 8 ("Gated-hook output assertions") feeds matching and non-matching command
JSON to each gated hook and asserts emit on a match, silence on a non-match —
locking the self-gating contract above. Add an assertion here whenever you add or
change a gated hook. Catches JS/regex regressions; does not exercise CC.
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.
- yesterday First seen · 133 lines · 1,933 tokens per session scan A c912dce97cc9
braynee CLAUDE.md is an instructions file published in the GitHub repository hamchowderr/braynee (2 stars, last pushed 6d ago), licensed MIT. It adds 1,933 tokens to every session, about $0.0097 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 instructions, from other repositories
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
next.js AGENTS.md
Instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.