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/itechmeat/open-second-brain/claude-mdgit clone --depth 1 https://github.com/itechmeat/open-second-brainWhat 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 | $0.00579 | $0.00579 |
| Opus 5 | $0.00290 | $0.00290 |
| Sonnet 5 | $0.00116 | $0.00116 |
| Haiku 4.5 | $0.00058 | $0.00058 |
Grade A, and why
open-second-brain 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 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 — 51 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
Guidance for agents working in this repository.
Versioning
package.json version is the single source of truth. The version is
mirrored into several manifests (plugin.yaml, plugins/hermes/plugin.yaml,
.claude-plugin/plugin.json, .codex-plugin/plugin.json,
plugins/codex/.codex-plugin/plugin.json, openclaw.plugin.json) and
pyproject.toml.
Never hand-edit the version in those mirrored files. To bump the version,
edit package.json only, then propagate with:
bun run scripts/sync-version.ts
CI gates on bun run scripts/sync-version.ts --check (the validate job,
step "Verify manifest version sync"). Hand-editing one file leaves the
others drifted and fails that gate before any other check runs. Run the
--check form locally before pushing a version change.
WHEN to bump: inside the feature PR, before the first push
The version bump is part of the change itself, NOT a separate later step.
Bump package.json (and run sync-version.ts) on the feature branch and
include it in the SAME pull request as the feature, before you push. Every
release-bearing squash commit on main carries its version in the title -
e.g. feat: … (v1.5.0) (#NN) - because the bump rode in with the feature.
Concretely, for any feature/fix PR that ships a release:
- Add the
CHANGELOG.mdentry under the new## [X.Y.Z] - <date>heading AND its[X.Y.Z]: …/compare/…link-reference at the bottom of the file. - Bump
package.jsontoX.Y.Zand runbun run scripts/sync-version.ts. - Commit both, then push the branch and open the PR.
Do this even though main is protected (direct pushes are rejected; all
changes go through a PR) - which is exactly why the bump cannot be a
post-merge step: a forgotten bump means package.json and the CHANGELOG
heading disagree on main and a second PR is needed to reconcile them.
This OVERRIDES the generic feature-release-playbook default ("do not bump
version mid-PR; bump once in the release phase"). That default assumes a
maintainer can push the bump straight to main at release time; this repo
cannot, so the bump belongs in the feature PR. The GitHub release
(gh release create vX.Y.Z) is published AFTER that PR merges and only tags
the already-bumped commit - it never changes the version.
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 · 51 lines · 579 tokens per session scan A ee94fbbd4512
open-second-brain CLAUDE.md is an instructions file published in the GitHub repository itechmeat/open-second-brain (385 stars, last pushed 5d ago), licensed MIT. It adds 579 tokens to every session, about $0.0029 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 2026-08-30.
Other instructions, from other repositories
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).
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.
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.