Borrowing it
Nothing to install: this file belongs to miguelarios/qkb. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/miguelarios/qkb/main/CLAUDE.mdgit clone --depth 1 https://github.com/miguelarios/qkbWrote 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/instructions/miguelarios/qkb/claude-md)<a href="https://agentmods.dev/instructions/miguelarios/qkb/claude-md"><img src="https://agentmods.dev/badge/instructions/miguelarios/qkb/claude-md/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/instructions/miguelarios/qkb/claude-md"><img src="https://agentmods.dev/badge/instructions/miguelarios/qkb/claude-md.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 | $0.01156 | $0.01156 |
| Opus 5.5 | $0.00462 | $0.00462 |
| Sonnet 5.5 | $0.00231 | $0.00231 |
| Haiku 4.5 | $0.00116 | $0.00116 |
Grade A, and why
qkb 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 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 — 70 lines — stays where its author put it; the contents beside it link to each section on GitHub.
qkb — Project Instructions
Hybrid BM25 + vector search for Obsidian-style knowledge-base vaults, with frontmatter treated as
structured metadata. TypeScript (Node ≥20, better-sqlite3 + sqlite-vec, node-llama-cpp,
commander CLI, @modelcontextprotocol/sdk MCP server). Package @miguelarios/qkb, command qkb.
The original Python implementation (qkb-search, v0.3.0) is no longer in the tree; it is on PyPI
and in git history. Source comments that cite legacy/python/... or a *.py module refer to the
last release that still carried it: git show v0.4.3:legacy/python/src/qkb/<module>.py.
Source of truth
- GitHub issues are the roadmap. The MVP is tracked in #19 (sub-issues, label
mvp). File new work as issues with the templates below rather than as plan documents; close issues from PRs (Closes #N). docs/plans/2026-07-20-typescript-rewrite.md— the TypeScript rewrite plan (complete, kept for history).docs/plans/2026-07-06-phase1-mvp.md— the original Python implementation plan, kept for history.docs/GUIDE.md— user guide: how notes are read, declared/sibling fields, related notes, ranking. Keep it in sync with behavior changes.docs/DESIGN.md— technical design.docs/adr/architecture-decisions.md— decision log; ADRs win over DESIGN.md on conflict.docs/PRD.md— success criteria. Primary: ≥8/10 golden queries return the target doc in the top 3.
Commands
npm test # unit tests (vitest, no Ollama, FakeProvider)
npx biome check . && npx tsc --noEmit # lint/format + typecheck
npm run build # tsc -> dist/
Hard rules
- This repo is public. No real names, personal contexts, private hostnames/IPs, or vault content in code, tests, fixtures, docs, or commit messages. Test data uses synthetic values (Alice Smith, example.com,
homelab-traefik-style contexts). The gitleaks pre-commit hook enforces this — if it blocks a commit, fix the data; NEVER--no-verify. - The owner's real golden-query file lives at
~/.config/qkb/golden_queries.yaml— read/run it locally, never copy it (or its contents) into the repo. - The Obsidian vault is read-only. Never write into it.
- Unit tests must pass offline: no model download, no Ollama, no network — use the
fakeprovider. Tests that need a real model live intest/integration/and run only withnpm run test:integration. - Releases: merging a
chore(release): X.Y.ZPR publishes to npm (release on merge — see.github/workflows/release.yml). An agent may open that PR when asked: bumppackage.json+package-lock.json(npm version X.Y.Z --no-git-tag-version) and add a## X.Y.Z (YYYY-MM-DD)section toCHANGELOG.md, nothing else. Merging it, and pushingv*tags, is owner-only.
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 · -2 lines · +80 tokens per session dfa83691e7eb
- 1mo ago Changed · +35 lines · +403 tokens per session 99052acbe1d1
- 2mo ago First seen · 37 lines · 673 tokens per session scan A f2e1ef416e0b
qkb CLAUDE.md is an instructions file published in the GitHub repository miguelarios/qkb (0 stars, last pushed 6d ago), licensed MIT. It adds 1,156 tokens to every session, about $0.0046 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.
qkb CLAUDE.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| qkb CLAUDE.mdmiguelarios/qkb | Instructions file | 0 | 6d ago | MIT | A | 1,156 | Claude Code |
| vscode buildNext.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 9,719 | GitHub Copilot |
| next.js AGENTS.mdvercel/next.js | Instructions file | 143k | yesterday | MIT | A | 7,461 | Codex, OpenCode |
| langchain AGENTS.mdlangchain-ai/langchain | Instructions file | 149k | yesterday | MIT | A | 4,680 | Codex, OpenCode |
| vscode oss-third-party-notices.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 5,516 | GitHub Copilot |
| vscode copilot-instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 3,093 | GitHub Copilot |
| deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness | Instructions file | 274k | 2d ago | MIT | A | 4,313 | Codex, OpenCode |