Borrowing it
Nothing to install: this file belongs to aahlijia/dekko. 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/aahlijia/dekko/main/CLAUDE.mdgit clone --depth 1 https://github.com/aahlijia/dekkoWrote 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/aahlijia/dekko/claude-md)<a href="https://agentmods.dev/instructions/aahlijia/dekko/claude-md"><img src="https://agentmods.dev/badge/instructions/aahlijia/dekko/claude-md.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 | $0.01613 | $0.01613 |
| Opus 5 | $0.00807 | $0.00807 |
| Sonnet 5 | $0.00323 | $0.00323 |
| Haiku 4.5 | $0.00161 | $0.00161 |
Grade A, and why
dekko 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 — 107 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
Project context for Claude Code (and other agents) working in this repo.
What this project is
dekko is a fast, offline, dependency-free static code map generator and
codebase indexer for LLM coding agents. It parses a repo once with
tree-sitter (no model tokens spent parsing) into MAP.md (human-readable)
and map.json (machine-readable), then answers targeted structural
questions — "who calls this function," "what does this file contain,"
"what tests does this change impact" — without an agent reading whole
files or grepping blind. It ships three ways: a CLI (dekko), a Claude
Code /map plugin + MCP server, and Cline MCP support.
Source lives under src/dekko/, split into subpackages by role:
core/ (parsing primitives — model, extractor, grammars, languages,
walker, resolver), render/ (MAP.md/JSON/HTML/lean/export
rendering), analysis/ (read-side commands — query, outline, search,
affected, trace, unused, stats, summary, workset, contextpack, diff,
relevance, ambiguous, deps, sanity), daemon/ (the daemon process and
its transport), integrations/ (cli, server, hooks, cline, orient,
claude_md, doctor), storage/ (on-disk caches/locks/notes/ledger under
.dekko/), and a handful of modules with no subpackage-specific home
(classify.py, textutil.py, source.py, repo_ops.py) staying
directly under src/dekko/. dekko outline src/dekko/<subpackage>/<file>.py or
dekko query symbol <name> are cheaper ways to get oriented in this
codebase than reading whole files — dekko is a good tool for exploring
its own source. See README.md and docs/ (docs/install.md,
docs/cli.md, docs/claude-code.md) for user-facing docs, and
CONTRIBUTING.md for the dev-setup/test/lint/release commands.
Working in this repo
uv run pytest/uv run ruff check ./uv run ruff format --check .— this is what CI runs; match it locally before considering something done. A project.venvexists (.venv/bin/python -m pytest -qworks equivalently ifuv runisn't available).- Tests live in
tests/, mirroringsrc/dekko/'s subpackages (tests/core/,tests/render/,tests/analysis/,tests/daemon/,tests/integrations/,tests/storage/) for tests that map cleanly to a single moved module; cross-cutting/behavioral tests (exercising several modules or the CLI end-to-end) and tests for the top-level modules stay flat directly undertests/. Test fixtures (tiny sample-language files) live intests/fixtures/. test-repos/holds real, unmodified open-source repos (awesome-go, claude-buddy, claude-code, cline, spring-boot, tensorflow, zed) used as realistic targets for manual/agent evaluation of dekko itself — not part of the pytest suite. It's gitignored (test-repos/in.gitignore), so nothing under it is tracked;test-repos/reports/(see below) is where evaluation write-ups accumulate locally.test-repos/TESTING-GUIDE.mdis the checklist an agent dispatched to test dekko should work from: every CLI command/flag, the MCP tools, the daemon, install/uninstall flows, hooks, and the known-hard cross-cutting correctness cases (overload disambiguation, search relevance, call-graph resolution on trait/interface-heavy code, vendored-dir exclusion, budget capping, staleness). Update it whenever a feature is added or an existing one's behavior changes — a new subcommand, flag, MCP tool, or behavior change isn't done until this guide reflects it; don't leave it to whoever tests next to discover the gap..dekko/MAP.md/.dekko/map.jsonat the repo root are dekko's own generated map of itself, regenerated on demand — expect them to show as modified after runningdekko map; they're git-ignored by default but this repo tracks its own for dogfooding, so check whether a given change is worth including before committing it alongside unrelated work.- Follow the branch/PR conventions in
CONTRIBUTING.md: one conceptual change per PR,feat:/fix:/perf:/docs:/chore:-style commit prefixes (seegit logfor the house style), releases cut by pushing av*tag.
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 Changed · +14 tokens per session 8c3f17e83a30
- 7d ago First seen · 107 lines · 1,599 tokens per session scan A a4a4eb1ccc4c
dekko CLAUDE.md is an instructions file published in the GitHub repository aahlijia/dekko (3 stars, last pushed 6d ago), licensed MIT. It adds 1,613 tokens to every session, about $0.0081 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
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.
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).
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
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).
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.