Borrowing it
Nothing to install: this file belongs to ComputerSaysNull/claude-delegate-local-mcp. 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/ComputerSaysNull/claude-delegate-local-mcp/main/CLAUDE.mdgit clone --depth 1 https://github.com/ComputerSaysNull/claude-delegate-local-mcpWrote 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/computersaysnull/claude-delegate-local-mcp/claude-md)<a href="https://agentmods.dev/instructions/computersaysnull/claude-delegate-local-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/computersaysnull/claude-delegate-local-mcp/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/computersaysnull/claude-delegate-local-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/computersaysnull/claude-delegate-local-mcp/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 | $0.02651 | $0.02651 |
| Opus 5.5 | $0.01060 | $0.01060 |
| Sonnet 5.5 | $0.00530 | $0.00530 |
| Haiku 4.5 | $0.00265 | $0.00265 |
Grade A, and why
claude-delegate-local-mcp 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 5d 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 — 157 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
Traps and invariants for anyone — human or agent — editing this repository. Terse on purpose: it assumes you can read code, and it exists to stop mistakes that are cheap to make and expensive to find.
Not a summary of docs/ARCHITECTURE.md. That explains how the system works and why.
This lists what will bite you.
Commands
python scripts/docs_gate.py --mode pre-commit # structural checks, by hand
python scripts/install_hooks.py # installs the commit-msg hook
python scripts/docs_gate.py --owner <path> # which document owns this file
python scripts/gen_config_docs.py # after touching config.py
python scripts/gen_agents_docs.py # after touching either agents directory
python scripts/gen_tools_docs.py # after touching tools.py
python scripts/plan_stack.py # the stack, and the commands to ship it
python -m pytest -q # parallel by default, `-n 0` for serial
bwrap needs Linux or WSL. Your own machine's paths go in the gitignored CLAUDE.local.md.
Documentation ownership
Every file under src/, scripts/, .github/ and .claude/ has exactly one owning
document, or is explicitly declared unowned. Changing the code means updating its owning document in the
same commit. The gate blocks otherwise.
Do not memorise the mapping and do not copy it here — scripts/docs_ownership.toml is the
only copy, and a second one is the drift this whole scheme exists to prevent. Ask instead:
python scripts/docs_gate.py --owner src/claude_delegate_local/paths.py
→ docs/AGENTS.md
Rules a machine cannot check, so they land here:
- A fact belongs to exactly one document, and to exactly one plane. Project plane is
the repo root (where are we, why did we choose this). Product plane is
docs/(how does it work). If you find yourself explaining a config default in prose, stop — link. docs/TROUBLESHOOTING.mdowns zero facts. It is a symptom index. It links to whichever document owns the answer and never restates it. Restating a default inside a symptom explanation is exactly how the project this descends from ended up documenting one setting three different ways.- Generated documents are never hand-edited.
docs/CONFIGURATION.mdanddocs/TOOLS.mdare rendered from code. Edit the source, run the generator. - Blocked by the gate and genuinely right anyway? Add a trailer:
Docs-Gate-Skip: owning-doc -- pure rename, no behaviour change. It is echoed in every run and audited, so it is visible rather than quiet. Two skips on one document in ninety days is a signal that something is wrong with the document, not with the rule.
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.
- 5d ago Changed · -2 lines · -38 tokens per session 8e089570f7ec
- 1mo ago Changed · +2 tokens per session 02750cbcc860
- 1mo ago Changed · -4 lines · -104 tokens per session bb682467162a
- 1mo ago Changed · -2 tokens per session d251bc3c5e5f
- 1mo ago Changed · -30 tokens per session e07e2f4da894
- 1mo ago Changed · +1 lines · +23 tokens per session 7f0dadd15169
- 1mo ago Changed · +2 lines · +38 tokens per session 8e15b8ac5e8b
- 1mo ago Changed · -3 lines · -39 tokens per session 5f5d70d69c98
- 1mo ago Changed · +5 lines · +107 tokens per session 0b2be2ecf32e
- 1mo ago First seen · 158 lines · 2,694 tokens per session scan A a0c9b9709119
claude-delegate-local-mcp CLAUDE.md is an instructions file published in the GitHub repository ComputerSaysNull/claude-delegate-local-mcp (0 stars, last pushed yesterday), licensed MIT. It adds 2,651 tokens to every session, about $0.0106 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 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).
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.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).
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 copilot-instructions.md
Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).
deepseek-harness AGENTS.md
AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.