What is claw-task-hub AGENTS.md?

Project instructions for Claw Task Hub, a local task-management application designed for AI agents and agent tools.

Use them when changing the project so work follows its local-only defaults, keeps generated files untracked, and runs the required build, lint, regression, and harness checks.

They give coding agents the project’s rules for local data, security, external tracker imports, documentation, and release checks.

How Catfish-75/claw-task-hub configures Codex and OpenCode

Reuse

Borrowing it

Nothing to install: this file belongs to Catfish-75/claw-task-hub. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/Catfish-75/claw-task-hub/main/AGENTS.md

Clone the repo

git clone --depth 1 https://github.com/Catfish-75/claw-task-hub

Made for: Codex, OpenCode.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/catfish-75/claw-task-hub/agents-md/github.svg)](https://agentmods.dev/instructions/catfish-75/claw-task-hub/agents-md)

Your own site

<a href="https://agentmods.dev/instructions/catfish-75/claw-task-hub/agents-md"><img src="https://agentmods.dev/badge/instructions/catfish-75/claw-task-hub/agents-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.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/catfish-75/claw-task-hub/agents-md"><img src="https://agentmods.dev/badge/instructions/catfish-75/claw-task-hub/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 472 This file is loaded in full into every session.

When invoked 472 The same file — it is already loaded in full.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

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	$0.00472	$0.00472
Opus 5.5	$0.00189	$0.00189
Sonnet 5.5	$0.00094	$0.00094
Haiku 4.5	$0.00047	$0.00047

Measured 2mo ago against content hash 7c117a0fcfca, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

claw-task-hub AGENTS.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 2mo 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.

AGENTS.md · 24 lines

What it actually says

Claw Task Hub Project Instructions

Product name: Claw Task Hub.
This repository is a local-first, Linear-like task hub designed primarily for AI agents and agentic harnesses.
Keep the product universal across harnesses. MCP-compatible agents, CLIs, and local automation runners are the target surface.
Use relative repository paths in documentation and code examples. Do not commit machine-specific install paths, LAN addresses, proxy settings, VPN settings, or user names.
Default API behavior must remain local-only. Non-loopback binding requires an explicit unsafe flag and must be documented as unsupported for public deployment without additional authentication.
The default local database is under data/; generated SQLite files, logs, screenshots, reports, and scratch files must stay untracked.
External tracker imports must stay in standalone operator tools and must not appear in normal API, CLI, or MCP runtime paths.
Normal Claw Task Hub work must not depend on any external ticketing account or hosted tracker.
Run core checks before release-oriented changes are considered done:
- npm run build
- npm run lint
- npm run store-regression
- npm run harness-smoke
- npm run ui-smoke
- npm run public-hygiene
Use docs/AGENTIC_HARNESS.md as the canonical agent and harness contract.
Use context bindings for project-bound harness startup. Bind stable keys such as repository remote, working directory, branch, or thread id to the owning project; never store secrets in binding metadata.
Use visible issue identifiers such as CTH-272, LOCAL-1, or imported historical identifiers in conversation and tool calls.
New issues must be filed under an explicit owning project id from list_projects; never infer or copy a default project id from unrelated examples.
Do not store secrets in issues, comments, docs, tests, fixtures, or screenshots.
In PowerShell, do not pass raw JSON to npm run hub -- tools/call when payloads contain comments, Markdown, quotes, backticks, or newlines. Use base64:<json> or .\tools\cth-call.ps1 -Tool <tool> -InputObject $payload instead of hand-escaping quotes.

Changes

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.

2mo ago First seen · 24 lines · 472 tokens per session scan A 7c117a0fcfca

Subscribe to this mod's changes

claw-task-hub AGENTS.md is an instructions file published in the GitHub repository Catfish-75/claw-task-hub (2 stars, last pushed 1mo ago), licensed MIT. It adds 472 tokens to every session, about $0.0019 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.

agentic ai-agents local-first mcp sqlite task-management

claw-task-hub AGENTS.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
claw-task-hub AGENTS.mdCatfish-75/claw-task-hub	Instructions file	2	1mo ago	MIT	A	472	Codex, OpenCode
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

claw-task-hub: Instructions file for Codex