What is dataclaw AGENTS.md?

Project instructions for DataClaw, a tool that exports Claude Code, Codex and other coding-agent conversations to Hugging Face. They define a staged process for authentication, configuration, review and publishing, including a privacy check for personal data.

Checking export status, choosing conversation and project scope, setting redacted strings, reviewing an export, confirming it and publishing it to Hugging Face.

They prevent exports from being published before the required review and confirmation steps. Following the tool's next-step instructions reduces the risk of skipping configuration or sending unreviewed conversation data.

How peteromallet/dataclaw configures Codex and OpenCode

About the project

DataClaw is an agent harness that turns coding-agent conversation histories into structured datasets and publishes them to Hugging Face. It is used by people who want to share or reuse records of human–AI coding collaboration.

peteromallet/dataclaw · 2,125 stars · on GitHub

Reuse

Borrowing it

Nothing to install: this file belongs to peteromallet/dataclaw. 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/peteromallet/dataclaw/main/AGENTS.md

Clone the repo

git clone --depth 1 https://github.com/peteromallet/dataclaw

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/peteromallet/dataclaw/agents-md/github.svg)](https://agentmods.dev/instructions/peteromallet/dataclaw/agents-md)

Your own site

<a href="https://agentmods.dev/instructions/peteromallet/dataclaw/agents-md"><img src="https://agentmods.dev/badge/instructions/peteromallet/dataclaw/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/peteromallet/dataclaw/agents-md"><img src="https://agentmods.dev/badge/instructions/peteromallet/dataclaw/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 1,395 This file is loaded in full into every session.

When invoked 1,395 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	$0.01395	$0.01395
Opus 5.5	$0.00558	$0.00558
Sonnet 5.5	$0.00279	$0.00279
Haiku 4.5	$0.00139	$0.00139

Measured 2mo ago against content hash 7b08ba4ce9a8, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

dataclaw 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 · 98 lines

How it starts

The opening of the file, as written. The whole thing — 98 lines — stays where its author put it; the contents beside it link to each section on GitHub.

DataClaw

Export Claude Code, Codex, and other coding-agent conversation history to Hugging Face.

THE RULE

Every dataclaw command outputs next_steps. FOLLOW THEM.

Do not memorize the flow. Do not skip steps. Do not improvise. Run the command -> read the output -> follow next_steps. That's it.

Runtime guidance follows this checklist:

Install
Install skill
Prep 3A. Choose source scope 3B. Choose project scope 3C. Set redacted strings
Export locally
Review and confirm
Publish

The CLI tracks your stage as 1-4: auth -> configure -> review -> done. dataclaw export (push) is gated - you must run dataclaw confirm first or it will refuse.

Getting Started

Run dataclaw status (or dataclaw prep for full details) and follow the next_steps.

Output Format

dataclaw prep, dataclaw config, dataclaw status, and dataclaw confirm output pure JSON
dataclaw export outputs human-readable text followed by ---DATACLAW_JSON--- and a JSON block
Always parse the JSON and act on next_steps

Key fields:

stage / stage_number / total_stages - where you are
next_steps - follow these in order
next_command - the single most important command to run next (null if user input needed first)

PII Audit (Stage 5)

After dataclaw export --no-push, follow the next_steps in the JSON output. The flow is:

Ask the user their full name - then grep the export for it
Run the pii_commands from the JSON output and review results with the user
Ask the user what else to look for - company names, client names, private URLs, other people's names, custom domains
Deep manual scan - sample ~20 sessions (beginning, middle, end) and look for anything sensitive the regex missed
Fix and re-export if anything found: dataclaw config --redact "string" then dataclaw export --no-push
Run dataclaw confirm with text attestations - pass --full-name, --attest-full-name, --attest-sensitive, and --attest-manual-scan. It runs PII scan, verifies attestations, shows project breakdown, and unlocks pushing.
Push only after explicit user confirmation: dataclaw export --publish-attestation "User explicitly approved publishing to Hugging Face."

Read the full file on GitHub · 98 lines

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 · 98 lines · 1,395 tokens per session scan A 7b08ba4ce9a8

Subscribe to this mod's changes

dataclaw AGENTS.md is an instructions file published in the GitHub repository peteromallet/dataclaw (2,125 stars, last pushed 27d ago), licensed MIT. It adds 1,395 tokens to every session, about $0.0056 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 2026-08-30.

dataclaw AGENTS.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
dataclaw AGENTS.mdpeteromallet/dataclaw	Instructions file	2.1k	27d ago	MIT	A	1,395	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

dataclaw: Instructions file for Codex