Borrowing it
Nothing to install: this file belongs to egedursun/clawtfup. 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/egedursun/clawtfup/main/AGENTS.mdgit clone --depth 1 https://github.com/egedursun/clawtfupWrote 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/egedursun/clawtfup/agents-md)<a href="https://agentmods.dev/instructions/egedursun/clawtfup/agents-md"><img src="https://agentmods.dev/badge/instructions/egedursun/clawtfup/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.
<a href="https://agentmods.dev/instructions/egedursun/clawtfup/agents-md"><img src="https://agentmods.dev/badge/instructions/egedursun/clawtfup/agents-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 | $0.00969 | $0.00969 |
| Opus 5.5 | $0.00388 | $0.00388 |
| Sonnet 5.5 | $0.00194 | $0.00194 |
| Haiku 4.5 | $0.00097 | $0.00097 |
Grade A, and why
clawtfup 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 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 — 55 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent rules: policy evaluation is mandatory
You are working in a repo that uses clawtfup (OPA + .clawtfup/). Treat this as a hard gate, not optional hygiene.
Required behavior
-
Before you treat a coding task as finished, a batch of edits as safe to ship, or a change as “ready for review”, run the evaluator from the repository root (or pass
--workspaceto that root):clawtfup evaluate --prettyIf
clawtfupis not onPATH, use the project venv and module form:python -m policy_eval evaluate --prettyThe CLI is strict by default: exit code 2 if
allowis false or there are error-severity findings (the JSON report is still printed on stdout). You do not pass a flag to “turn strict on”—that is already the behavior. -
You do not skip this because the diff is “small”, “only docs”, or “obviously fine”. If the command is missing or fails to run, fix the environment (e.g.
pip install -e ., OPA onPATHortools/opa) and re-run—do not silently continue. -
Only use
--no-strictwhen a human explicitly asked for a non-failing exit while inspecting a denied report (e.g. scripting that parses JSON regardless). Agents must not use--no-strictto avoid fixing policy violations. -
If evaluation fails (non-zero exit), read
findings[]and each item’sfeedback.remediation(when present). Implement fixes that satisfy policy, then run the command again until exit 0—or stop and say clearly that policy blocks the change and why. -
Default semantics: the evaluator indexes the working tree on disk (no
git diff HEADfor the default full scan), applies.cfupignorepatterns when that file exists (gitignore syntax), then runs policy on the entire indexed tree by default (inputs.scan_mode:full_tree). Pass--diff-fileor stdin to layer a unified diff on top of the disk index. Use--diff-onlywithout--diff-fileonly when you intentionally scope togit diff HEAD(legacy). Agents must not use--diff-onlyto evade fixes unless the user asked.
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 First seen · 55 lines · 969 tokens per session scan A 3b9d7d265bf9
clawtfup AGENTS.md is an instructions file published in the GitHub repository egedursun/clawtfup (5 stars, last pushed 6mo ago), licensed MIT. It adds 969 tokens to every session, about $0.0039 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).
vscode model-prompts.instructions.md
Model-specific prompt authoring and registry guidelines.