Borrowing it
Nothing to install: this file belongs to arrrrny/zuraffa. 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/arrrrny/zuraffa/master/AGENTS.mdgit clone --depth 1 https://github.com/arrrrny/zuraffaWrote 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/arrrrny/zuraffa/agents-md)<a href="https://agentmods.dev/instructions/arrrrny/zuraffa/agents-md"><img src="https://agentmods.dev/badge/instructions/arrrrny/zuraffa/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/arrrrny/zuraffa/agents-md"><img src="https://agentmods.dev/badge/instructions/arrrrny/zuraffa/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 | $0.05541 | $0.05541 |
| Opus 5.5 | $0.02216 | $0.02216 |
| Sonnet 5.5 | $0.01108 | $0.01108 |
| Haiku 4.5 | $0.00554 | $0.00554 |
Grade B, and why
zuraffa AGENTS.md scanned grade B with 2 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 2d 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.
Asks for rootmediumPrivilege escalation
A mod that escalates privileges can change anything on the machine, not only the project.
same, the platform is not. `sudo apt-get install` steps are mapped to a local Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -s http://127.0.0.1:8888/tasks \ How it starts
The opening of the file, as written. The whole thing — 479 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AI Agents Guide for Zuraffa
ZURAFFA MISFIRE RULE (HARD, NON-NEGOTIABLE — HARDCODED TOP RULE)
On ANY misfire (test failure, compilation error, runtime crash, unexpected output) related to zuraffa:
- STOP IMMEDIATELY on the first misfire.
- Report the issue to zuraffa GitHub (
arrrrny/zuraffa) with: the command that failed, expected vs actual output, and root cause. - Continue with a workaround to make the task pass (e.g., skip the failing test, use an alternative approach, or mock the failing component).
- Add a comment in the code explaining the workaround applied and linking to the zuraffa GitHub issue.
On ANY misfire related to the repo itself (not zuraffa):
- STOP IMMEDIATELY on the first misfire.
- Report the issue to the repo's GitHub with full details.
- Continue with a workaround to make the task pass.
- Add a comment in the code explaining the workaround applied.
This rule takes precedence over all other rules. Never skip a misfire or rationalize it away.
The forklift pool owns the PR — never merge a pull request yourself
Every pull request in these repos is reviewed by the forklift pool
(arrrrny/forklift — the local PR-review pipeline). It mints three tasks, in
this order, and that chain is the only sanctioned way from "PR opened" to "PR
merged":
PR review <repo>#<n>— the automated review; it posts its actionable findings on the PR.Apply review fixes <repo>#<n>— one fixes round, pushed onto the PR's branch.Merge PR <repo>#<n>— the merge itself; the task refuses while reviewer findings are still unaddressed.
Never merge or close a PR by hand, and never merge one because it "looks
finished". A hand merge lands the code while findings are still open: the
pool's fixes task is then killed by its closed-PR guard — the dispatcher log
says …#<n> is closed — cancelled, no agent started — and every finding the
review posted is dropped with nobody to own it. That is not a review, it is a
race the pipeline cannot win.
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.
- 2d ago Changed · +123 lines · +1,631 tokens per session ac3a0af2ad8f
- 4d ago Changed a209ff57eaf8
- 13d ago Changed · +69 lines · +896 tokens per session scan A → B 186487fe8721
- 1mo ago Changed · +23 lines · +386 tokens per session d6868fdc0c72
- 1mo ago Changed · +74 tokens per session eb47ae180edb
- 1mo ago Changed · -11 lines · -91 tokens per session 3a25bb65e4c1
- 1mo ago Changed · +1 lines · +58 tokens per session 504630b69c49
- 1mo ago First seen · 274 lines · 2,587 tokens per session scan A b1bde70687c8
zuraffa AGENTS.md is an instructions file published in the GitHub repository arrrrny/zuraffa (5 stars, last pushed yesterday), licensed MIT. It adds 5,541 tokens to every session, about $0.0222 per session on Opus 5.5. A static security scan graded it B with 2 findings (asks for root, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.
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.