Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add rules/mohamedzhioua/agent-done-or-not/cursorrulesgit clone --depth 1 https://github.com/mohamedzhioua/agent-done-or-notWrote 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/rules/mohamedzhioua/agent-done-or-not/cursorrules)<a href="https://agentmods.dev/rules/mohamedzhioua/agent-done-or-not/cursorrules"><img src="https://agentmods.dev/badge/rules/mohamedzhioua/agent-done-or-not/cursorrules.svg" alt="Measured on agentmods" 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 | $0.00140 | $0.00140 |
| Opus 5 | $0.00070 | $0.00070 |
| Sonnet 5 | $0.00028 | $0.00028 |
| Haiku 4.5 | $0.00014 | $0.00014 |
Grade A, and why
cursorrules 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.
What it actually says
Proof-of-Done Rule (agent-done-or-not)
Before claiming a task is complete, you MUST verify it through the proof gate. Declaring "done" without a passing receipt is not allowed.
- Run the command that proves the work through the gate:
bash done-gate.sh capture --label check -- <your verifying command>It records the command, exit code, and a SHA-256 of the output, and exits with the command's own code — so a failing check fails here. - Only report completion after a PASSING receipt.
- If the check fails, fix the code and capture again. Never report success on a red check.
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 First seen · 13 lines · 140 tokens per session scan A 159b7110ed6f
cursorrules is a cursor rule published in the GitHub repository mohamedzhioua/agent-done-or-not (6 stars, last pushed 1mo ago), licensed MIT. It adds 140 tokens to every session, about $0.0007 per session on Opus 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 cursor rules, from other repositories
modern
You are an expert TypeScript developer working on PromptScript - a language and toolchain for standardizing AI instructions across enterprise organizations.
cursor
You are working on the checkout service. Preserve transaction integrity and auditability.
multifile
You are an expert TypeScript developer working on PromptScript - a language and toolchain for standardizing AI instructions across enterprise organizations.
p8-enforcement
P8 Enforcement Rules — Injected into every Agent conversation.
archcore-files
Enforce MCP-only operations when working with .archcore/ files.
frontend-architecture
Vite + React SPA architecture - directory layout, providers, bundle splitting. Tailwind styling in tailwind.mdc.