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.
git clone --depth 1 https://github.com/jayvee/aigonWrote 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/jayvee/aigon/cursor-rule)<a href="https://agentmods.dev/rules/jayvee/aigon/cursor-rule"><img src="https://agentmods.dev/badge/rules/jayvee/aigon/cursor-rule/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/rules/jayvee/aigon/cursor-rule"><img src="https://agentmods.dev/badge/rules/jayvee/aigon/cursor-rule.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 | $0.00424 | $0.00424 |
| Opus 5.5 | $0.00170 | $0.00170 |
| Sonnet 5.5 | $0.00085 | $0.00085 |
| Haiku 4.5 | $0.00042 | $0.00042 |
Grade A, and why
cursor-rule 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.
This is a copy
100% identical to aigon — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
What it actually says
Aigon
This project uses the Aigon development workflow. Read these docs before starting any work:
- Agent instructions:
AGENTS.md— codebase orientation, module map, coding rules - Development workflow:
.aigon/docs/development_workflow.md— feature/research lifecycle - Agent-specific notes:
.aigon/docs/agents/cursor.md
Key Rules
mainvs implementation work. Land implementation (any non-trivial code change tied to active feature/research implementation) via the repo's usual feature branch or worktree — not silently onmainwhen isolation is intended.aigon feature-create/research-create, which produce canonical specs underdocs/specs/*/00-specs/in stable-layout repos and visible inbox entries in the lifecycle view, normally do commit tomain(or whatever the default integration branch is); do not create a disposable Git branch only to commit a fresh spec.- Use
aigonCLI for all state transitions — never move spec files or lifecycle-view entries manually - Use
aigon dev-server startfor dev servers — never run the project's dev command directly (bypasses port allocation) - Signal when done — run
aigon agent-status implementation-completewhen implementation is complete - Read the spec first — run
aigon feature-spec <ID>to find and read the feature spec before coding - Verify per the project's own conventions — run whatever lint/tests/builds the project defines (check the project's docs) before submitting
Dev Server
NEVER run the project's dev command directly. Use aigon dev-server start which handles port allocation and proxy registration.
If you need to check your dev server URL: aigon dev-server url
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 · 28 lines · 424 tokens per session scan A 20cbf26cbc4e
cursor-rule is a cursor rule published in the GitHub repository jayvee/aigon (26 stars, last pushed 14d ago), licensed Apache-2.0. It adds 424 tokens to every session, about $0.0017 per session on Opus 5.5. A static security scan graded it A with 0 findings. It is 100% identical to aigon, differing in 0 lines, and is treated as a copy.
Other cursor rules, from other repositories
dos-verify-done-claims-cursorrules-prompt-file
Gate AI done/shipped/fixed claims on ground truth from the DOS kernel (dos verify, dos commit-audit) — git ancestry and the commit's own diff, never the agent's own narration.
commit-and-push
Commit (conventional commit) files and push to the remote repository.
release-checklist
What to update with each code change or version release.
conventional-commits
Always use Conventional Commits for git commit messages.
sciclaw-papercuts
Papercuts from Sol/ImageMagick/release cycles — release, brew, CI, and workspace hygiene for sciClaw agents.
check
Analyze staged git changes with archguardian before committing.