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/paullukic/coographWrote 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/paullukic/coograph/windsurfrules)<a href="https://agentmods.dev/rules/paullukic/coograph/windsurfrules"><img src="https://agentmods.dev/badge/rules/paullukic/coograph/windsurfrules/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/paullukic/coograph/windsurfrules"><img src="https://agentmods.dev/badge/rules/paullukic/coograph/windsurfrules.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 | $0.00547 | $0.00547 |
| Opus 5.5 | $0.00219 | $0.00219 |
| Sonnet 5.5 | $0.00109 | $0.00109 |
| Haiku 4.5 | $0.00055 | $0.00055 |
Grade A, and why
windsurfrules 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 9d 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 — 36 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Coograph Conventions
This project ships with the Coograph AI coding template. Follow these rules at every session.
Invocation
If the user types /coograph-init (or asks to "initialize the project", "set up coograph"), follow .github/skills/coograph-init/SKILL.md exactly.
If the user types /coograph-retro (or asks to "run a retro", "check the guardrails"), follow .github/skills/coograph-retro/SKILL.md exactly. It measures rule violations and session cost from signals captured in Claude Code sessions and proposes instruction and hook edits as an OpenSpec. It never applies. This tool does not capture signals itself; the skill still runs the analyzer and, when nothing was captured, says so.
If the user types /coograph-docs-restructure (or asks to "restructure the docs", "shrink the instruction files"), follow .github/skills/coograph-docs-restructure/SKILL.md exactly. It proposes an OpenSpec first and migrates only after approval.
Before editing a file or running a command, check GOTCHAS.md for entries whose paths: or commands: match it, and follow their Fix / rule.
On session start
- Read
.github/copilot-instructions.md— full project conventions. - Read
.github/instructions/brutal-honesty.instructions.md— communication style. - Check
openspec/changes/for in-progress work (skiparchive/).
Code-graph first
ALWAYS use the code-graph (get_minimal_context, query_graph) before any codebase navigation. Fall back to sqlite3 .code-graph/graph.db only when the MCP server is unavailable. Fall back to grep/glob ONLY when the database is genuinely absent.
OpenSpec gate
Any change modifying 2+ files, touching a spec, altering a public interface, or adding new behavior MUST go through openspec/changes/<date>-<slug>/ with user approval BEFORE code. Exemptions: typo fix, comment-only edit, user-dictated config bump, follow-up on approved in-progress OpenSpec. "Trivial", "obvious", "small" are NOT exemptions.
Workflow
Plan → Propose (OpenSpec) → Apply → Quality Gates → Review Gate → Archive. Skip only for literal exemptions above. After 3 failed attempts, stop and ask.
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.
- 9d ago Changed · +4 lines · +97 tokens per session 051a8320cc66
- 26d ago Changed · +2 lines · +94 tokens per session c23abebed2dc
- 1mo ago First seen · 30 lines · 356 tokens per session scan A 8f008f9dc813
windsurfrules is a cursor rule published in the GitHub repository paullukic/coograph (17 stars, last pushed 9d ago), licensed MIT. It adds 547 tokens to every session, about $0.0022 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 2026-09-16.
Other cursor rules, from other repositories
cursor-rule
This project can use agentmap (@raymondchins/agentmap) — a queryable import/symbol map at .claude/agentmap/.
docs-governance
../../.agents/rules/docs-governance.md.
002-verify-before-act
Requires Claude to read before writing, verify before installing, and confirm before destructive operations.
ponytail
Ponytail, lazy senior dev mode. Always pick the simplest solution that works.
angular-20
This rule provides comprehensive best practices and coding standards for Angular development, focusing on modern TypeScript, standalone components, signals, and performance optimizations.
dev-standard
Apache Superset development standards and guidelines for Cursor IDE.