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/aquifer-sea/pattern8/p8-enforcementgit clone --depth 1 https://github.com/Aquifer-sea/pattern8Wrote 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/aquifer-sea/pattern8/p8-enforcement)<a href="https://agentmods.dev/rules/aquifer-sea/pattern8/p8-enforcement"><img src="https://agentmods.dev/badge/rules/aquifer-sea/pattern8/p8-enforcement.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 | $0.00513 | $0.00513 |
| Opus 5 | $0.00257 | $0.00257 |
| Sonnet 5 | $0.00103 | $0.00103 |
| Haiku 4.5 | $0.00051 | $0.00051 |
Grade C, and why
p8-enforcement scanned grade C with 1 finding 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 3d 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.
Recursive force deletehighDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
<!-- SecurityGuard fence — intercepts dangerous commands like rm -rf, sudo, etc. --> How it starts
The opening of the file, as written. The whole thing — 58 lines — stays where its author put it; the contents beside it link to each section on GitHub.
P8 Enforcement Rules
You are working in a project governed by Pattern 8 (P8). Follow these rules.
1. SKILL Discovery
Before starting any task, read MCP Resource skill://index to find a matching SKILL.
If a SKILL matches, read its checklist and template Resources.
If no SKILL matches, work normally without P8 constraints.
2. execute_tool — Before Running Commands
Before executing any OS command, call:
execute_tool({ command: "your command", skill: "matched_skill_name" })
If it returns allowed: false, you MUST stop. Do NOT attempt to bypass.
3. submit_review — After Completing a SKILL Pipeline
After completing a task that uses a SKILL pipeline, call:
submit_review({ content: "your output", skill: "matched_skill_name" })
If it returns passed: true → deliver the output to the user.
If it returns P8_AUDIT_FAILED:
- Read the
violationslist - Fix each violation in your output
- Call
submit_reviewagain - Repeat up to 3 times
- If still failing after 3 retries, inform the user with the violations
4. Absolute Prohibitions
- Do NOT skip
execute_tooland run OS commands directly - Do NOT modify files under
skills/unless the user explicitly asks - Do NOT modify
AGENTS.md - Do NOT attempt to read
references/guidelines.yamlorreferences/security.yamldirectly — these are loaded internally by the P8 engine
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.
- 3d ago First seen · 58 lines · 513 tokens per session scan C f767fb13f3e2
p8-enforcement is a cursor rule published in the GitHub repository Aquifer-sea/pattern8 (49 stars, last pushed 5mo ago), licensed MIT. It adds 513 tokens to every session, about $0.0026 per session on Opus 5. A static security scan graded it C with 1 finding (recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other cursor rules, from other repositories
cursor
You are working on the checkout service. Preserve transaction integrity and auditability.
code-optimization
Guidelines for optimizing duplicate and poorly structured code.
type-inference
Derive TypeScript types from Zod schemas - no hand-written interfaces for wire shapes.
paperfit
PaperFit project rule for LaTeX visual typesetting optimization.
frontend-architecture
Vite + React SPA architecture - directory layout, providers, bundle splitting. Tailwind styling in tailwind.mdc.
ports
Local dev port allocation - role ranges, registry, inspectorport, strictPort, multi-config wrangler.