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/gammalabtechnologies/harmonist/protocol-enforcementgit clone --depth 1 https://github.com/GammaLabTechnologies/harmonistWhat 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 | $0.00570 | $0.00570 |
| Opus 5 | $0.00285 | $0.00285 |
| Sonnet 5 | $0.00114 | $0.00114 |
| Haiku 4.5 | $0.00057 | $0.00057 |
Grade A, and why
protocol-enforcement 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 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.
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 — 56 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Protocol Enforcement
Precedence (when rules conflict)
If two rules give conflicting guidance, resolve in this order:
- Project
AGENTS.md(closest to codebase reality) — wins for architecture, invariants, stack, module boundaries. - This rule (
protocol-enforcement.mdc) — wins for ENFORCEMENT: which agents must be invoked, which hooks must pass, which memory files must be updated. Protocol never negotiates. project-domain-rules.mdc— wins for domain specifics (e.g. financial invariants, game-dev performance budgets). Never overrides enforcement.- Any other
.cursor/rules/*.mdc— wins for stylistic / taste content (naming, formatting, commenting). Never overrides 1–3.
When you follow 2 over 4, say so explicitly in your response.
Enforcement (non-negotiable)
- Your FIRST action must be: read
.cursor/memory/session-handoff.md. - Consult
harmonist/agents/index.jsonto pick agents by tag. Never hard-code agent names; never invent slugs. - NEVER edit code without delegating to the correct subagent. If you edit a file directly, the stop hook will block your turn until a reviewer ran.
- NEVER skip
qa-verifier— run it before claiming done. - NEVER skip
security-reviewerwhen the protocol requires it (auth, secrets, payments, user input, crypto). - When delegating via Task, the FIRST line of the subagent prompt MUST
be
AGENT: <slug>(e.g.AGENT: qa-verifier). Hooks rely on this marker to credit the reviewer. - If you violated the protocol — STOP, tell the user, redo correctly. Do not self-justify.
- Respond to the user in their preferred language.
Escape hatch
For pure Q&A / documentation / planning with zero file writes, the enforcement gate skips itself automatically. You don't need to cite this rule — just answer.
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 · 56 lines · 570 tokens per session scan A 19c6bcef3618
protocol-enforcement is a cursor rule published in the GitHub repository GammaLabTechnologies/harmonist (2,254 stars, last pushed 2mo ago), licensed MIT. It adds 570 tokens to every session, about $0.0029 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 2026-08-30.
Other cursor rules, from other repositories
webdriver-management
Selenium WebDriver lifecycle management — driver factory, explicit waits, browser options, and teardown.
api-testing
Cypress network interception and API testing patterns (cy.intercept, service mocking, request/response validation).
minimax-m3-status-verification
MiniMax M3 status and verification contract: exact claim labels, proof matching, multimodal-grounded visual claims, and evidence-first closeouts.
minimax-mcp-tools
MCP and web-tool guidance: current-doc retrieval, direct-tool preference, MCP Apps structured content, and version-aware external lookups.
versioning-and-npm-distribution
Versioning integrity and GitHub/npm distribution flow for AgentProdReady.
serialization-rules
Unity serialization best practices.