protocol-enforcement

A mandatory rule set that requires every task to follow the project's AGENTS.md instructions and specified review process. It also defines which checks and helper agents must be used.

In plain words
What is it for?
Checking project instructions, selecting the required agents, delegating code edits, running verification, and completing required handoff steps.
Why use it?
It enforces the repository's required workflow and prevents code changes from bypassing reviews, memory updates, or verification.

Cursor rule

Install

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.

agentmods
npx agentmods add rules/gammalabtechnologies/harmonist/protocol-enforcement
Clone the repo
git clone --depth 1 https://github.com/GammaLabTechnologies/harmonist
Per session 570 This file is loaded in full into every session.
When invoked 570 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce 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

Measured 3d ago against content hash 19c6bcef3618, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

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.

agents/templates/rules/protocol-enforcement.mdc · 56 lines

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:

  1. Project AGENTS.md (closest to codebase reality) — wins for architecture, invariants, stack, module boundaries.
  2. 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.
  3. project-domain-rules.mdc — wins for domain specifics (e.g. financial invariants, game-dev performance budgets). Never overrides enforcement.
  4. 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.json to 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-reviewer when 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.

Read the full file on GitHub · 56 lines

Changes

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.

  1. 3d ago First seen · 56 lines · 570 tokens per session scan A 19c6bcef3618

Subscribe to this mod's changes

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.