EXECUTION_PROTOCOL

A default step-by-step workflow for AI coding agents working on code or documentation in a repository.

In plain words
What is it for?
Use it to guide implementation and documentation tasks, including checking repository status, following documentation order, and reporting conflicts.
Why use it?
It tells the agent which project rules and documents to read first, helping avoid conflicts and work based on outdated assumptions.

Agent

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 agents/zyqzyq/unfour/execution_protocol
Clone the repo
git clone --depth 1 https://github.com/zyqzyq/Unfour
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,409 The whole file, excluding the scripts and references it only reads on demand.
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 $0.00000 $0.01409
Opus 5 $0.00000 $0.00705
Sonnet 5 $0.00000 $0.00282
Haiku 4.5 $0.00000 $0.00141

Measured yesterday against content hash d202242adbd5, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

EXECUTION_PROTOCOL 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 yesterday.

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.

docs/agents/EXECUTION_PROTOCOL.md · 170 lines

How it starts

The opening of the file, as written. The whole thing — 170 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Execution Protocol

Default execution workflow for AI coding agents working on implementation or documentation tasks in this repository.

1. Role And Authority

Document precedence (highest to lowest):

  1. AGENTS.md for repository-wide rules and architecture constraints.
  2. Task-specific prompt for current goal, scope, and acceptance criteria.
  3. docs/agents/START_HERE.md for context loading strategy.
  4. Domain documentation under docs/architecture/, docs/ui/, docs/mcp/, docs/testing/, and docs/release/.
  5. Package or crate AGENTS.md / README.md.
  6. This file for default workflow and reporting conventions.

When a task prompt conflicts with AGENTS.md, follow AGENTS.md and report the conflict.

2. Start-Of-Task Checklist

Before writing code or documentation:

  1. Read AGENTS.md.
  2. Read docs/agents/START_HERE.md and follow its scoped reading order.
  3. Read task-specific files listed in the prompt.
  4. Read relevant domain docs, such as package boundaries for dependency changes or UI docs for interaction changes.
  5. Run git status --short to inspect the working tree.
  6. Inspect the current diff before editing.
  7. Confirm the requested scope and identify verification commands.

Begin execution directly after a short plan unless a critical ambiguity makes safe execution impossible. If blocked, state the ambiguity and stop.

3. Scope Discipline

  • Modify only files necessary for the requested task.
  • Do not perform opportunistic refactors, dependency upgrades, or unrelated formatting.
  • Do not change public contracts, exported types, store shape, or Tauri command behavior unless the task requires it.
  • Record out-of-scope issues in the final report under remaining risks instead of fixing them.
  • Stop and report when a required change would cross an explicitly forbidden boundary.

4. Change Discipline

  • Prefer small, reviewable changes over large rewrites.
  • Preserve existing behavior unless the task explicitly requests behavior changes.
  • Keep architecture boundaries intact.
  • Do not add any, @ts-ignore, or @ts-expect-error unless the task explicitly justifies it.
  • Do not introduce silent fallbacks or hide errors to make builds pass.
  • Reuse existing project patterns before adding new abstractions.
  • Do not create new documentation files unless the task requires them.

Read the full file on GitHub · 170 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. yesterday First seen · 170 lines · 0 tokens per session scan A d202242adbd5

Subscribe to this mod's changes

EXECUTION_PROTOCOL is an agent published in the GitHub repository zyqzyq/Unfour (2 stars, last pushed yesterday), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 1,409 tokens. 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 2026-08-31.