subagent-mcp AGENTS.md

Repository instructions that define how work on the Heretyc/subagent-mcp project must be planned, reviewed, and approved. They make the project board the main record of planning and status, subject to the documented alignment rules.

In plain words
What is it for?
Use them when contributing to that repository, especially for checking project status, preparing plans, requesting required human choices, and keeping the README premise aligned with the project.
Why use it?
They give agents a fixed process for handling changes and human decisions instead of allowing each agent to invent its own workflow. They also define terms such as repository work, human review, and project premise.

Instructions file for CodexOpenCode

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 instructions/heretyc/subagent-mcp/agents-md
Clone the repo
git clone --depth 1 https://github.com/Heretyc/subagent-mcp

Made for: Codex, OpenCode.

Per session 4,263 This file is loaded in full into every session.
When invoked 4,263 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 $0.04263 $0.04263
Opus 5 $0.02132 $0.02132
Sonnet 5 $0.00853 $0.00853
Haiku 4.5 $0.00426 $0.00426

Measured 2d ago against content hash 33bd9bf17f79, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

subagent-mcp AGENTS.md 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 2d 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.md · 202 lines

How it starts

The opening of the file, as written. The whole thing — 202 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Repository Agent Instructions

PROJECT BOARD LAW - BINDING, NO EXCEPTIONS

https://github.com/users/Heretyc/projects/4 is the canonical Source of Truth for the PLANNING and STATUS of all repo Work. It is subordinate to the alignment chain in Law 2: where Board and Premise conflict, the Premise wins and the Board is corrected.

DEFINITIONS

"Work" = any mutation of git-tracked content: commits, branches, PRs. Wiki edits, releases, tags, and comments are not Work. Board mutations are not Work and never require issues. "Human Review" (HR) = engagement of the human via the structured question tool, presented as if the human has no knowledge of the project or repo. Two modes:

  • Decision HR: 2+ options, each with pros and cons.
  • Action HR: 1 required action, why it is needed, and the consequence of inaction. HR is NEVER skippable for any authority or reason. One HR session MAY bundle every trigger pending at that moment. "Premise" = The answer to "what is this + why care?": who it's for + problem + what it does + why not alternatives. Canonical copy: first paragraph of README.md, MAXIMUM 1000 characters. "Short Premise" = Verbatim-identical version of Premise (minus the "why not alternatives" aspect) MAXIMUM 350 characters and found in BOTH the Repo and Project Short Descriptions. "Interactive Session" = A harness that has a working structured question tool. Lacking this, the session is considered non-interactive.

DIRECTIVES

  1. Short Premise must faithfully condense the canonical Premise. Any edit to the Premise updates both Short Premise copies in the same session. If the copies mismatch, truncate, or drift from the canonical: the README is canonical and the mismatch is an HR trigger.
  2. Code MUST align with repo Spec docs. Spec MUST align with the Premise at all times. The Premise is always the tie-breaker. If in doubt, HR. If the Repo lacks the canonical Premise in README.md, or either Short Description lacks the Short Premise: recon the project specs/code and present a proposed Premise and Short Premise via Decision HR; that same HR authorizes the board issue for the restoration edit (which is Work).
  3. All Work maps to a board issue. All issues map to Milestones. No unmapped Work.
  4. Every issue/epic carries ALL required fields at ALL times: Label(s), Priority, Size, Estimate, Iteration, Milestone, Assignee, Relationships, branch/PR link, and updated Status. Satisfiability rules: issues are created fully populated in a single operation, with Iteration taken from the authorizing HR (Law 9, bundled per the HR definition); the branch/PR link is mandatory from the moment the branch or PR exists and MUST be back-filled in the same working session ("none yet" before that; "n/a" for board-only issues); Assignee follows Law 11 (an idle issue may be unassigned or assigned to anyone; an actively-worked issue MUST be assigned to the worker).
  5. Every PR maps to a fully populated issue.
  6. Live updates are mandatory: update the mapped item BEFORE, DURING, and AFTER Work. Agents update existing items in real time without seeking permission. While an HR is pending on an item, only Status changes and comments recording the block are permitted on it.
  7. Every agent MUST fully understand the Board plan and the Premise BEFORE acting. The read-only sweep in Law 13 both requires and satisfies this understanding.
  8. Any conflict between tasked work and the Board: STOP and deconflict via HR BEFORE any board edit. Conflicts between Board and Premise resolve per Law 2.
  9. Net-new Work not on the board: HR BEFORE adding it. That HR also supplies the new issue's Iteration and other judgment fields (Law 4).
  10. Board ops use ONLY the gh CLI, including gh api where subcommands lack field coverage (Relationships). If gh is not authenticated or lacks the project scope: Action HR asking the human to run gh auth refresh -s project (interactive; agents cannot complete it).
  11. Before starting Work on an unassigned issue, assign it to the logged-in gh user. If an issue you are tasked to work is assigned to someone else: Action HR to reassign. If the human declines, stand down from that item: you are forbidden from performing Work on any issue not assigned to the logged-in gh user. Idle issues may remain unassigned or assigned to others.
  12. Never store local paths or machine-specific information anywhere on the Board.
  13. Sweep the Board before starting and after finishing Work: find the most recently COMPLETED "Project Board true-up #". If it completed more than 5 business days ago, or none exists: dispatch 2+ review subagents over all incomplete board items for non-compliance with these Laws (if the harness cannot spawn subagents, perform work directly). HR is mandated on all non-compliant items found (bundle-able). Once the true-up is complete: mark it complete and create the next true-up issue with an incremented #, NO assignee, description = a VERBATIM copy of these Laws from their canonical home (this document at the repo root).
  14. HR may be DEFERRED only in headless runs where no human is reachable (determined if no structured question tool exists in your harness), and deferral is never resolution. Queue the item as a comment on the dedicated HR-queue board item, set the affected issue's Status to "Awaiting Review" (rename "In Review" to "Awaiting Review" if it exists. If you cannot rename, use "In Review" status), and proceed only with Work unaffected by the pending question; doubt about whether Work is affected resolves to AFFECTED. Any Interactive Session MUST drain the queue (bundled HR) BEFORE starting any new Work. If any queued item is older than 5 business days, ALL Work halts until the queue drains. Every true-up (Law 13) reports the queue's contents. Queued items are never deemed approved, expired, or abandoned.

Read the full file on GitHub · 202 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. 2d ago First seen · 202 lines · 4,263 tokens per session scan A 33bd9bf17f79

Subscribe to this mod's changes

subagent-mcp AGENTS.md is an instructions file published in the GitHub repository Heretyc/subagent-mcp (3 stars, last pushed 4d ago), licensed Apache-2.0. It adds 4,263 tokens to every session, about $0.0213 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 2026-08-31.