subagent-mcp copilot-instructions.md

Repository instructions for subagent-mcp, a tool that lets a host coding-agent command line coordinate local helper-agent sessions. They describe fallback behavior, orchestration rules, and status handling.

In plain words
What is it for?
Launching and coordinating delegated agents, following the required fallback rule, reading orchestration state, and handling status or repair steps.
Why use it?
They tell different coding agents how to coordinate helper sessions consistently when the dedicated subagent-mcp features are unavailable.

Instructions file for GitHub Copilot

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

Made for: GitHub Copilot.

Per session 726 This file is loaded in full into every session.
When invoked 726 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 $0.00726 $0.00726
Opus 5 $0.00363 $0.00363
Sonnet 5 $0.00145 $0.00145
Haiku 4.5 $0.00073 $0.00073

Measured 2d ago against content hash 599743e20109, 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 copilot-instructions.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.

.github/copilot-instructions.md · 61 lines

How it starts

The opening of the file, as written. The whole thing — 61 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Copilot Repository Instructions

subagent-mcp turns a host CLI into an orchestrator for local sub-agent sessions. It exposes MCP tools such as launch_agent, poll_agent, wait, get_status, orchestration-mode, swarm, and handoff tools. Provider credentials and user config live outside the repo.

The sub-orchestrator: true flag on launch_agent is for the swarm dispatch stage only (main orchestrator, depth 0); it launches a delegate-only child orchestrator for one disjoint plan section and is never set elsewhere.

Fallback Rule

Use this file when the host reads instruction files but does not load subagent-mcp skills, hooks, or slash commands. This applies to instruction-tier fallback use in Gemini CLI, Cursor, Windsurf, Kiro, Copilot, and similar agents.

Orchestration

  • If a <subagent-mcp state="..."> hook tag is present, treat it as the authoritative orchestration state.
  • If no hook tag is present, say: subagent-mcp: no hook injection detected: orchestration state unknown; defaulting to ON.
  • When orchestration is ON, use only launch_agent for sub-agent work. Do not use native agent/task tools or shell-spawned agents.
  • Every sub-agent prompt must begin with <this is a request from a parent process>.
  • Sub-agents return JSON with status, summary, source_locators, risks, and writes_requested.

Read Ladder

  1. Use poll_agent tail output first.
  2. If the tail is insufficient, launch one summarizer sub-agent and trust its summary if it is 100 lines or fewer.
  3. For larger handoffs, have sub-agents write scratch files and pass file paths between them. The orchestrator does not read large files inline.
  4. Use wait to learn completion. A quiet or stalled agent is still alive.

Status And Repair

  • /smcp:help: load skills/smcp-help/SKILL.md for install, config, and maintenance guidance.
  • /smcp:status: load skills/smcp-status/SKILL.md and call get_status.
  • /smcp:doctor: load skills/smcp-doctor/SKILL.md; run subagent-mcp doctor read-only first and ask before any repair.
  • /smcp:config: load skills/smcp-config/SKILL.md and call configure to list, read, or update configuration by canonical key.
  • Config commands: subagent-mcp config init, subagent-mcp config validate, subagent-mcp doctor, subagent-mcp upgrade, subagent-mcp rollback.

Read the full file on GitHub · 61 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 · 61 lines · 726 tokens per session scan A 599743e20109

Subscribe to this mod's changes

subagent-mcp copilot-instructions.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 726 tokens to every session, about $0.0036 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.

Related

Other instructions, from other repositories

neo4j-skills AGENTS.md

Instructions for neo4j-contrib/neo4j-skills, covering writing skills for this repository, language style — write for agents, not humans, six design principles, skill.md spec (agentskills.io) and frontmatter.

neo4j-contrib/neo4j-skills · 4,196 tokens

sgrep AGENTS.md

Instructions for XiaoConstantine/sgrep, covering sgrep - agent integration guide, build & test, build, test and install.

XiaoConstantine/sgrep · 524 tokens

harness-anchor CLAUDE.md

Instructions for Redtropig/harness-anchor, covering harness-anchor — contributor & ai collaborator guidelines, if you are an ai agent editing this plugin, design invariants (do not break), shell hazards no tool in this repo catches and authoring a new skill (when explicitly asked).

Redtropig/harness-anchor · 2,570 tokens

awesome-gemini-cli-subagents GEMINI.md

Instructions for ankitmundada/awesome-gemini-cli-subagents, covering gemini.md, project overview, repository structure, subagent file format and communication protocol.

ankitmundada/awesome-gemini-cli-subagents · 589 tokens

linkedin-maxxing CLAUDE.md

Claude Code instructions for warpirate/linkedin-maxxing, covering claude.md, what this repo is, layout, skill anatomy and how writing skills produce non-ai output.

warpirate/linkedin-maxxing · 1,226 tokens

redthread AGENTS.md

AGENTS.md instructions for matheusht/redthread, covering redthread agent architecture, 1. core operating guidelines, 2. the orchestration workflow (principal vs subagents), the principal agent must and subagent usage.

matheusht/redthread · 1,929 tokens