What is Fireteam AGENTS.md?

A repository instruction file for Fireteam, a file-based system for coordinating groups of AI agents. It explains the project, its constraints, file structure, and naming rules.

Use it when maintaining Fireteam to check required files, portable shell rules, dependency limits, and backward-compatible template changes.

It gives agents the history and compatibility rules needed to change Fireteam without breaking existing copies or platform support.

Fireteam AGENTS.md — Instructions file for Codex and OpenCode by martinnaithani: A repository instruction file for Fireteam, a file-based sy

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/martinnaithani/fireteam/agents-md

Clone the repo

git clone --depth 1 https://github.com/martinnaithani/Fireteam

Made for: Codex, OpenCode.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/martinnaithani/fireteam/agents-md.svg)](https://agentmods.dev/instructions/martinnaithani/fireteam/agents-md)

Your own site

<a href="https://agentmods.dev/instructions/martinnaithani/fireteam/agents-md"><img src="https://agentmods.dev/badge/instructions/martinnaithani/fireteam/agents-md.svg" alt="Measured on agentmods" height="20"></a>

Per session 1,156 This file is loaded in full into every session.

When invoked 1,156 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.

Model	Per session	Once invoked
Fable 5	$0.01156	$0.01156
Opus 5	$0.00578	$0.00578
Sonnet 5	$0.00231	$0.00231
Haiku 4.5	$0.00116	$0.00116

Measured 3d ago against content hash 859d90c2d05a, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

Fireteam 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 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.

Origin

Copies of this mod

1 near-identical copy found in the catalogue:

Fireteam CLAUDE.md — 100% identical, 5 lines differ

AGENTS.md · 100 lines

How it starts

The opening of the file, as written. The whole thing — 100 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Agent Instructions for Maintaining Fireteam

Read HISTORY.md first. It contains the full design evolution and WHY every decision was made.

What This Repo Is

Fireteam is a file-system-native protocol for coordinating AI agent squads. No server, no database, no dependencies — just markdown files. This is the boilerplate repo that users copy into their projects.

Critical Constraints

ZERO DEPENDENCIES. The .fireteam/ folder works with a text editor. The CLI needs only bash. The dashboard needs only Python 3.6+ stdlib. Do not add npm, pip, or any package manager.
PORTABLE BASH. The CLI must work on macOS AND Linux. Use the sedi() wrapper for sed. Do not use grep -P (Perl regex), readlink -f (not on macOS), or GNU-specific flags.
BACKWARD COMPATIBLE TEMPLATES. Thousands of projects may use these templates. Adding fields is safe. Renaming or removing fields breaks existing projects.
THE THREE PROMPTS ARE LOAD-BEARING. START_MISSION.md, RESUME_AGENT.md, and the onboarding prompt each have a specific multi-step process. Every step exists for a reason documented in HISTORY.md. Do not simplify them without understanding the rationale.

File Structure

fireteam/
├── README.md              ← GitHub landing page
├── HISTORY.md             ← Design evolution (READ THIS)
├── AGENTS.md              ← You are here
├── PRD_TEMPLATE.md        ← User fills this to start
├── START_MISSION.md       ← Bootstrap prompt (creates Team Lead)
├── RESUME_AGENT.md        ← Recovery prompt (after crashes)
├── fireteam.sh            ← CLI tool (portable bash)
├── hq.py                 ← Live Command Center (HTTP server + daemon + dashboard)
├── LICENSE                ← MIT
├── .gitignore
└── .fireteam/             ← THE PROTOCOL (users copy this into projects)
    ├── MISSION.md         ← Why we're here
    ├── CONVENTIONS.md     ← Rules of engagement
    ├── ROSTER.md          ← Who's on the team
    ├── BOARD.md           ← Objective status
    ├── INTEL.md           ← Curated knowledge
    ├── README.md          ← Quick reference
    ├── tasks/             ← OBJ-XXX.md files
    ├── handoffs/          ← HO-XXX.md files
    ├── comms/             ← THREAD-XXX.md files
    ├── decisions/         ← DEC-XXX.md files
    ├── memory/            ← YYYY-MM-DD.md field logs
    ├── checkpoints/       ← [callsign].md + soul + heartbeat files
    ├── presets/           ← Team configurations (Solo, Duo, Squad, Platoon)
    ├── pro.yml            ← Pro Mode config (callsign → CLI mapping)
    └── templates/         ← 8 templates (task, handoff, thread, decision,
                              fieldlog, checkpoint, soul, heartbeat)

Read the full file on GitHub · 100 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.

3d ago First seen · 100 lines · 1,156 tokens per session scan A 859d90c2d05a

Subscribe to this mod's changes

Fireteam AGENTS.md is an instructions file published in the GitHub repository martinnaithani/Fireteam (4 stars, last pushed 5mo ago), licensed MIT. It adds 1,156 tokens to every session, about $0.0058 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.

ai-agents ai-coding antigravity-ide claude-code claude-skill developer-tools

Fireteam AGENTS.md

Getting it into your agent

Wrote this? Show the measurements

What it costs to keep this loaded

Grade A, and why

Nothing flagged

Copies of this mod

How it starts

Agent Instructions for Maintaining Fireteam

What This Repo Is

Critical Constraints

File Structure

What this file has done since we first saw it

Other instructions, from other repositories

pdca-agentic-coding-framework CLAUDE.md

pdca-agentic-coding-framework AGENTS.md

project-coding-companion-skill AGENTS.md

AmbyKit CLAUDE.md

sugar AGENTS.md

nextjs-skills CLAUDE.md