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.
npx agentmods add instructions/adelie-squad/solosquad/agents-mdgit clone --depth 1 https://github.com/Adelie-Squad/solosquadWrote 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.
[](https://agentmods.dev/instructions/adelie-squad/solosquad/agents-md)<a href="https://agentmods.dev/instructions/adelie-squad/solosquad/agents-md"><img src="https://agentmods.dev/badge/instructions/adelie-squad/solosquad/agents-md.svg" alt="Measured on agentmods" height="20"></a>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 | $0.04790 | $0.04790 |
| Opus 5 | $0.02395 | $0.02395 |
| Sonnet 5 | $0.00958 | $0.00958 |
| Haiku 4.5 | $0.00479 | $0.00479 |
Grade A, and why
solosquad 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 4d 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.
How it starts
The opening of the file, as written. The whole thing — 334 lines — stays where its author put it; the contents beside it link to each section on GitHub.
SoloSquad — AGENTS.md
Canonical workspace guide. Every AI tool working on this codebase (Claude Code, Codex, Aider, Cursor, OpenHands, etc.) reads this file. Human-edited only — no AI agent may modify this file. (CLAUDE.md at the repo root is a thin redirect kept for backward compatibility.)
A 24/7 AI assistant system for solo founders. Powered by Claude Code + messenger bot (Discord/Slack) + automated crons + team-based agents.
Core Philosophy
Output ≠ Goal. Output = Means to achieve the goal.
Tech Stack
TypeScript + Node.js. Distributed as npm package.
npm install -g solosquad
solosquad init # Setup wizard
solosquad bot # Start messenger bot
solosquad cron start # Start automated scheduler
solosquad status # Dashboard
solosquad update # Self-update (OpenClaw-style)
solosquad doctor # Environment diagnostics
solosquad cron run # Manual cron execution
solosquad migrate # Upgrade workspace layout across versions
solosquad add org # Add another organization to workspace
solosquad add repo # Clone (URL) or register (local path) a repository
solosquad sync # Sync org/repositories/ with .org.yaml
solosquad chief status / reset / compact # v0.3.0 (PM→Chief, v1.1) — Chief session ops
solosquad workflow list / show / focus # v0.3.0 — workflow inspect
solosquad rollback --workflow <id> # v0.3.0 — snapshot revert
solosquad goal new / list / show / run / status / stop / verify # v0.4
Project Structure
package.json → npm package config
tsconfig.json → TypeScript config
bin/solosquad.ts → CLI entry point
src/
cli/ → CLI commands (init, bot, cron, status, update, doctor,
agent, workflow, goal, memory, readiness)
bot/ → Chief runner, claude-process factory, session-store,
events, agents-builder, workflow-reconciler,
slash-commands, git-snapshot, workspace-meta,
spawn-assembler (v0.6 8-layer JIT),
agent-budget (v0.6 — author-budget 일반화), mention-parser (v1.0.1 — @<slug> multi-repo intent), repo-registry (v1.0.1)
messenger/ → Platform adapters (Discord, Slack)
scheduler/ → Cron-based cron execution + memory,
trajectory-extractor (v0.6 §3),
freq-keyword-miner (v0.6 §3.4),
v06-stats-extract (v0.6 §2.5)
memory/ → FTS5 archive schema + rotate (v0.6 §4)
util/ → Config, paths, logger, cost
engine/ → v0.4 autonomous engine + stop-hook-adapter (v0.6 §5b)
migrations/scripts/ → 0.5.0-to-0.6.0.ts (dry-run + apply)
agents/ → Agent definitions (v1.1 flat layout — canonical bundle)
main/{agent}/SKILL.md → 5 main bots: chief, pm, engineer, designer, marketer
specialists/{agent}/SKILL.md → 20 specialists, flat (no team folder nesting)
teams/{team}/ → 4 teams (product/engineering/design/marketing)
composition.yaml → Team membership (= data, not folders) + main supervisor
KNOWLEDGE.md → Team(=domain) shared knowledge (v0.6 §2.1)
OKR.md → Quarterly OKR (Chief-authored)
skills/{skill}/SKILL.md → Reusable skills (PM Tier-1/2 + Chief-invoked)
crons/{cron}.md → Bundled cron prompts (editable): morning/evening brief,
pm-compaction, leading-indicator, *-housekeeping, *-rotate
(top-level since v1.3.3; was assets/routines/)
knowledge/ → Bundled workspace knowledge starter (v0.6 §2.3; top-level since v1.1)
user/ → Bundled owner profile: profile.md, voice.md, preferences.md
(replaced assets/core/, removed v1.3.1 §9)
assets/ → Remaining bundled defaults staged into .solosquad/ on init
docker/ → Dockerfile + docker-compose.yml (v1.2.10)
.env.example → Sample environment file
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.
- 4d ago First seen · 334 lines · 4,790 tokens per session scan A 6439ff15bafc
solosquad AGENTS.md is an instructions file published in the GitHub repository Adelie-Squad/solosquad (19 stars, last pushed 13d ago), licensed MIT. It adds 4,790 tokens to every session, about $0.0239 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.
Other instructions, from other repositories
tezgah CLAUDE.md
Instructions for komunite/tezgah, covering tezgah, proje yapısı, skill'ler, kurallar and varsayılan tech stack.
soleur AGENTS.md
AGENTS.md instructions for jikig-ai/soleur, covering agent instructions — index, hard rules, workflow gates, code quality and review & feedback.
soleur CLAUDE.md
Claude Code instructions for jikig-ai/soleur, a project described as: The Company-as-a-Service platform. Build, ship, and scale -- powered by AI teams.
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.