Borrowing it
Nothing to install: this file belongs to dkyazzentwatwa/agent-swarm-os. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/dkyazzentwatwa/agent-swarm-os/main/CLAUDE.mdgit clone --depth 1 https://github.com/dkyazzentwatwa/agent-swarm-osWrote 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/dkyazzentwatwa/agent-swarm-os/claude-md)<a href="https://agentmods.dev/instructions/dkyazzentwatwa/agent-swarm-os/claude-md"><img src="https://agentmods.dev/badge/instructions/dkyazzentwatwa/agent-swarm-os/claude-md/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/instructions/dkyazzentwatwa/agent-swarm-os/claude-md"><img src="https://agentmods.dev/badge/instructions/dkyazzentwatwa/agent-swarm-os/claude-md.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.02733 | $0.02733 |
| Opus 5 | $0.01367 | $0.01367 |
| Sonnet 5 | $0.00547 | $0.00547 |
| Haiku 4.5 | $0.00273 | $0.00273 |
Grade A, and why
agent-swarm-os CLAUDE.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 12d 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 — 318 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent Squad
Agent Squad runs domain-specific multi-agent missions with a manifest-driven workspace and dashboard.
Claude Agent Teams (Required)
This project expects Claude Agent Teams to be enabled for all runs.
Use: CLAUDE_CODE_EXPERIMENTAL_AGENT_TEAMS=1 claude --teammate-mode in-process
Reference: https://code.claude.com/docs/en/agent-teams.md
Workspace Conventions
All mission data is under workspaces/:
workspaces/{YYYY-MM-DD}-{slug}/
workspace.json
tasks.json
source/mission.md
agents/*.md
artifacts/{module-id}/
Use workspace.json as the source of truth for:
- team metadata
- groups
- agents
- modules
- workflow lanes
- comms settings
Directory Safety
Before creating new directories or workspaces:
- Confirm the correct working directory with the user
- Default to operating within the current project structure
- Never create workspaces outside
workspaces/without explicit confirmation - Use
pwdto verify location before spawning agents
Ownership Rules
- Each agent owns its assigned tasks and module outputs.
- Do not rewrite another agent's deliverable unless task dependencies require it.
- Keep edits traceable and mission-focused.
Team Comms Feed
Post updates to the team feed JSONL:
~/.claude/teams/{teamName}/team-feed.jsonl
Using agent-squad:comms skill (recommended):
post_update(message="Research phase complete")
post_insight(message="Found pattern: 80% of leads lack decision-maker info", category="data-quality")
post_blocker(message="Cannot proceed - missing API credentials", blockedTask="task-003")
Manual JSONL format (if skills unavailable):
{"timestamp":"ISO8601","agent":"agent-id","type":"update|insight|blocker","message":"text","workspaceId":"workspace-id"}
CRITICAL: workspaceId is REQUIRED
When multiple workspaces share the same team name, messages WITHOUT a workspaceId field will NOT appear in the dashboard. The dashboard filters messages to show only those belonging to the current workspace.
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.
- 12d ago First seen · 318 lines · 2,733 tokens per session scan A 31538ddb5106
agent-swarm-os CLAUDE.md is an instructions file published in the GitHub repository dkyazzentwatwa/agent-swarm-os (2 stars, last pushed 4mo ago), licensed MIT. It adds 2,733 tokens to every session, about $0.0137 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.
Other instructions, from other repositories
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.
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
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.
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).
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).