Borrowing it
Nothing to install: this file belongs to russelleNVy/three-man-team. 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/russelleNVy/three-man-team/main/CLAUDE.mdgit clone --depth 1 https://github.com/russelleNVy/three-man-teamWrote 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/russellenvy/three-man-team/claude-md)<a href="https://agentmods.dev/instructions/russellenvy/three-man-team/claude-md"><img src="https://agentmods.dev/badge/instructions/russellenvy/three-man-team/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/russellenvy/three-man-team/claude-md"><img src="https://agentmods.dev/badge/instructions/russellenvy/three-man-team/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 | $0.00326 | $0.00326 |
| Opus 5.5 | $0.00130 | $0.00130 |
| Sonnet 5.5 | $0.00065 | $0.00065 |
| Haiku 4.5 | $0.00033 | $0.00033 |
Grade A, and why
three-man-team 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 2mo 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.
What it actually says
Three Man Team — Session Router
Token Rules — Always Active
Is this in a skill or memory? → Trust it. Skip the file read.
Is this speculative? → Kill the tool call.
Can calls run in parallel? → Parallelize them.
Output > 20 lines you won't use → Route to subagent.
About to restate what user said → Delete it.
Grep before Read. Never read a whole file to find one thing. Do not re-read files already in context this session.
Session Start — Every Role
- Load your token-optimizer skill if you have one — first, before anything else.
- Check
SESSION-CHECKPOINT.md— if active and recent, read it. That is your state. - Load your role file — copied to project root →
ARCHITECT.md·BUILDER.md·REVIEWER.md - If no checkpoint — Architect reads
BUILD-LOG.md+ARCHITECT-BRIEF.mdonly.
Project Owner role is set by the human. Do not ask.
Reference Files — On Demand Only
| File | Load when |
|---|---|
| Project spec | Architect needs it; checkpoint doesn't cover it |
| ARCHITECT-BRIEF.md | Builder and Reviewer load at task start |
| BUILD-LOG.md | Architect checks status; Builder updates when done |
| REVIEW-REQUEST.md | Reviewer loads at review start |
| REVIEW-FEEDBACK.md | Builder loads after Reviewer signals done |
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.
- 2mo ago First seen · 39 lines · 326 tokens per session scan A dd7fee0502f7
three-man-team CLAUDE.md is an instructions file published in the GitHub repository russelleNVy/three-man-team (953 stars, last pushed 5mo ago), licensed MIT. It adds 326 tokens to every session, about $0.0013 per session on Opus 5.5. 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.
three-man-team CLAUDE.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| three-man-team CLAUDE.mdrusselleNVy/three-man-team | Instructions file | 953 | 5mo ago | MIT | A | 326 | Claude Code |
| vscode buildNext.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 9,719 | GitHub Copilot |
| next.js AGENTS.mdvercel/next.js | Instructions file | 143k | yesterday | MIT | A | 7,461 | Codex, OpenCode |
| langchain AGENTS.mdlangchain-ai/langchain | Instructions file | 149k | yesterday | MIT | A | 4,680 | Codex, OpenCode |
| vscode oss-third-party-notices.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 5,516 | GitHub Copilot |
| vscode copilot-instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 3,093 | GitHub Copilot |
| deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness | Instructions file | 274k | 2d ago | MIT | A | 4,313 | Codex, OpenCode |