Borrowing it
Nothing to install: this file belongs to cnavta/sprint-mcp. 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/cnavta/sprint-mcp/main/CLAUDE.mdgit clone --depth 1 https://github.com/cnavta/sprint-mcpWrote 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/cnavta/sprint-mcp/claude-md)<a href="https://agentmods.dev/instructions/cnavta/sprint-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/cnavta/sprint-mcp/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/cnavta/sprint-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/cnavta/sprint-mcp/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 | $0.03073 | $0.03073 |
| Opus 5.5 | $0.01229 | $0.01229 |
| Sonnet 5.5 | $0.00615 | $0.00615 |
| Haiku 4.5 | $0.00307 | $0.00307 |
Grade A, and why
sprint-mcp CLAUDE.md scanned grade A with 1 finding 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -X POST \ How it starts
The opening of the file, as written. The whole thing — 384 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.
Repository Purpose
This is a sprint-based development repository governed by a strict LLM agent workflow protocol defined in AGENTS.md. The repository implements a structured sprint methodology where LLM agents execute development work through defined phases: Plan → Approve → Implement → Validate → Verify → Publish (PR) → Retro → Learn.
Critical Precedence Rules
Always consult these sources in order:
architecture.yaml— canonical source of truth for system behavior (when it exists)AGENTS-uncompressed.md— operational and behavioral rules for agents (SOURCE FILE with explicit intent)AGENTS.md— semantically compressed version of AGENTS-uncompressed.md for token efficiency (DO NOT MODIFY)- Everything else — examples, legacy docs, and supporting materials
If conflicts occur, architecture.yaml wins. Surface the conflict and align to it.
Protocol File Relationship
- AGENTS-uncompressed.md: The SOURCE file for all protocol changes. Higher token count, more explicit intent. Always modify this file when updating the Sprint Protocol.
- AGENTS.md: A semantically compressed version optimized for token efficiency. This is generated FROM AGENTS-uncompressed.md and should NOT be modified directly. Future sprints may need to recompress this file when AGENTS-uncompressed.md changes significantly.
Sprint Protocol Overview
Sprint Control Rules
- S1: A sprint begins only when the user explicitly says "Start sprint"
- S2: A sprint ends when validation criteria are satisfied OR documented exceptions are explicitly accepted, and the user says "Sprint complete" or "Force complete sprint"
- S3: Only one sprint may be active at a time
- S4: Prompts related to this repo are included in sprint scope unless specified otherwise
- S5: If sprint state is unclear, ask once, then proceed with best judgment, but do not bypass explicit approval gates
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 · 384 lines · 3,073 tokens per session scan A 94d96ff57333
sprint-mcp CLAUDE.md is an instructions file published in the GitHub repository cnavta/sprint-mcp (1 stars, last pushed 2mo ago), licensed MIT. It adds 3,073 tokens to every session, about $0.0123 per session on Opus 5.5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
sprint-mcp CLAUDE.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| sprint-mcp CLAUDE.mdcnavta/sprint-mcp | Instructions file | 1 | 2mo ago | MIT | A | 3,073 | Claude Code |
| vscode buildNext.instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 9,719 | GitHub Copilot |
| next.js AGENTS.mdvercel/next.js | Instructions file | 143k | today | MIT | A | 7,461 | Codex, OpenCode |
| vscode oss-third-party-notices.instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 5,516 | GitHub Copilot |
| langchain AGENTS.mdlangchain-ai/langchain | Instructions file | 149k | today | MIT | A | 4,680 | Codex, OpenCode |
| vscode copilot-instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 3,093 | GitHub Copilot |
| deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness | Instructions file | 275k | 3d ago | MIT | A | 4,313 | Codex, OpenCode |