agentmods.dev

claude-prove: Instructions file for Claude Code

CLAUDE.md

claude-prove CLAUDE.md is an instructions file for Claude Code from mjmorales/claude-prove. It costs 2,588 tokens per session, scanned A, original, MIT.

A project instruction file for the Claude Code plugin called claude-prove. It explains the project's folders, naming rules, validation command, and how to find files and coordinate team agents.

In plain words
What is it for?
Use it as a reference when adding agents, commands, documentation, scripts, or skills, naming files, checking changes, or finding project context.
Why use it?
It gives coding agents shared rules for working in the repository and helps them avoid broad, inefficient searches or inconsistent changes.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md. Also seen: reads .claude/ paths; mentions CLAUDE.md; mentions subagents.

This is mjmorales/claude-prove's own configuration. It tells Claude Code how to work on claude-prove itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything claude-prove configures →

not rated 2repo 2mo ago A scan 2,588 tokens original MIT
View source ↗ mjmorales/claude-prove
Reuse

Borrowing it

Nothing to install: this file belongs to mjmorales/claude-prove. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/mjmorales/claude-prove/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/mjmorales/claude-prove

Made for: Claude Code.

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.

agentmods badge for claude-prove CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/mjmorales/claude-prove/claude-md/github.svg)](https://agentmods.dev/instructions/mjmorales/claude-prove/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/mjmorales/claude-prove/claude-md"><img src="https://agentmods.dev/badge/instructions/mjmorales/claude-prove/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.

agentmods 80×15 button for claude-prove CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/mjmorales/claude-prove/claude-md"><img src="https://agentmods.dev/badge/instructions/mjmorales/claude-prove/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 2,588 This file is loaded in full into every session.
When invoked 2,588 The same file — it is already loaded in full.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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.

ModelPer sessionOnce invoked
Fable 5.1 $0.02588 $0.02588
Opus 5.5 $0.01035 $0.01035
Sonnet 5.5 $0.00518 $0.00518
Haiku 4.5 $0.00259 $0.00259

Measured 2mo ago against content hash 3444c0370785, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

claude-prove 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.

CLAUDE.md · 158 lines

How it starts

The opening of the file, as written. The whole thing — 158 lines — stays where its author put it; the contents beside it link to each section on GitHub.

claude-prove

Prove plugin v4.8.0 — if bun run "${CLAUDE_PROVE_PLUGIN_DIR:-$HOME/.claude/plugins/prove}/packages/cli/bin/run.ts" --version does not match v4.8.0, run /prove:update to sync.

JavaScript/TypeScript (npm)

Structure

  • agents/ — Agent definitions
  • commands/ — Slash commands
  • docs/ — Documentation
  • scripts/ — Build/utility scripts
  • skills/ — Plugin skills

Conventions

  • File naming: kebab-case
  • Test files: *.test.ext (dot)

Validation

Run before committing:

  • llm: skill claude-skills:comment-audit

Discovery Protocol

Before broad Glob/Grep searches, check the file index first:

  • bun run "${CLAUDE_PROVE_PLUGIN_DIR:-$HOME/.claude/plugins/prove}/packages/cli/bin/run.ts" cafi context — full index with routing hints
  • bun run "${CLAUDE_PROVE_PLUGIN_DIR:-$HOME/.claude/plugins/prove}/packages/cli/bin/run.ts" cafi lookup <keyword> — search by keyword

Only fall back to Glob/Grep when the index doesn't cover what you need.

Team Agents

Role-bound team agents registered in .claude/agents/:

  • discovery: team-discovery-tech_lead, team-discovery-engineer, team-discovery-implementer
  • engine: team-engine-tech_lead, team-engine-engineer, team-engine-implementer
  • methodology: team-methodology-tech_lead, team-methodology-engineer, team-methodology-implementer

Dispatch and memory protocol:

  • For subagent work that falls inside a team's scope, dispatch that team's role agent — never a general-purpose agent. Resolve scope from each team's bundle teams/<slug>.md; use a general-purpose agent only when no team's bundle scope covers the task.
  • Every dispatched team agent must honor its memory protocol: read its team bundle teams/<slug>.md (scope, roster, recent Lore) before acting, and record what it learns:
    • seat notes with bun run "${CLAUDE_PROVE_PLUGIN_DIR:-$HOME/.claude/plugins/prove}/packages/cli/bin/run.ts" scrum annotation add --target-kind team --target <team-slug> --body <text> --author <CT-UUID>
    • team Lore with bun run "${CLAUDE_PROVE_PLUGIN_DIR:-$HOME/.claude/plugins/prove}/packages/cli/bin/run.ts" scrum lore record <team-slug> --body <text> --author <CT-UUID> (tech_lead seat; non-lead seats route journal-worthy findings to a seat annotation instead)
    • durable decisions with bun run "${CLAUDE_PROVE_PLUGIN_DIR:-$HOME/.claude/plugins/prove}/packages/cli/bin/run.ts" scrum decision record <path> --kind adr

Read the full file on GitHub · 158 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.

  1. 2mo ago First seen · 158 lines · 2,588 tokens per session scan A 3444c0370785

Subscribe to this mod's changes

claude-prove CLAUDE.md is an instructions file published in the GitHub repository mjmorales/claude-prove (2 stars, last pushed 2mo ago), licensed MIT. It adds 2,588 tokens to every session, about $0.0104 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 2026-08-31.

Related

Other instructions, from other repositories

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).

microsoft/vscode · 9,719 tokens

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.

vercel/next.js · 7,461 tokens

vscode oss-third-party-notices.instructions.md

Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).

microsoft/vscode · 5,516 tokens

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.

langchain-ai/langchain · 4,680 tokens

vscode copilot-instructions.md

Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).

microsoft/vscode · 3,048 tokens

deepseek-harness AGENTS.md

AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.

deepseek-ai/deepseek-harness · 4,269 tokens