trustable-ai CLAUDE.md

trustable-ai CLAUDE.md is an instructions file for Claude Code from keychain-io/trustable-ai. It costs 4,180 tokens per session, scanned A, original, MIT.

Project instructions for Trustable AI, a software framework that makes AI coding work more reliable by requiring checks before work is marked complete.

In plain words
What is it for?
Use them when developing Trustable AI, following its setup steps, or checking work against external systems and required workflow gates.
Why use it?
They help prevent an AI agent from claiming a task is finished without verifying that the work exists and works.

Instructions file for Claude Code

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

Install

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.

agentmods
npx agentmods add instructions/keychain-io/trustable-ai/claude-md
Clone the repo
git clone --depth 1 https://github.com/keychain-io/trustable-ai

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 trustable-ai CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/keychain-io/trustable-ai/claude-md.svg)](https://agentmods.dev/instructions/keychain-io/trustable-ai/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/keychain-io/trustable-ai/claude-md"><img src="https://agentmods.dev/badge/instructions/keychain-io/trustable-ai/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 4,180 This file is loaded in full into every session.
When invoked 4,180 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
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 $0.04180 $0.04180
Opus 5 $0.02090 $0.02090
Sonnet 5 $0.00836 $0.00836
Haiku 4.5 $0.00418 $0.00418

Measured 5d ago against content hash fe370ddfd32c, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

trustable-ai 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 5d 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 · 476 lines

How it starts

The opening of the file, as written. The whole thing — 476 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Trustable AI Development Workbench

⚠️ CRITICAL: For AI Agents Working On This Project

VISION.md describes PROBLEMS TO SOLVE, not behaviors to emulate.

When VISION.md says "AI agents routinely claim completion without doing work" or "skip verification steps" - those are ANTI-PATTERNS this framework prevents. As an AI agent working ON this project:

  • DO: Verify all work is complete before marking tasks done
  • DO: Query external sources of truth (Azure DevOps, file system) to verify work exists
  • DO: Follow workflow verification gates explicitly - never skip them
  • DO: Implement the SOLUTIONS described in VISION.md (verification gates, state persistence)
  • DO NOT: Skip verification steps described in workflow templates
  • DO NOT: Claim work is complete without external verification
  • DO NOT: Reproduce the anti-patterns VISION.md describes

You are building the solution to AI unreliability. Execute workflows with complete, programmatic verification.


Overview

Trustable AI is an AI-assisted software lifecycle framework that solves the fundamental unreliability of AI coding agents (VISION.md). Generic AI agents fail software development tasks by claiming completion without doing work, skipping verification steps, and losing progress when sessions crash.

This framework doesn't make AI smarter - it makes AI failures visible and recoverable through structured SDLC processes that catch errors early.

Project Overview

Trustable AI is an AI-assisted software lifecycle framework featuring multi-agent orchestration, state management, and work tracking integration. It enables reliable software development with Claude Code through specialized agents, re-entrant workflows, and hierarchical context management.

Current State (v1.2.0):

  • ✅ Configuration system with Pydantic validation
  • ✅ Agent template rendering with project context injection (12 agents)
  • ✅ Workflow template rendering (7 workflows)
  • ✅ Work tracking platform adapters (Azure DevOps, file-based, extensible to Jira/GitHub)
  • ✅ CLI (trustable-ai) for initialization, configuration, and management
  • ✅ State management with re-entrancy support
  • ✅ Profiling and analytics
  • ✅ Skills system for reusable capabilities
  • ✅ Learnings capture system

Read the full file on GitHub · 476 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. 5d ago First seen · 476 lines · 4,180 tokens per session scan A fe370ddfd32c

Subscribe to this mod's changes

trustable-ai CLAUDE.md is an instructions file published in the GitHub repository keychain-io/trustable-ai (2 stars, last pushed 7mo ago), licensed MIT. It adds 4,180 tokens to every session, about $0.0209 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.

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 · 6,785 tokens

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.

openai/codex · 5,182 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, applying the notice (cutover) and fallback chain (never fail the build).

microsoft/vscode · 5,001 tokens

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.

github/spec-kit · 7,104 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 · 7,296 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 · 4,469 tokens