CLAUDE

CLAUDE is an agent for coding agents from keychain-io/trustable-ai. It costs 0 tokens per session (2,113 once invoked), scanned A, original, MIT.

A set of specialized AI agents, each given a separate context and responsibility. Separate context means each agent receives only the information needed for its role.

In plain words
What is it for?
It includes roles such as business analysis and project management, helping assess feature value, revenue impact, customer benefit, and strategic fit.
Why use it?
It reduces confusion caused by long conversations containing unrelated tasks and instructions.

Agent

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 agents/keychain-io/trustable-ai/claude
Clone the repo
git clone --depth 1 https://github.com/keychain-io/trustable-ai

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

README.md
[![agentmods](https://agentmods.dev/badge/agents/keychain-io/trustable-ai/claude.svg)](https://agentmods.dev/agents/keychain-io/trustable-ai/claude)
Your own site
<a href="https://agentmods.dev/agents/keychain-io/trustable-ai/claude"><img src="https://agentmods.dev/badge/agents/keychain-io/trustable-ai/claude.svg" alt="Measured on agentmods" height="20"></a>
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,113 The whole file, excluding the scripts and references it only reads on demand.
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 $0.00000 $0.02113
Opus 5 $0.00000 $0.01056
Sonnet 5 $0.00000 $0.00423
Haiku 4.5 $0.00000 $0.00211

Measured 4d ago against content hash bac8838baf40, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

CLAUDE 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 4d 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.

agents/CLAUDE.md · 213 lines

How it starts

The opening of the file, as written. The whole thing — 213 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Agents

Purpose

Solves context overload (#3) and implements Agent Specialization (Pillar #3) from VISION.md.

When AI operates in overloaded context windows with mixed responsibilities:

  • Instructions from early conversation get forgotten
  • Constraints ignored due to context pollution
  • Work skipped because agent lost track of requirements
  • Hallucinations increase as context window fills

The agent system implements fresh context per role - each agent spawns in a clean context window with only the information needed for its specific responsibility. No conversation history, no accumulated cruft, just focused execution.

Key Agents

business-analyst

Problem Solved: Business value and priority decisions made without structured analysis

Analyzes backlog items for business value, revenue impact, customer benefit, and strategic alignment. Returns prioritized recommendations.

Real Failure Prevented: Feature prioritization happens in conversation. "Let's do the shiny feature first!" Ship feature with low ROI, delay high-value work. With business analyst: data-driven prioritization shows auth feature has 10x revenue impact vs UI polish. Build auth first.

project-architect

Problem Solved: Technical decisions made without architecture review or risk analysis

Reviews proposed features for technical feasibility, architecture patterns, integration complexity, and risks.

Real Failure Prevented: Engineer implements real-time updates with WebSockets. Architect review reveals: existing infra can't handle WebSocket connections, requires $5k/month infrastructure upgrade. Alternative: SSE with existing infra, zero extra cost.

senior-engineer

Problem Solved: Story point estimates made without task breakdown or historical data

Breaks features into granular tasks, estimates effort based on complexity, identifies unknowns.

Real Failure Prevented: Feature estimated at "3 points". Implementation reveals 8 integration points, 12 edge cases, security review needed. Actual: 13 points. With senior engineer breakdown: accurate 13-point estimate upfront, sprint capacity planned correctly.

Read the full file on GitHub · 213 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. 4d ago First seen · 213 lines · 0 tokens per session scan A bac8838baf40

Subscribe to this mod's changes

CLAUDE is an agent published in the GitHub repository keychain-io/trustable-ai (2 stars, last pushed 6mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 2,113 tokens. 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.