What is eatp-reference?

A technical reference for implementing EATP trust features in the Kailash SDK. EATP is a framework for recording and checking what an automated system is allowed to do and how that action can be traced.

Use it when building trust controls with the TrustPlane library, its Python API, command-line tool, or MCP server, including storage, key management, access roles, logging, and archives.

It gives implementers concrete patterns for storing trust data, managing keys, handling errors, and connecting the trust system to enterprise services.

How terrene-foundation/metis configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to terrene-foundation/metis. 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/terrene-foundation/metis/main/.claude/skills/26-eatp-reference/SKILL.md

Clone the repo

git clone --depth 1 https://github.com/terrene-foundation/metis

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/terrene-foundation/metis/26-eatp-reference/github.svg)](https://agentmods.dev/skills/terrene-foundation/metis/26-eatp-reference)

Your own site

<a href="https://agentmods.dev/skills/terrene-foundation/metis/26-eatp-reference"><img src="https://agentmods.dev/badge/skills/terrene-foundation/metis/26-eatp-reference/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/terrene-foundation/metis/26-eatp-reference"><img src="https://agentmods.dev/badge/skills/terrene-foundation/metis/26-eatp-reference.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 50 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 756 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin 95% copy Near-identical to another mod 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.

Model	Per session	Once invoked
Fable 5.1	$0.00050	$0.00756
Opus 5	$0.00025	$0.00378
Sonnet 5	$0.00010	$0.00151
Haiku 4.5	$0.00005	$0.00076

Measured 12d ago against content hash 6eee569e4e3a, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

eatp-reference 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 12d 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.

Origin

This is a copy

95% identical to eatp-reference — 2 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

.claude/skills/26-eatp-reference/SKILL.md · 47 lines

How it starts

The opening of the file, as written. The whole thing — 47 lines — stays where its author put it; the contents beside it link to each section on GitHub.

EATP SDK Implementation Reference

Implementation reference for the EATP trust module in the Kailash SDK. For EATP spec/concepts (5 elements, verification gradient, trust postures), see co-reference/eatp-spec.md.

TrustPlane Reference Implementation

Production-grade Python library implementing the full EATP trust chain.

3 store backends: SQLite (default), Filesystem, PostgreSQL
Key managers: LocalFileKeyManager (Ed25519), AWS KMS (ECDSA P-256), Azure Key Vault, HashiCorp Vault
11 hardened security patterns validated through 14 rounds of red teaming
22-class exception hierarchy, all tracing to TrustPlaneError
1473 tests, zero CRITICAL/HIGH findings

Entry Points

CLI: attest command (Click-based)
MCP Server: trustplane-mcp via FastMCP
Python API: from kailash.trust.plane.project import TrustProject

Enterprise Features

RBAC (4 roles), OIDC (JWKS auto-discovery), SIEM (CEF/OCSF/TLS syslog), Dashboard (bearer token auth), Archive (ZIP + SHA-256), Shadow mode (non-blocking evaluation)

Implementation Reference (load on demand)

eatp-trust-posture-canonical.md — Canonical TrustPosture names (AUTONOMOUS/DELEGATING/SUPERVISED/TOOL/PSEUDO), legacy aliases, mapper branch → posture table. Load first when touching trust posture tests.
eatp-sdk-quickstart.md — Getting started, 4-operation lifecycle, store selection
eatp-sdk-api-reference.md — Complete API surface, module reference, type signatures
eatp-sdk-patterns.md — Implementation patterns, critical gotchas, architecture
eatp-sdk-reasoning-traces.md — Reasoning trace extension, confidentiality, knowledge bridge
eatp-budget-tracking.md — BudgetTracker API, SQLiteBudgetStore, integer microdollars, threshold callbacks
eatp-posture-stores.md — PostureStore protocol, SQLitePostureStore, PostureEvidence
eatp-security-patterns.md — Red team security patterns: lock ordering, integer arithmetic, symlink rejection
eatp-store-backends.md — Adding new TrustPlaneStore backends (6-requirement security contract)
eatp-trust-plane-security.md — 11 hardened security patterns (TrustPlane-specific)
eatp-trust-plane-enterprise.md — RBAC, OIDC, SIEM, Dashboard, Archive, Shadow mode, Cloud KMS

Read the full file on GitHub · 47 lines

Files

What ships with it

11 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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.

12d ago First seen · 47 lines · 50 tokens per session scan A 6eee569e4e3a

Subscribe to this mod's changes

eatp-reference is a skill published in the GitHub repository terrene-foundation/metis (2 stars, last pushed 4mo ago), licensed Apache-2.0. It adds 50 tokens to every session and 756 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. It is 95% identical to eatp-reference, differing in 2 lines, and is treated as a copy.

Security

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

local-ai-agents

Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…

microsoft/ai-agents-for-beginners · 200 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

chat-pet-sprite-creation

Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.

microsoft/vscode · 53 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens

insight-error-page

Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…

vercel/next.js · 83 tokens

metis: Skill for Claude Code