manifest

An integrity checker for a Claude Code agent, which compares the agent currently running with an approved baseline. The baseline records its tools, skills, connected servers, model, permissions, and instructions.

In plain words
What is it for?
Use it to create, inspect, or verify an integrity baseline and report what has been added, removed, or changed.
Why use it?
It helps detect unexpected changes to the agent before you trust its output or actions.

Command

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 commands/agentrust-io/integrations/manifest
Clone the repo
git clone --depth 1 https://github.com/agentrust-io/integrations
Per session 14 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 514 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 $0.00014 $0.00514
Opus 5 $0.00007 $0.00257
Sonnet 5 $0.00003 $0.00103
Haiku 4.5 $0.00001 $0.00051

Measured 2d ago against content hash eee12f2c0032, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

manifest 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 2d 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-code/commands/manifest.md · 49 lines

What it actually says

You are running the AgenTrust agent-integrity command. It answers one question for the user: is the agent they are running the one they approved, with nothing added and nothing subtracted since their baseline?

The engine is at ${CLAUDE_PLUGIN_ROOT}/engine/capture.py. It captures the agent's composition (skills, tools, MCP servers, model, permissions, instruction layer) and diffs it against the approved baseline at ~/.claude/agentrust/baseline.json.

The shell hook cannot see the live tool roster, so YOU enrich it. Before running, write the current session's real facts to a temp live.json. Use real values you actually observe this session, never invented ones:

{
  "model_id": "<the model you are running>",
  "model_provider": "anthropic",
  "model_version": "<version>",
  "builtin_tools": ["<your actual built-in tool names>"],
  "mcp_servers": ["<the MCP servers actually connected this session>"]
}

Then dispatch on $ARGUMENTS:

  • verify (default): run python "${CLAUDE_PLUGIN_ROOT}/engine/capture.py" verify --live-context live.json. Verify always re-reads the setup fresh and merges your live.json, so it reflects the agent's state right now, including drift introduced partway through this session. Show the result and explain any change in plain language, then ask whether to approve it.
  • approve: run python "${CLAUDE_PLUGIN_ROOT}/engine/capture.py" approve --live-context live.json --sign --out . to make the current composition the new approved baseline and write signed records. Use this when the user confirms the changes are intentional.
  • show: run python "${CLAUDE_PLUGIN_ROOT}/engine/capture.py" snapshot --live-context live.json to display the current composition without touching the baseline.

Report the result in plain English. Name the categories that changed (a skill, a permission, an MCP server, the instruction layer) and what the user should do about each. Never claim hardware attestation: on a normal dev box this is software-only (Level 0) integrity, not silicon-rooted proof.

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. 2d ago First seen · 49 lines · 14 tokens per session scan A eee12f2c0032

Subscribe to this mod's changes

manifest is a command published in the GitHub repository agentrust-io/integrations (2 stars, last pushed 2d ago), licensed Apache-2.0. It adds 14 tokens to every session and 514 once invoked, about $0.0001 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.