A command that creates a signed report of the current Claude Code session, containing an Agent Manifest and a TRACE record. It also creates a public verification key for checking the signature.

Use it to generate manifest.json, trace.json, and verification_key.json, then optionally verify the TRACE record with the supplied test command.

It provides a verifiable record of the session’s actual model, tools, and connected servers, helping others check that the report was not altered.

trace — Command by agentrust-io

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/trace

Clone the repo

git clone --depth 1 https://github.com/agentrust-io/integrations

Per session 13 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 462 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.

Model	Per session	Once invoked
Fable 5	$0.00013	$0.00462
Opus 5	$0.00006	$0.00231
Sonnet 5	$0.00003	$0.00092
Haiku 4.5	$0.00001	$0.00046

Measured yesterday against content hash 57769ff614cc, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

trace 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 yesterday.

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/trace.md · 40 lines

What it actually says

You are running the AgenTrust report command. Generate a signed record of THIS session and explain it in plain English. Engine: ${CLAUDE_PLUGIN_ROOT}/engine/capture.py.

Steps:

Ensure the signing packages are installed (once). Prefer the pinned set: pip install -r "${CLAUDE_PLUGIN_ROOT}/requirements.txt".
Write this session's real facts to live.json. Use values you actually observe, never invented ones: model_id, model_provider, model_version, builtin_tools (your actual built-in tools), mcp_servers (the MCP servers actually connected now).
Run python "${CLAUDE_PLUGIN_ROOT}/engine/capture.py" report --live-context live.json --out . This writes manifest.json, trace.json, and verification_key.json (the public key a third party uses to verify the manifest). The manifest is signed with the persistent key at ~/.claude/agentrust/signing_key.json; the private half never leaves the machine.
Optionally confirm the TRACE record passes the suite: trace-tests verify --record trace.json --level 0 (or python -m trace_tests.cli verify --record trace.json --level 0 if the console script is not on PATH).

Then explain the report the user actually cares about:

what the agent IS: skills, tools, MCP, model, permissions, each fingerprinted.
what it DID this run: the TRACE record, software-only and Level 0 on a dev box.
whether anything changed since their approved baseline.
that the records are shareable: manifest.json verifies on any machine with verification_key.json, and trace.json passes the public conformance suite.

Be honest about scope. No TEE on a normal laptop means Level 0, not hardware attestation. The instruction-layer fingerprint covers CLAUDE.md and memory, not Claude Code's internal system prompt, which is not on disk.

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.

yesterday First seen · 40 lines · 13 tokens per session scan A 57769ff614cc

Subscribe to this mod's changes

trace is a command published in the GitHub repository agentrust-io/integrations (2 stars, last pushed yesterday), licensed Apache-2.0. It adds 13 tokens to every session and 462 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.

Testing

trace

Getting it into your agent

What it costs to keep this loaded

Grade A, and why

Nothing flagged

What it actually says

What this file has done since we first saw it

Other commands, from other repositories

checklist

clarify

specify

analyze

converge

implement