trust

A command that manually assigns a skill a trust level such as verified, trusted, or autonomous. These levels control how much the system relies on the skill.

In plain words
What is it for?
Promoting or restoring a named skill to a chosen trust level.
Why use it?
It allows an explicit trust decision when the normal automatic process should be bypassed.

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/ankitkr3/compounded/trust
Clone the repo
git clone --depth 1 https://github.com/ankitkr3/compounded
Per session 40 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 176 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 $0.00040 $0.00176
Opus 5 $0.00020 $0.00088
Sonnet 5 $0.00008 $0.00035
Haiku 4.5 $0.00004 $0.00018

Measured yesterday against content hash 18538ac24d5d, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

trust 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.

commands/trust.md · 12 lines

What it actually says

Manually set the trust tier for the requested skill:

!python3 ${CLAUDE_PLUGIN_ROOT}/scripts/pin_skill.py trust $ARGUMENTS

The $ARGUMENTS should be of the form <skill-name> --to <state>, where <state> is verified, trusted, or autonomous. If the user did not supply both, prompt them for the missing piece before running.

Note: this bypasses the trust gradient. Reserved for cases where the user is certain a skill should be at a particular tier (e.g., promoting a hand-authored skill to verified, or recovering after a misverification).

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. yesterday First seen · 12 lines · 40 tokens per session scan A 18538ac24d5d

Subscribe to this mod's changes

trust is a command published in the GitHub repository ankitkr3/compounded (5 stars, last pushed 2mo ago), licensed MIT. It adds 40 tokens to every session and 176 once invoked, about $0.0002 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.