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.
npx agentmods add commands/trustmybot/plugin/onboardgit clone --depth 1 https://github.com/trustmybot/pluginWhat 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 | $0.00029 | $0.01026 |
| Opus 5 | $0.00015 | $0.00513 |
| Sonnet 5 | $0.00006 | $0.00205 |
| Haiku 4.5 | $0.00003 | $0.00103 |
Grade A, and why
onboard 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.
How it starts
The opening of the file, as written. The whole thing — 70 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Onboard / Re-onboard
Bro orchestrates an AskUserQuestion ceremony in 2-3 rounds — Round 3 runs only when shape == 'remote'. Pass answers between AUQ and the server; all deterministic logic lives in the onboard_* MCP tools.
1. Read state (one MCP call)
Call onboard_state_get(agent='bro'). Returns { first_run, current, probe }. The server re-probes internally on each call, so bro never feeds the probe back — read state.probe only to spot a shape/remote conflict in Round 1.
2. Ask the questions
Run the AskUserQuestion ceremony in up to three rounds.
Round 1 — Project shape
Call onboard_get_questions(agent='bro', round='shape'). Feed the returned questions into AskUserQuestion. When a round returns no questions, skip its AUQ.
Store the answer as shape ∈ {local, remote}.
If the answer conflicts with the probe
Only when the user picks Local-only but state.probe.origin_kind showed github/gitlab, surface the contradiction:
Heads up: this project has a
<github|gitlab>origin remote, but you picked Local-only. Issues won't mirror to the remote and PRs/MRs won't be tracked. Continue, or switch to Remote-tracked?
Re-render Round 1 once. Trust the user's second answer.
Round 2 — Branching + PR target (per repo)
Branching model and PR target are per-repo. Enumerate repos with repos_list(agent='bro').
One repo — single pass. Call onboard_get_questions(agent='bro', shape=<shape>, round='main'), feed into AskUserQuestion, no per-repo framing.
Multiple repos — loop. For each repo <name>:
- Call
onboard_get_questions(agent='bro', shape=<shape>, round='main', repo=<name>). - Feed the returned branching + PR-target questions into
AskUserQuestion, framed for<name>. - Call
onboard_apply(agent='bro', shape=<shape>, repo=<name>, branching_model=<answer>, pr_target=<answer>)— writes only that repo's row.shapeis required (the value resolved in Round 1).
The remote/provider is git-derived (scan), not asked per repo — Round 2 asks only branching + PR target.
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 · 70 lines · 29 tokens per session scan A 5f674ad9a23c
onboard is a command published in the GitHub repository trustmybot/plugin (6 stars, last pushed 2d ago), licensed MIT. It adds 29 tokens to every session and 1,026 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.
Other commands, from other repositories
advisor
Advisory gate for triage or plan decisions. Spawns a second-opinion agent that challenges assumptions, surfaces risks, and proposes alternatives before the decision commits. Based on Anthropic advisor tool pattern.
guide
You are a triage agent who continuously prioritizes loom:issue issues by applying loom:urgent to the top 3 priorities.
pm-review
Review local git diff with reasoning + snippets; cross-check; dispose findings into the rules library.
new
Creates a new item in a module that supports the new capability.
card
Open one self-contained OverClick card.
linear-bulk
Apply the same change to many Linear issues at once. Dry-run by default.