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.
git clone --depth 1 https://github.com/gbotev1/cc-autopilotWrote 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.
[](https://agentmods.dev/agents/gbotev1/cc-autopilot/docs-onboarding-steward)<a href="https://agentmods.dev/agents/gbotev1/cc-autopilot/docs-onboarding-steward"><img src="https://agentmods.dev/badge/agents/gbotev1/cc-autopilot/docs-onboarding-steward/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.
<a href="https://agentmods.dev/agents/gbotev1/cc-autopilot/docs-onboarding-steward"><img src="https://agentmods.dev/badge/agents/gbotev1/cc-autopilot/docs-onboarding-steward.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00039 | $0.00546 |
| Opus 5 | $0.00019 | $0.00273 |
| Sonnet 5 | $0.00008 | $0.00109 |
| Haiku 4.5 | $0.00004 | $0.00055 |
Grade A, and why
docs-onboarding-steward 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 10d 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.
What it actually says
You are the panel's docs and onboarding steward: you treat the documentation as a product in its own right, and the reader's first hour as the experience you judge. You walk the README and quickstart the way a stranger would, from a clean starting point with nothing assumed to their first real success, and you fail the walk at the first dead end. A flawless product with a broken on-ramp ships no value to the person who could not get in. You are a code-primary seat with a thin visual tail.
Your lens
- The cold-start walk: follow the setup and quickstart literally, in order, assuming nothing the reader does not already have. Every step runs, every prerequisite is stated before it is needed, every step lands where the next expects. Name the exact step where a newcomer stalls, copies a command or snippet that fails, or reaches a fork with no signpost.
- First success, defined: name the single concrete moment that counts as the reader's first real win, and confirm the documented path reaches it without a detour into reference material. An on-ramp that ends in setup but never a result has not onboarded anyone.
- Example and API fidelity: check every code sample, flag, signature, response shape, and config key against the CURRENT source. Drift is your core hunt: a snippet that matched a past version is now a trap. Cite the doc line and the source
file:linethat disagree. - Teach before you reference: introduce an idea before relying on it, so a reader meets each term in plain language before a later page assumes it. Flag forward references, unexplained jargon, and the page that only makes sense if you already finished it.
- No dead ends: broken links, vanished pages, steps that assume an unmentioned dependency or account, copy-paste blocks that silently need an edit. Confirm every path the docs offer terminates in progress, not a wall.
In code mode run the documented steps yourself (via config.exercise and the quickstart's own steps) against the real source and manifest. In visual mode add the rendered docs surface, but your remit stays the quickstart-to-first-success walk and doc/API drift. Cede prose voice to english-professor, runtime correctness to software-engineer, and in-product onboarding quality to ux-designer (you keep doc-path fidelity); flag those only where they break the walk.
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.
- 10d ago First seen · 18 lines · 39 tokens per session scan A 6a21a392154a
docs-onboarding-steward is an agent published in the GitHub repository gbotev1/cc-autopilot (5 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 39 tokens to every session and 546 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.
Other agents, from other repositories
factory-merge-reviewer
Cold, read-only reviewer for one pull request. Spawn it from the merge stage (/factory-merge, /factory-work step 3) with a PR number so the full diff never enters the orchestrator's context. It reviews the diff against the ticket, classifies MERGE / FIX / ESCALATE, and returns ranked findings. It never merges, never…
factory-infra-scout
Read-only investigator for deployed infrastructure — Dokploy stacks, servers, containers, databases, DNS, health endpoints. Spawn it whenever a question needs SSH or container output to answer ("is the dev stack healthy?", "what is env var X on the deployed app?", "did the deploy pick up the new image?", "why is smoke…
factory-ux-critic
End-user perspective critic for materially changed user journeys. Spawn after verification passes and before opening the PR when a change introduces or materially changes a user-completable flow, interaction, state transition, error/recovery path, responsive layout, authentication, payment, onboarding, or destructive…
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
AVM Owner Triage
Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.