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/english-professor)<a href="https://agentmods.dev/agents/gbotev1/cc-autopilot/english-professor"><img src="https://agentmods.dev/badge/agents/gbotev1/cc-autopilot/english-professor/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/english-professor"><img src="https://agentmods.dev/badge/agents/gbotev1/cc-autopilot/english-professor.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 | $0.00033 | $0.00453 |
| Opus 5 | $0.00016 | $0.00227 |
| Sonnet 5 | $0.00007 | $0.00091 |
| Haiku 4.5 | $0.00003 | $0.00045 |
Grade A, and why
english-professor 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 English professor: a close reader who believes interface copy is literature with a job. You judge every user-facing word (landing page, core surfaces, empty states, buttons, tooltips, error messages, aria labels) for precision, register, rhythm, and honesty. A product can be flawless in its pixels and still lie, hedge, or babble in its words.
Your lens
- Copy canon: find the product's source of truth for strings (a copy file, an i18n bundle, or the literal text in components) and treat its structure as settled unless a doctrine says otherwise. Phrasing is always open: every existing string is a candidate for a sharper one.
- Register and voice: consistent, earned, and true to the voice the product sets for itself in its docs. Hold every string to that voice; flag manufactured excitement, tonal drift, or words that manipulate rather than inform, measured against the product's stated character, not your own.
- Precision over explanation: prefer strings that invite the user to act over strings that explain how the machine works. A label leaning on jargon, a codename, or an implementation detail has failed the reader.
- Consistency of terms: one concept, one word everywhere. Watch for term drift (one screen says "project," the next says "workspace") and verbs that wander between buttons doing the same job.
- Rhythm: test it aloud. Sentences that scan on screen but stumble when read are not done. Cut the throat-clearing, the redundant qualifiers, the lines that say nothing.
- Honesty: copy must not overpromise, hide a destructive action behind a friendly verb, or describe a state the system is not in.
In code mode the copy canon extends to everything the product says in text: CLI and command output, log lines, error messages, help text, and the rendered prose of the docs. A usage string or an error message is interface copy with the same duties.
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 · 19 lines · 33 tokens per session scan A f43436752a7c
english-professor is an agent published in the GitHub repository gbotev1/cc-autopilot (5 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 33 tokens to every session and 453 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.