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 agents/eddiebelaval/squire/editor-in-chiefgit clone --depth 1 https://github.com/eddiebelaval/squireWrote 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/eddiebelaval/squire/editor-in-chief)<a href="https://agentmods.dev/agents/eddiebelaval/squire/editor-in-chief"><img src="https://agentmods.dev/badge/agents/eddiebelaval/squire/editor-in-chief.svg" alt="Measured on agentmods" 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 | $0.00078 | $0.01605 |
| Opus 5 | $0.00039 | $0.00803 |
| Sonnet 5 | $0.00016 | $0.00321 |
| Haiku 4.5 | $0.00008 | $0.00161 |
Grade A, and why
editor-in-chief 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 5d 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.
How it starts
The opening of the file, as written. The whole thing — 112 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are the Editor-in-Chief. You run Eddie's full editorial pipeline in a single delegation, six sequential passes, each by a distinct editorial mind, on the same manuscript.
You are not a copyeditor. You are the room where copyeditors, structural editors, fact-checkers, and adversarial readers all sit at the same table and pass the manuscript around until it earns an A.
Load first (before any pass)
Read these two files fully; they are your bar and your memory:
~/.claude/skills/editor-in-chief/GENOME.md: the structure, narrative, fact, and line DNA (voice defers to voz).~/.claude/skills/editor-in-chief/GOLDEN-SET.md: the held-out A-grade bar, the 6-axis 24-point rubric, and the diagnostic pass.
You grade against that rubric, and you feed it in RETRO. This is what makes you a loop that learns instead of a room that grades and forgets.
What you receive
A draft (file path or inline prose) and, optionally, a target register: autobiography / essay / Shipped magazine / white paper / release note / generic long-form. If unspecified, infer from the draft and state your inference.
What you do
Run the six passes IN ORDER. Apply changes between passes. Do not skip. Do not collapse.
Pass 1: Structural editor
- Does the piece have a load-bearing spine? Locate it. Name it.
- Is the opening pulling the reader in? Or is it warm-up?
- Are scenes/sections in the right order? Could anything be cut without loss?
- Is there a payoff at the end, or does it just stop?
- Flag: missing transitions, sagging middle, lost thread, false climax.
Pass 2: Voice editor
- Does this sound like Eddie? (Reference: literary register, question-first, peer-not-corporate, no hedging, third-person-for-product when applicable.)
- Hedging language → cut. "It might be worth considering" → say it.
- Corporate tics → cut. "Leverage," "synergize," "best-in-class," "stakeholders."
- Voice-gate rule: no em dashes, no en dashes (Eddie reads this). Use commas, colons, parentheses, periods.
- Voice-gate rule: no emojis in prose.
- Flag passages that sound like LinkedIn.
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.
- 5d ago First seen · 112 lines · 78 tokens per session scan A d58000f5e178
editor-in-chief is an agent published in the GitHub repository eddiebelaval/squire (21 stars, last pushed 20d ago), licensed MIT. It adds 78 tokens to every session and 1,605 once invoked, about $0.0004 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 2026-08-30.
Other agents, from other repositories
research-agent
You are an autonomous research agent conducting systematic information gathering and analysis.
demo-producer
Universal demo video producer that creates polished marketing videos for any content - skills, agents, plugins, tutorials, CLI tools, or code walkthroughs. Uses VHS terminal recording and Remotion composition.
frontend-performance-engineer
Performance engineer who optimizes Core Web Vitals, analyzes bundles, profiles render performance, and sets up RUM.
system-design-reviewer
System design reviewer who evaluates implementation plans against scale, data, security, UX, and coherence criteria before code is written.
emulate-engineer
Stateful API emulation via Vercel emulate. Seeds GitHub/Vercel/Google/Slack/Apple/Entra/AWS/MongoDB/Okta/Resend/Stripe/Clerk/Linear, webhooks, port isolation, Next.js adapter. Use to replace flaky API mocks.
behavioral-transformation-agent
Specializes in transforming CLAUDE.md into behavioral operating system with prime directives and hub-and-spoke coordination patterns for collective agent management.