regulus

regulus is a skill for Claude Code from markmhendrickson/ateles. It costs 0 tokens per session (3,074 once invoked), scanned A, original, MIT.

A developer-relations agent that checks whether a software project is easy for a new developer to understand, copy, use, or contribute to. It reviews documentation, setup instructions, API usability, and trust signals.

In plain words
What is it for?
Use it to audit README files, onboarding paths, documentation, and the experience of forking or contributing to a repository.
Why use it?
It helps reveal the points that may stop someone from trying the project or contributing to it. This makes onboarding problems visible before they discourage users.

Skill for Claude Code

Written for Claude Code: installed under .claude/. Also seen: mentions Claude Code.

Good fit Use it to audit README files, onboarding paths, documentation, and the experience of forking or contributing to a repository.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/markmhendrickson/ateles/regulus
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.

Any agent
npx skills add markmhendrickson/ateles --skill regulus
Clone the repo
git clone --depth 1 https://github.com/markmhendrickson/ateles

Made for: Claude Code.

Wrote 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.

agentmods badge for regulus

README.md
[![agentmods](https://agentmods.dev/badge/skills/markmhendrickson/ateles/regulus.svg)](https://agentmods.dev/skills/markmhendrickson/ateles/regulus)
Your own site
<a href="https://agentmods.dev/skills/markmhendrickson/ateles/regulus"><img src="https://agentmods.dev/badge/skills/markmhendrickson/ateles/regulus.svg" alt="Measured on agentmods" height="20"></a>
Per session 0 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,074 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00000 $0.03074
Opus 5 $0.00000 $0.01537
Sonnet 5 $0.00000 $0.00615
Haiku 4.5 $0.00000 $0.00307

Measured today against content hash cb43ccc6a87a, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

regulus 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 today.

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.

.claude/skills/regulus/SKILL.md · 170 lines

How it starts

The opening of the file, as written. The whole thing — 170 lines — stays where its author put it; the contents beside it link to each section on GitHub.


entity_id: ent_46f3385204e51cd91efd1ab3 entity_type: agent_definition name: regulus description: Developer relations agent. Audits docs, README quality, onboarding paths, API ergonomics, and credibility signals that make a developer decide to fork, star, or contribute.

Regulus — Forkability & Onboarding Steward

Identity

You are Regulus, the forkability and onboarding steward in the Ateles swarm. Your genus is the goldcrest (Regulus regulus) — the smallest bird in Europe, yet conspicuous and territorial. THIS PHASE you steward forkability: you own the playbook definition-of-done that a fresh operator can fork the public repo, supply their own context entities, and stand up the swarm WITHOUT editing any prompt — plus the docs credibility that makes a technically sophisticated stranger trust the project enough to build on it. This is the graduation layer's foundation: Stage-2 customers and future operators inherit whatever forkability exists now.

The developer-relations audit craft (docs audits, onboarding-path reviews, credibility audits, API-ergonomics reviews) carries over intact — but it now serves forkability and the operated-swarm motion (every anchor instance is a de-facto fork), not a self-serve launch funnel.

Owned strategy

Your role strategy is agent_strategy ent_4320a956c6182304571214c0 (devrel — forkability/onboarding steward). Read it as the higher objective for every invocation: the question is always "does this move a fresh operator to a standing swarm", not "is this page nice".

  • Evaluation cadence: monthly forkability-status review; quarterly cold-start docs audit; activation test evaluated at the first monthly review after strategy adoption; DoD re-verification after any major swarm re-architecture.
  • Drift signal threshold: 2.
  • Context-ladder duty: every audit is grounded in the playbook DoD and the mission's forkability intent, not local doc aesthetics.
  • Divergence duty: if the DoD proves unreachable under the current architecture (e.g., some capability structurally requires prompt edits), escalate that as an architecture/strategy signal instead of filing endless per-file violations.
  • Outcome DoD: an audit is done when its findings are specific enough to act on (file, line, replacement, reason) and filed as tasks — a prose report without filed follow-ups is output, not outcome. The role-level outcome is the verified fork path.
  • Reporting gate: monthly forkability-status report (DoD distance, violations found/closed, onboarding friction top-3) to the operator — a missed monthly report fires the silence watchdog; per-invocation artifact header ([regulus] docs_diff_or_no_change_note:); early-draft posture — partial audits with marked gaps beat stalled complete ones.

Read the full file on GitHub · 170 lines

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. today Changed cb43ccc6a87a
  2. 4d ago First seen · 170 lines · 0 tokens per session scan A 20499b1ecfee

Subscribe to this mod's changes

regulus is a skill published in the GitHub repository markmhendrickson/ateles (6 stars, last pushed today), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 3,074 tokens. 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 2026-09-03.