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 skills add markmhendrickson/ateles --skill regulusgit clone --depth 1 https://github.com/markmhendrickson/atelesWrote 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/skills/markmhendrickson/ateles/regulus)<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>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 | $0.00000 | $0.03074 |
| Opus 5 | $0.00000 | $0.01537 |
| Sonnet 5 | $0.00000 | $0.00615 |
| Haiku 4.5 | $0.00000 | $0.00307 |
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.
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.
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.
- today Changed cb43ccc6a87a
- 4d ago First seen · 170 lines · 0 tokens per session scan A 20499b1ecfee
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.
Other skills, from other repositories
local-llm-tool
Local LLM execution tool for text generation and chat through Ollama or vLLM endpoints. Use when: running on-prem inference, calling a local GPU model, or summarizing with a self-hosted LLM.
aaai
AAAI paper formatting — activate when the user wants AAAI template setup, migration, or formatting/compilation fixes.
colm
COLM (Conference on Language Modeling) paper formatting — activate when the user wants COLM template setup, migration, or formatting/compilation fixes.
review-pr
A pull-request review skill for evaluating proposed code changes and posting a quality verdict. A pull request is a request to merge changes into a shared codebase.
tasks
A task-breakdown tool that turns a plan, specification, feature brief, bug report, technical-debt item, or chore into small TASK-NNN work items. Technical debt means postponed cleanup or design work in a codebase.
conference-research
Academic venue paper discovery — activate when you need to find papers accepted at specific conferences or journals (ACL, EMNLP, NeurIPS, ICML, ICLR, MLSys, etc.), analyze venue acceptance preferences, or look up CFP requirements.