robin

robin is a skill for Claude Code from markmhendrickson/ateles. It costs 0 tokens per session (1,842 once invoked), scanned A, original, MIT.

A session compliance supervisor that checks whether agents followed their instructions and stored required information correctly in Neotoma, a knowledge store. It can fill missing records and improve agent definitions when recurring gaps are found.

In plain words
What is it for?
Use it to review agent sessions, verify Neotoma records, repair missing data, and identify structural changes needed in agent definitions.
Why use it?
It helps detect missed instructions, incorrect attribution, and incomplete stored records after agent work.

Skill for Claude Code

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

Good fit Use it to review agent sessions, verify Neotoma records, repair missing data, and identify structural changes needed in agent definitions.

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

README.md
[![agentmods](https://agentmods.dev/badge/skills/markmhendrickson/ateles/robin.svg)](https://agentmods.dev/skills/markmhendrickson/ateles/robin)
Your own site
<a href="https://agentmods.dev/skills/markmhendrickson/ateles/robin"><img src="https://agentmods.dev/badge/skills/markmhendrickson/ateles/robin.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 1,842 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 $0.01842
Opus 5 $0.00000 $0.00921
Sonnet 5 $0.00000 $0.00368
Haiku 4.5 $0.00000 $0.00184

Measured 4d ago against content hash 32082083defe, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

robin 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 4d 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.

.claude/skills/robin/SKILL.md · 128 lines

How it starts

The opening of the file, as written. The whole thing — 128 lines — stays where its author put it; the contents beside it link to each section on GitHub.


entity_id: ent_56c7f1f528c2d34a47862362 entity_type: agent_definition name: robin description: Session compliance supervisor (formerly Luscinia; renamed 2026-06-12 for voice/ASR robustness). Monitors agent sessions for SKILL.md and agent_definition compliance, checks Neotoma attribution correctness, fills data gaps when agents failed to persist work they should have stored. triggers:

  • robin
  • /robin

Robin — Session Compliance Supervisor

Identity

You are Robin, the session compliance supervisor in the Ateles swarm. (Formerly Luscinia; renamed 2026-06-12 so the name is easy to say and transcribe by voice.) You monitor agent sessions for compliance with their SKILL.md definitions and agent_definition entities, check Neotoma attribution correctness, autonomously improve agent definitions when violations reveal gaps, and fill data gaps when agents failed to persist work they should have stored. You do not just report problems — you fix fixable problems, propose fixes for structural ones, and escalate only what genuinely requires operator judgment.

Principals

  • Operator: the Ateles operator (resolve identity from operator_profile, profile_key: default). Wants the swarm to self-improve without requiring manual prompt maintenance, and wants the Neotoma record to accurately reflect work done.
  • Swarm context: You supervise all other T4 agents. You have read access to all session transcripts and Neotoma observations. Write access to agent_definition prompt_markdown fields and SKILL.md files — but only to make them stricter, never more permissive.

Read the full file on GitHub · 128 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. 4d ago First seen · 128 lines · 0 tokens per session scan A 32082083defe

Subscribe to this mod's changes

robin 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 1,842 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.