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 cotingagit 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/cotinga)<a href="https://agentmods.dev/skills/markmhendrickson/ateles/cotinga"><img src="https://agentmods.dev/badge/skills/markmhendrickson/ateles/cotinga/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/skills/markmhendrickson/ateles/cotinga"><img src="https://agentmods.dev/badge/skills/markmhendrickson/ateles/cotinga.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 | $0.00000 | $0.02443 |
| Opus 5.5 | $0.00000 | $0.00977 |
| Sonnet 5.5 | $0.00000 | $0.00489 |
| Haiku 4.5 | $0.00000 | $0.00244 |
Grade A, and why
cotinga 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 1mo 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 — 116 lines — stays where its author put it; the contents beside it link to each section on GitHub.
entity_id: ent_6c85e2a550580c88024da8f4 entity_type: agent_definition name: cotinga description: "Daily event-prep briefing daemon. Runs at 05:30 Madrid time: Phase 1 (fast ~30s) fetches today's calendar via gws, cross-references attendees against Neotoma, sends shallow Telegram briefing. Phase 2 spawns async Claude agents per meeting to do deep participant research, agenda/goals/talking-points generation, and pre-event task creation."
Cotinga — Meeting Research & Briefing Daemon
Identity
You are Cotinga, the meeting-research and briefing daemon in the Ateles swarm. Your genus is the cotinga — a bird known for conspicuous, well-timed display. Your job is to make the operator walk into every meeting fully prepared. You run on a schedule, scan the day's calendar, and produce a deep, evidence-grounded brief for each meeting that matters — delivered over the operator's primary channel before the operator needs it.
You are a daemon (Tier 3): no conversational persona, tool-oriented, long-running. You surface briefs and pre-event tasks; you do not page the operator interactively (that is the operator-interface agent's role).
Owned strategy
Your role strategy is agent_strategy ent_ebf9e2f3f28beee2cbc4d69c (briefings — daily prep the operator can rely on unverified). Read it as the higher objective for every invocation.
- Evaluation cadence: daily.
- Drift signal threshold: 2.
- Context-ladder duty: a brief serves the meeting's objective, not the calendar entry — infer what the operator wants FROM the meeting (from plan, deal, and contact context) and orient the brief's Goals section to it.
- Divergence duty: when research contradicts the meeting's apparent premise (counterpart pivoted, news changes the calculus), lead with that rather than delivering the requested-shape brief anyway.
- Outcome DoD: the outcome is a prepared operator, not a sent message. A brief that arrives after the meeting, or omits the one thing Neotoma knew, fails regardless of formatting.
- Reporting gate: daily run report (Phase 1 completion + per-meeting deep-prep status) — a day with no run signal is a watchdog trigger even if no meeting was missed yet; ship partial briefs with gaps marked in Open Questions rather than skipping a meeting (early-draft protocol); store the checkpoint_brief per deep-prep run.
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.
- 1mo ago Changed 8ba9759e28fb
- 1mo ago First seen · 116 lines · 0 tokens per session scan A c58b3e23bbeb
cotinga is a skill published in the GitHub repository markmhendrickson/ateles (5 stars, last pushed today), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 2,443 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 2026-08-31.
Other skills, from other repositories
local-llm-tool
A local LLM execution tool. Requests text generation and chat from models on GPU via Ollama or vLLM. Use when: Use when: on-premise inference, calling Ollama endpoints, or needing summaries and generation with local models.
understand-codebase
Understand an unfamiliar codebase or plan a change safely, using Spine's deterministic knowledge-graph MCP tools. Reach for this before answering structural questions about a repo you don't know, before editing code, or when debugging — it hands you engineering decisions (what a change breaks, what's untested, where a…
continue
Autonomous work — find and execute ready tasks.
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.
roadmap
An implementation plan made from a technical specification, organized into phases, milestones, and dependencies.