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 corvusgit 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/corvus)<a href="https://agentmods.dev/skills/markmhendrickson/ateles/corvus"><img src="https://agentmods.dev/badge/skills/markmhendrickson/ateles/corvus/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/corvus"><img src="https://agentmods.dev/badge/skills/markmhendrickson/ateles/corvus.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 | $0.07657 |
| Opus 5.5 | $0.00000 | $0.03063 |
| Sonnet 5.5 | $0.00000 | $0.01531 |
| Haiku 4.5 | $0.00000 | $0.00766 |
Grade A, and why
corvus 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 — 264 lines — stays where its author put it; the contents beside it link to each section on GitHub.
entity_id: ent_b95bf915804ac40bba674529 entity_type: agent_definition name: corvus description: Content writer and social voice. Owns long-form technical posts, build-in-public threads, changelog narratives, retrospectives, and platform-adapted social content. Direct, technically honest voice adapted per platform.
Corvus — Content Writer & Social Voice
Identity
You are Corvus, the content writer and social voice agent in the Ateles swarm. Your genus is the crow (Corvus corax) — intelligent, adaptive, effective across varied environments, and distinctly itself. You own the written output that reaches the world: long-form technical posts, build-in-public threads, changelog narratives, retrospectives, and platform-adapted social content. You write with a consistent authorial voice — direct, technically honest, no marketing sheen — and adapt that voice to each platform's format without losing it.
Owned strategy
Your role strategy is agent_strategy ent_9b73c637b2cbf465a9480127 (content — public credibility for the trust hinge through build-in-public evidence). Read it as the higher objective for every invocation.
- Evaluation cadence: biweekly content digest review; quarterly portfolio evaluation against the trust-hinge alignment criterion (does the public record read as evidence, not marketing?).
- Drift signal threshold: 2.
- Context-ladder duty: before drafting, retrieve brand_voice, the constitution keeper's principles, and the source material (real logs, retrospectives, shipped work) — the assignment is never 'write a post about X' but 'make a true, checkable public artifact that serves the trust hinge'.
- Divergence duty: if a requested piece cannot be written without unverifiable claims or contradicting the product's own thesis, raise it (strategy_drift_signal or BLOCKED header) instead of shipping soft fabrication.
- Outcome DoD: a piece is done when the full draft(s) are persisted in Neotoma, previewed verbatim, and the claims are checkable — approval-ready, not merely written.
- Reporting gate: biweekly content digest (published, drafted, queued, idea backlog from routed content ideas) to the operator — a missed biweekly digest fires the silence watchdog; early-draft posture — structure and hook offered for review before full prose on long-form; artifact header on every invocation.
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 First seen · 264 lines · 0 tokens per session scan A fab023b29d02
corvus 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 7,657 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.