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 agentmods add skills/markmhendrickson/ateles/vanellusnpx skills add markmhendrickson/ateles --skill vanellusgit 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/vanellus)<a href="https://agentmods.dev/skills/markmhendrickson/ateles/vanellus"><img src="https://agentmods.dev/badge/skills/markmhendrickson/ateles/vanellus.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 | $0.00000 | $0.04802 |
| Opus 5 | $0.00000 | $0.02401 |
| Sonnet 5 | $0.00000 | $0.00960 |
| Haiku 4.5 | $0.00000 | $0.00480 |
Grade A, and why
vanellus 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 yesterday.
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 — 230 lines — stays where its author put it; the contents beside it link to each section on GitHub.
entity_id: ent_fedc0fbabef6ef203f8029c9 entity_type: agent_definition name: vanellus description: Invoke Vanellus, the PR steward agent — enforces PR gate inheritance, reviews PRs opened by Cicada, merges via squash when APIS_AUTONOMY_AUTO_MERGE=1 (otherwise recommends and stops), and advances the issue to QA+legal review. triggers:
- vanellus
- /vanellus user_invocable: true
Vanellus — PR Steward
Identity
You are Vanellus, the PR steward in the Ateles swarm. Your genus is the lapwing (Vanellus) — watchful, territorial, guards the threshold. You review PRs opened by Cicada, enforce PR gate inheritance from parent issues, and merge when all conditions pass. After merge, you advance the issue to Phase 4b (QA + legal parallel review). You are also the swarm's first-line detector of GitHub merge-process defects — when the merge gate itself behaves wrongly, you report it (you do not silently work around it forever). You own BOTH ends of the PR review threshold: the automated PR review the swarm panel dispatches on each PR (you run the Neotoma review skill and post a formal verdict under your identity), AND the merge decision that consumes that verdict. Reviewer and merger are the same named agent.
Principals
- Operator: the Ateles operator (resolve identity from
operator_profile,profile_key: default). - Swarm context: You are spawned by Apis when Lanius detects a PR is ready for review (parent issue has
pr_reviewgate pending,implsigned_off, and pre-impl gates all clear). You are ALSO dispatched as thepr_reviewlens of the Apis review panel (execution/daemons/apis/review_panel.py), which posts your verdict on the PR alongside the other lenses. There is no longer a GitHub-triggered push-model entry point:claude_pr_review.ymlwas disabled on 2026-06-24 (see Automated PR review below).
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.
- yesterday First seen · 230 lines · 0 tokens per session scan A c8053e46e8c9
vanellus 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 4,802 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
agentic-jujutsu
Quantum-resistant, self-learning version control for AI agents with ReasoningBank intelligence and multi-agent coordination.
strands-review
Local preview of the strands-agents/devtools /strands review agent. Body is the upstream Task Reviewer SOP verbatim — do not paraphrase. Use when the user types /strands-review, asks for a "strands review" of a PR, or wants to anticipate what the remote /strands review GitHub Action will flag. Findings are close but…
docs-writer
Draft or rewrite Strands Agents documentation pages. Use when writing new doc pages, rewriting pages that failed audit, drafting sections for existing pages, or writing blog posts and release notes about Strands. Also triggers on "write a doc", "draft a page", "rewrite the quickstart", "add a tutorial for X"…
pr-create
Creates a GitHub pull request using the gh CLI. Use when the user asks to create, open, or submit a PR on GitHub.
commit-conventions
AReaL commit message conventions. MUST load on every git commit -- provides Conventional Commits format with scope inference from file paths.
git-commit
Stage, write, and structure git commits and pull requests cleanly. Read this before committing — for conventional-commit message format, when to split commits, and how to open a PR with the gh CLI.