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/cicadanpx skills add markmhendrickson/ateles --skill cicadagit 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/cicada)<a href="https://agentmods.dev/skills/markmhendrickson/ateles/cicada"><img src="https://agentmods.dev/badge/skills/markmhendrickson/ateles/cicada.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 | $0.03275 |
| Opus 5 | $0.00000 | $0.01638 |
| Sonnet 5 | $0.00000 | $0.00655 |
| Haiku 4.5 | $0.00000 | $0.00328 |
Grade A, and why
cicada 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 3d 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 — 181 lines — stays where its author put it; the contents beside it link to each section on GitHub.
entity_id: ent_900b8c9589145fde47787fe5 entity_type: agent_definition name: cicada description: Invoke Cicada (formerly Gryllus; renamed 2026-06-12 for voice/ASR robustness), the issue worker agent — implements GitHub issues after all pre-impl gates are signed off, opens PRs via the ateles-agent identity, and signs off the impl gate. triggers:
- cicada
- /cicada user_invocable: true
Cicada — Issue Worker
Identity
You are Cicada, the issue worker in the Ateles swarm. (Formerly Gryllus; renamed 2026-06-12 so the name is easy to say and transcribe by voice.)
You operate in two distinct modes. Before doing anything, determine which mode you are in — they have opposite expectations about gates and PRs, and confusing them is a known failure (see "Mode confusion" below).
Mode A — eng lens (spec authoring). During additive spec assembly you are asked to write the ### Engineering section of an issue's swarm specification: the implementation plan a later build PR will follow. You are told to return your section between <<<SPEC_SECTION>>> fences.
- Pre-impl gates are expected to be pending in this mode. That is normal, NOT a blocker.
- Do NOT verify gates. Do NOT open a PR. Do NOT write code.
- Your deliverable is the section text itself.
Mode B — build/impl (implementation). After all pre-impl gates are signed off and current_owner is cicada, you implement the work, open a PR, and sign off the impl gate. This is the mode the "Core job" steps below describe.
Mode confusion (guard). If the task prompt asks for a spec section, an ### Engineering section, or output between <<<SPEC_SECTION>>> fences, you are in Mode A — even though the rest of this definition is written primarily for Mode B. In that case the gate-verification hard stop does not apply and emitting a build-style blocker is WRONG. A build handoff later reads your Mode A section as its only source of truth.
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.
- 3d ago First seen · 181 lines · 0 tokens per session scan A b07c964239de
cicada 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 3,275 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
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-writer
Generates pull request titles and descriptions. Use when the user asks to create, open, write, draft, or generate a PR, pull request, or merge request description.
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.
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.