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 instructions/ecodan/cicadas/claude-mdgit clone --depth 1 https://github.com/ecodan/cicadasWhat 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 | $0.03000 | $0.03000 |
| Opus 5 | $0.01500 | $0.01500 |
| Sonnet 5 | $0.00600 | $0.00600 |
| Haiku 4.5 | $0.00300 | $0.00300 |
Grade A, and why
cicadas CLAUDE.md 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 2d 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 — 151 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository. It is not used by Cursor, Antigravity, Rovodev, or other agents — those environments use the Cicadas skill file (SKILL.md / cicadas.mdc) alone, which includes the same implementation guardrails.
Python / Environment
Tests are written in unittest style and are commonly run with uv run pytest. The project currently declares pytest and pytest-cov in the dev dependency group in pyproject.toml, and recent CLI coverage was verified with uv run pytest.
Commands
Run all tests:
uv run pytest
Run a single test file:
uv run pytest tests/test_kickoff.py
Run the context-template regression checks:
uv run pytest tests/test_templates.py
Run a single test:
uv run pytest tests/test_kickoff.py -k test_basic_kickoff
Run with coverage:
uv run pytest --cov=src/cicadas/scripts --cov-report=term-missing
Lint:
source .venv/bin/activate && ruff check src/ tests/
Format:
source .venv/bin/activate && ruff format src/ tests/
CLI scripts:
python src/cicadas/scripts/cicadas.py init
python src/cicadas/scripts/cicadas.py status
python src/cicadas/scripts/cicadas.py check
python src/cicadas/scripts/cicadas.py kickoff {name} --intent "..."
python src/cicadas/scripts/cicadas.py kickoff {name} --intent "..." --worktree
python src/cicadas/scripts/cicadas.py branch {name} --intent "..." --modules "mod1,mod2" --initiative {name}
python src/cicadas/scripts/cicadas.py branch {name} --intent "..." --modules "mod1,mod2" --initiative {name} --worktree
python src/cicadas/scripts/cicadas.py signal "message"
python src/cicadas/scripts/cicadas.py archive {name} --type {branch|initiative}
python src/cicadas/scripts/cicadas.py update-index --branch {name} --summary "..."
python src/cicadas/scripts/cicadas.py create-lifecycle {name} # optional: --pr-specs, --no-pr-initiatives, etc.
python src/cicadas/scripts/cicadas.py open-pr [--base branch] # open PR from current branch (gh/glab/URL/fallback); blocks on BLOCK verdict
python src/cicadas/scripts/cicadas.py review [--initiative name] # check review.md verdict (exit 0=PASS, 1=BLOCK, 2=not found)
python src/cicadas/scripts/cicadas.py prune {name} --type {branch|initiative}
python src/cicadas/scripts/cicadas.py abort
python src/cicadas/scripts/cicadas.py history [--output path]
python src/cicadas/scripts/cicadas.py validate-skill {slug-or-path}
python src/cicadas/scripts/cicadas.py skill-publish {slug} [--publish-dir DIR] [--symlink] [--force]
python src/cicadas/scripts/cicadas.py unarchive {name}
python src/cicadas/scripts/cicadas.py emit-event --initiative {name} --type {event.type} [--data '{json}']
python src/cicadas/scripts/cicadas.py get-events --initiative {name} [--type prefix] [--since ISO] [--last N]
python src/cicadas/scripts/cicadas.py graph build
python src/cicadas/scripts/cicadas.py graph search <query>
python src/cicadas/scripts/cicadas.py graph watch
python src/cicadas/scripts/cicadas.py graph usage --view table
python src/cicadas/scripts/cicadas.py tutorial
python src/cicadas/scripts/cicadas.py init --tutorial # run tutorial automatically
python src/cicadas/scripts/cicadas.py init --no-tutorial # skip tutorial prompt
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.
- 2d ago First seen · 151 lines · 3,000 tokens per session scan A e04cdde5169f
cicadas CLAUDE.md is an instructions file published in the GitHub repository ecodan/cicadas (9 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 3,000 tokens to every session, about $0.0150 per session on Opus 5. 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 instructions, from other repositories
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
next.js AGENTS.md
Instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.