cicada CLAUDE.md

cicada CLAUDE.md is an instructions file for coding agents from wende/cicada. It costs 1,410 tokens per session, scanned A, original, MIT.

A set of project instructions for AI assistants working on the Cicada codebase. It explains the supported languages, required commands, coding rules, testing process, and pull-request review workflow.

In plain words
What is it for?
Use it when developing, testing, formatting, committing, or reviewing pull requests in Cicada.
Why use it?
It helps the agent follow the repository’s specific rules instead of guessing which commands and practices to use.

Instructions file

Install

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.

agentmods
npx agentmods add instructions/wende/cicada/claude-md
Clone the repo
git clone --depth 1 https://github.com/wende/cicada

Wrote 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.

agentmods badge for cicada CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/wende/cicada/claude-md.svg)](https://agentmods.dev/instructions/wende/cicada/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/wende/cicada/claude-md"><img src="https://agentmods.dev/badge/instructions/wende/cicada/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 1,410 This file is loaded in full into every session.
When invoked 1,410 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.01410 $0.01410
Opus 5 $0.00705 $0.00705
Sonnet 5 $0.00282 $0.00282
Haiku 4.5 $0.00141 $0.00141

Measured 4d ago against content hash b6b2e7a18b13, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

cicada 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 4d 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.

CLAUDE.md · 143 lines

How it starts

The opening of the file, as written. The whole thing — 143 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CICADA - AI Assistant Guidelines

This file contains project-specific instructions for AI assistants working on the CICADA codebase.

Quick Reference

  • Language Support: Elixir, Python, Erlang (Beta), TypeScript (planned)
  • Primary Installation: uv tool install cicada-mcp
  • Storage Directory: ~/.cicada/projects/<repo_hash>/ (use cicada dir to find it)
  • Testing: Always use make test (never use pytest directly)
  • Development: Always use uv commands, run make dev after code changes

Critical Rules

Code Style & Testing

  • Use black for Python code formatting
  • Include type hints where appropriate
  • Write tests for new features
  • ALWAYS use make test for running tests - Never use pytest or uv run pytest directly
  • Always use uv to run any python commands
  • Don't use --no-verify unless explicitly asked
  • There is no such thing as unrelated tests. They need to pass before commit
  • Tags and publishing is automated via CI/CD

PR Review Workflow

When asked to review, address, or analyze PR comments, ALWAYS use make pr-comments first.

CRITICAL RULE: When addressing PR feedback, you MUST include "addressed" in your commit message.

# ✓ Good commit messages
git commit -m "Add gh CLI dependency check (addressed PR feedback)"
git commit -m "Addressed: Fix jq safe iteration"

# ❌ Bad - comment will still show up
git commit -m "Add gh CLI dependency check"

Cicada Tool Usage

ALWAYS use cicada-mcp tools for code concept searches. NEVER use Grep/Find for these tasks.

Use cicada tools for:
  • PRIMARY TOOL: mcp__cicada__query - Start here for ALL code exploration and discovery
  • DEEP-DIVE: mcp__cicada__search_module - View a module's complete API and dependencies
  • DEEP-DIVE: mcp__cicada__search_function - Find function definitions and call sites
  • UNIFIED HISTORY: mcp__cicada__git_history - One tool for all git history queries
  • DRILL-DOWN: mcp__cicada__expand_result - Expand a query result to see complete details
  • ADVANCED: mcp__cicada__query_jq - Execute jq queries against the Cicada index

Read the full file on GitHub · 143 lines

Changes

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.

  1. 4d ago First seen · 143 lines · 1,410 tokens per session scan A b6b2e7a18b13

Subscribe to this mod's changes

cicada CLAUDE.md is an instructions file published in the GitHub repository wende/cicada (40 stars, last pushed 1mo ago), licensed MIT. It adds 1,410 tokens to every session, about $0.0070 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 2026-08-30.