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/wende/cicada/claude-mdgit clone --depth 1 https://github.com/wende/cicadaWrote 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/instructions/wende/cicada/claude-md)<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>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 | $0.01410 | $0.01410 |
| Opus 5 | $0.00705 | $0.00705 |
| Sonnet 5 | $0.00282 | $0.00282 |
| Haiku 4.5 | $0.00141 | $0.00141 |
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.
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>/(usecicada dirto find it) - Testing: Always use
make test(never usepytestdirectly) - Development: Always use
uvcommands, runmake devafter code changes
Critical Rules
Code Style & Testing
- Use
blackfor Python code formatting - Include type hints where appropriate
- Write tests for new features
- ALWAYS use
make testfor running tests - Never usepytestoruv run pytestdirectly - Always use
uvto 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
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.
- 4d ago First seen · 143 lines · 1,410 tokens per session scan A b6b2e7a18b13
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.
Other instructions, from other repositories
repobrain copilot-instructions.md
Copilot instructions for study8677/repobrain, covering github copilot bootstrap instructions and hard rule — query the repobrain hub first.
octocode CLAUDE.md
Claude Code instructions for bgauryy/octocode: Read AGENTS.md. Discover repository skills under .agents/skills and activate only those matching the task.
trace-mcp CLAUDE.md
Claude Code instructions for nikolai-vysotskyi/trace-mcp, covering trace-mcp development guide, what this project is, agent behavior — read before every task, no flattery, no filler and disagree when the premise is wrong.
trace-mcp AGENTS.md
AGENTS.md instructions for nikolai-vysotskyi/trace-mcp: IMPORTANT: For ANY code exploration task, ALWAYS use trace tools first. NEVER use Read/Grep/Glob/Bash(ls,find) for navigating source code.
codesage AGENTS.md
Instructions for iliaal/codesage, covering codesage, build, sanity check before pushing, crate map and search pipeline.
pixir AGENTS.md
Instructions for Ranvier-Technologies/pixir, covering agents.md - pixir harness, progressive discovery, screaming architecture, beta stance and commands.