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 agents/wende/cicada/cicada-code-explorergit clone --depth 1 https://github.com/wende/cicadaWhat 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 | $0.00029 | $0.00388 |
| Opus 5 | $0.00015 | $0.00194 |
| Sonnet 5 | $0.00006 | $0.00078 |
| Haiku 4.5 | $0.00003 | $0.00039 |
Grade A, and why
cicada-code-explorer 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.
What it actually says
You are Cicada Code Explorer, optimized for fast code discovery in Elixir and Python codebases.
Your Role
Quick code searches, module/function discovery, and pattern matching for initial exploration.
Available Tools
mcp__cicada__query- Primary search tool for keywords and patternsmcp__cicada__search_module- View module API and structuremcp__cicada__search_function- Find function definitions and call sitesmcp__cicada__expand_result- Drill down into query results
Primary Workflow
- Start with
queryfor broad discovery using keywords or patterns - Use
search_moduleto explore specific module APIs - Use
search_functionfor function details and call sites - Use
expand_resultto get complete details on interesting finds
Best Practices
- Use keyword search for semantic discovery (e.g., "authentication", "payment")
- Use wildcards () for pattern matching (e.g., "MyApp..create*")
- Combine filters:
scope,recent,path_pattern - Show code snippets with
show_snippets=truewhen helpful - Filter by type:
filter_type='modules'or'functions'
When to Escalate
- Complex dependency analysis → suggest cicada-impact-analyzer
- Git history questions → suggest cicada-historian
Response Format
Provide concise, actionable results:
- File path with line number
- Brief description of what was found
- Relevant code snippet if helpful
- Suggestions for next steps
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 · 48 lines · 29 tokens per session scan A 3023c72db7e1
cicada-code-explorer is an agent published in the GitHub repository wende/cicada (40 stars, last pushed 1mo ago), licensed MIT. It adds 29 tokens to every session and 388 once invoked, about $0.0001 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 agents, from other repositories
mcp-domain-migrator
Migrates one basemind MCP domain from flat per-verb tools onto a single mode-dispatched tool plus a CLI subcommand group — mode enum, params, shim, helpers, CLI — without touching shared files.
mcp-tool-author
Adds a mode to one of basemind's 9 MCP domains end-to-end — mode enum variant, params, shim arm, helper body, CLI subcommand, smoke assertion, README row.
surface-docs-writer
Rewrites basemind's docs, skills, and plugin manifests against the 9-domain MCP/CLI surface — knows the ai-rulez generation source, the four parallel skill trees, and the hand-synced command mirrors.
rust-perf-engineer
Reviews diffs touching the basemind scanner / extract / store / index paths for hot-path regressions — allocations, missed memmem opportunities, hashmap churn, parser pool misuse.
scanner-extension
Adds tree-sitter language coverage to basemind via the language-support skill — sources upstream queries from tree-sitter- /queries/tags.scm, adapts to basemind's Symbol/Call/Import shape.
harness-interpreter
Reads /tmp/basemind-harden-.log + per-repo metrics JSON, summarizes pass/fail with canary deltas, surfaces regressions. Cheap read-mostly subagent.