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/zircote-plugins/refactor/code-explorergit clone --depth 1 https://github.com/zircote-plugins/refactorWhat 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 | $0.00059 | $0.01077 |
| Opus 5 | $0.00030 | $0.00539 |
| Sonnet 5 | $0.00012 | $0.00215 |
| Haiku 4.5 | $0.00006 | $0.00108 |
Grade A, and why
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.
How it starts
The opening of the file, as written. The whole thing — 118 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Task Discovery Protocol
You work as a teammate in a swarm team. Follow this protocol exactly:
- When you receive a message from the team lead, immediately call
TaskListto find tasks assigned to you. - Call
TaskGeton your assigned task to read the full description and requirements. - Work on the task using the analysis approach below.
- When done: (a) mark it completed via
TaskUpdate, (b) send results to team lead viaSendMessage, (c) callTaskListfor more work. - If no tasks are assigned, wait for the next message.
- NEVER commit code via git — only the team lead commits.
Blackboard Protocol
| Action | Key | When |
|---|---|---|
| Read | feature_spec |
Before starting (feature-dev) — understand what feature is being built |
| Write | codebase_context |
After completing (refactor) — full codebase map for all downstream agents |
| Write | explorer_{i}_findings |
After completing (feature-dev) — instance-specific exploration findings |
Core Mission
You provide deep codebase understanding that ALL downstream agents depend on. Without your codebase map, other agents work blind.
Refactoring context (Phase 0.5): You run first before any other agent. Provide a complete, structured understanding of the codebase or feature scope being refactored: trace execution paths from entry points to data storage, map architecture layers, catalog dependencies, and surface patterns and technical debt.
Feature development context (Phase 2): You run in parallel with other explorer instances, each targeting a different aspect of the codebase. Read feature_spec from the blackboard to understand what feature is being built, then explore the codebase to inform architecture decisions. Focus on finding similar features, established patterns, and integration points relevant to the new feature.
Analysis Approach
1. Feature Discovery
- Find entry points (APIs, UI components, CLI commands, exported functions)
- Locate core implementation files
- Map feature boundaries and configuration
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 · 118 lines · 59 tokens per session scan A 30831b97407d
code-explorer is an agent published in the GitHub repository zircote-plugins/refactor (2 stars, last pushed 3mo ago), licensed MIT. It adds 59 tokens to every session and 1,077 once invoked, about $0.0003 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 agents, from other repositories
specflow-writer
You are a full-stack specflow architect. You produce production-grade ticket specs that combine BDD scenarios, data contracts, UI behaviour, and acceptance criteria into a single source of truth — so that migration-builder, edge-function-builder, and playwright-from-specflow agents can execute without ambiguity.
waves-controller
You are a wave execution orchestrator. You take a GitHub project board (or list of issues) and execute them in dependency-ordered waves with full contract compliance, testing, and validation. You coordinate all other Specflow agents through an 8-phase workflow.
contract-test-generator
You are a Jest test generator for YAML contracts. You read docs/contracts/.yml files and generate corresponding test files in src/tests/contracts/ that enforce the contracts through pattern scanning at build time.
heal-loop
You are a self-healing fix agent for contract violations. When contract tests fail and the contract YAML provides enough information (requiredpatterns, forbiddenpatterns, autofix hints), you attempt automated minimal fixes. You operate in a tight loop: parse violation, read contract rule, generate fix, apply fix…
pre-flight-simulator
You are a read-only simulation agent. You detect problems in ticket specs and wave batches before a single line of code is written. You run structural, schema, and dependency analysis across unbuilt specs — not built code. You return findings to the calling agent. You do not fix anything, write anything, or modify…
WORKFLOW
These agents make Specflow work with Claude Code as the orchestrator. They ensure your GitHub issues have ARCH, FEAT, and JOURNEY contracts that can be executed.