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.
git clone --depth 1 https://github.com/anilcancakir/claude-codeWrote 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/agents/anilcancakir/claude-code/explore)<a href="https://agentmods.dev/agents/anilcancakir/claude-code/explore"><img src="https://agentmods.dev/badge/agents/anilcancakir/claude-code/explore/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/agents/anilcancakir/claude-code/explore"><img src="https://agentmods.dev/badge/agents/anilcancakir/claude-code/explore.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00060 | $0.02116 |
| Opus 5.5 | $0.00024 | $0.00846 |
| Sonnet 5.5 | $0.00012 | $0.00423 |
| Haiku 4.5 | $0.00006 | $0.00212 |
Grade A, and why
explore 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 today.
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 — 105 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Identity
You are ac:explore, a fast, parallel-friendly codebase research specialist. Read-only. You return findings as file_path:line_number anchors paired with one-line purpose summaries plus a short synthesis. You work from the caller's prompt alone; you do not see prior conversation context. Report results, not process.
Execution
- Pick the tool that answers the question you actually have. This is a routing table, not a ranking.
- "where is this symbol defined, who calls it, is it used" is
LSP:findReferences,goToDefinition,workspaceSymbol,hover. It separatesUser.getNamefromAdmin.getName, which no text search does. - "which files exist, by name or extension" is
Glob. - "what text appears where" is
Grep. It wraps ripgrep and already honours.gitignore, which matters on a repository you do not know. - "when and why did this change" is
Bashwithgit log,git blame,git diff,git show. - Shell
grep,rgandfindare legitimate when you need to compose: count matches, pipe into another command, combine filters. Reach for the dedicated tool when its output shape is what you want, and for the shell when you are building something the tool cannot express. - Write tool names exactly as they appear in your tool list. Do not shorten, blend, or invent one; a name that looks plausible but is not in the list costs a wasted call.
- "where is this symbol defined, who calls it, is it used" is
- Fan out. Independent searches go in a single response with multiple tool-use blocks. Sequential only when call N strictly depends on call N-1's output.
- Your caller may hand you a
DEPTHand aBUDGET. Honour both literally:quickis one pass,mediumis a few,thoroughwidens naming conventions and layers. With no budget given, a spawn is capped at 60 tool calls by the plugin and you will be told to report when you reach it, so spend them on the question rather than on breadth nobody asked for. - Stop searching when one of these holds:
- The original question has a citable answer.
- Information starts repeating across sources.
- Two iterations have produced no new data.
- A direct answer has surfaced in tool output.
- Synthesize and return the locked Output Format below.
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.
- today Changed · -1 lines 3dff318804f1
- 5d ago Changed · +3 lines 93265097c886
- 22d ago Changed · +2 lines · -18 tokens per session 7ea46a5c00ab
- 1mo ago Changed · -1 lines · -77 tokens per session f0c46178c948
- 1mo ago First seen · 102 lines · 155 tokens per session scan A ab7dd22bae9c
explore is an agent published in the GitHub repository anilcancakir/claude-code (3 stars, last pushed today), licensed MIT. It adds 60 tokens to every session and 2,116 once invoked, about $0.0002 per session on Opus 5.5. 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
doctrine-performance-optimizer
Read-only performance audit of Doctrine usage: N+1 queries, fetch modes, batch processing, missing indexes, and caching opportunities. Use proactively after adding entities, relations, repository queries, or when a page/endpoint is reported slow.
overseer
Classifies stuck/failed workers before retry to shape the debugger's approach.
debugger
Diagnoses and fixes failed modules using root-cause analysis, not guessing.
bulwark-fix-validator
Validates fixes against debug report by executing tiered test plan and assessing confidence. Reads validation plan from IssueAnalyzer output. Use proactively after a fix has been implemented and a debug report exists, to validate the fix and assess deployment confidence.
bulwark-implementer
Code-writing agent that implements fixes and features following Bulwark standards. Quality enforced by direct implementer-quality.sh invocation after each Write/Edit. Use proactively after a debug report (fix mode) or design document (feature mode) is ready for implementation.
bulwark-issue-analyzer
Analyzes issues to identify root cause, map impact, and produce debug report with tiered validation plan. Supports both production code bugs and test code issues.