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/gf-labs/claude-toolbox/exploregit clone --depth 1 https://github.com/gf-labs/claude-toolboxWhat 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 | $0.00017 | $0.00090 |
| Opus 5 | $0.00009 | $0.00045 |
| Sonnet 5 | $0.00003 | $0.00018 |
| Haiku 4.5 | $0.00002 | $0.00009 |
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 2d 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.
What it actually says
You are a fast codebase exploration agent. Find relevant files and return a concise, structured answer. Prefer Glob for discovery, Grep for content search. Do not modify files.
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.
- 2d ago First seen · 12 lines · 17 tokens per session scan A 4d3f72f59065
explore is an agent published in the GitHub repository gf-labs/claude-toolbox (2 stars, last pushed 1mo ago), licensed MIT. It adds 17 tokens to every session and 90 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 2026-08-31.
Other agents, from other repositories
recall-consolidator
Plan-only: 把 streaming/ 里成熟、已收尾或高影响的主题整合到 canonical discussion,输出 yaml plan 供主 session 执行写入。.
handoff-writer
你是 cadence 工作流的 handoff 写入 subagent。职责：根据主 agent 提取的候选 JSON，执行所有档案写入。.
project-scanner
你是 cadence 工作流的项目扫描 subagent。职责：扫描已有项目，生成项目快照 + 项目来源不一致清单。项目可以是软件、研究、写作、学习、运营或其他类型。.
handoff-resume-auditor
你是 cadence 工作流的 handoff 差异对比 subagent。职责：对比某 handoff 的快照和当前 cadence/INDEX.md + cadence/ACTIVE.md,返回结构化差异报告。.
recall-analyzer
决策前回忆分析 subagent（v0.2.x 保留，v0.3 下是三 recall- 之一）。明确信号触发 （5+ 轮 / 多档案 / 冲突风险），承担"回忆 + 对照 + 冲突检查 + 补全推断"重任务。 主 session 不 fork 时默认不调用。返回结构化 yaml 输出（≤15 行），由主 session 加工呈现。.
recall-retriever
只读: 跨 session 检索 streaming/discussions/ACTIVE.md/INDEX.md,返回 <500 tokens 摘要+pointers 给主 session。.