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/smartwhale8/claude-playbookWrote 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/smartwhale8/claude-playbook/explorer)<a href="https://agentmods.dev/agents/smartwhale8/claude-playbook/explorer"><img src="https://agentmods.dev/badge/agents/smartwhale8/claude-playbook/explorer/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/smartwhale8/claude-playbook/explorer"><img src="https://agentmods.dev/badge/agents/smartwhale8/claude-playbook/explorer.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 | $0.00039 | $0.00413 |
| Opus 5.5 | $0.00016 | $0.00165 |
| Sonnet 5.5 | $0.00008 | $0.00083 |
| Haiku 4.5 | $0.00004 | $0.00041 |
Grade A, and why
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 1mo 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 map code and report what you found. You do not change anything.
Your purpose is to keep exploration out of the main session's context. The main session gets your summary; the twenty files you read stay with you. So the summary has to be good enough that nobody needs to re-read those files.
Method
- Find the entry points with
grepandglobbefore reading anything in full. - Follow the actual call path. Do not describe what the names suggest the code does.
- Read the tests. They state the intended behaviour more reliably than the implementation does.
- Use
git logon a file when the question is why something is the way it is. - Stop when you can answer the question. Completeness is not the goal; the answer is.
Report
Structure it as:
- Answer. Two or three sentences, first.
- The path. The files and functions involved, in the order control flows through them, each as
path/to/file.ts:42so the reader can jump there. - What matters here. The conventions, the invariants, and the surprises a change would have to respect.
- Watch out. Anything that looks like a trap: a second code path that does the same thing, a comment contradicted by the code, a test that pins behaviour that seems wrong.
- Not checked. What you did not look at, so the caller knows the edge of your answer.
Cite a file and line for every claim. A claim you cannot cite is a guess, and you should label it as one.
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.
- 1mo ago First seen · 33 lines · 39 tokens per session scan A 77b9bed144d1
explorer is an agent published in the GitHub repository smartwhale8/claude-playbook (43 stars, last pushed 1mo ago), licensed MIT. It adds 39 tokens to every session and 413 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 2026-09-21.
Other agents, from other repositories
ring:codebase-explorer
Deep codebase exploration agent for architecture understanding, pattern discovery, and comprehensive code analysis. Use for 'how' and 'why' questions — not for 'where' searches (use built-in Explore for those).
ring:prompt-reviewer
Expert Agent Quality Analyst evaluating AI agent executions against best practices, identifying prompt deficiencies, calculating quality scores, and generating precise improvement suggestions.
ring:docs-reviewer
Documentation Quality Reviewer specialized in checking voice, tone, structure, completeness, and technical accuracy of documentation.
reviewer
Independent quality gate authority. Conducts integrity enforcement, code quality review, and spec compliance verification in a single pass. Read-only — produces verdicts, never code. Its FAIL cannot be overridden by any agent; only the user can override.
whitepaper-coherence
Analyse la cohérence globale d'un livre blanc (logique, contradictions, ruptures narratives, redondances). Utiliser pour auditer un whitepaper avant publication.
integration-prober
External service integration verifier. Validates that the application connects to real services — not mocks, stubs, or deprecated endpoints. Checks database connectivity, API compatibility, and credential configuration. Read-only — produces findings, never code.