Borrowing it
Nothing to install: this file belongs to pandazki/pneuma-skills. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/pandazki/pneuma-skills/main/.claude/agents/pneuma-explore.mdgit clone --depth 1 https://github.com/pandazki/pneuma-skillsWrote 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/pandazki/pneuma-skills/pneuma-explore)<a href="https://agentmods.dev/agents/pandazki/pneuma-skills/pneuma-explore"><img src="https://agentmods.dev/badge/agents/pandazki/pneuma-skills/pneuma-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/pandazki/pneuma-skills/pneuma-explore"><img src="https://agentmods.dev/badge/agents/pandazki/pneuma-skills/pneuma-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 | $0.00132 | $0.00282 |
| Opus 5.5 | $0.00053 | $0.00113 |
| Sonnet 5.5 | $0.00026 | $0.00056 |
| Haiku 4.5 | $0.00013 | $0.00028 |
Grade A, and why
pneuma-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 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
Read .agents/skills/dev-workflow/references/roles/explore.md before acting.
That file is the canonical role instruction shared with Codex.
Read root AGENTS.md and its matching domain-rule pointers as directed there.
Apply the parent's task, checkout, acceptance criteria, and authorization. Use the tools actually available in this session. Return the evidence and result format required by the shared role; do not merely summarize the guide.
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 Changed · -94 lines · -4 tokens per session b69fba548bc3
- 1mo ago First seen · 119 lines · 136 tokens per session scan A 7fefc64d1d76
pneuma-explore is an agent published in the GitHub repository pandazki/pneuma-skills (161 stars, last pushed today), licensed MIT. It adds 132 tokens to every session and 282 once invoked, about $0.0005 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 2026-08-30.
Other agents, from other repositories
implementer
Owns an MCP Task Orchestrator work item's implementation (work) phase — builds the change the item's queue-phase notes describe and fills the work-phase notes its resolved schema requires.
planner
Owns an item's queue-phase planning seat — verifies the plan, freezes decisions, fills the queue notes its seat owns.
reviewer
Owns an MCP Task Orchestrator work item's review phase — independently verifies the implementation against its plan and fills the review-phase notes its resolved schema requires.
test-author
Writes tests for a work item independently of its implementation — blind to production source by capability boundary, not by request.
director
Hardened director entry for claude --agent director - a session that runs the board (open runs, frontier, decisions, rollups) and delegates every read or edit to background agents and coordinators. Its tool list has no file or shell access.
planner
Researches codebase and creates detailed implementation plans. Use before any complex task to prevent regressions.