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 skills add adamancyzhang/claude-orchestrator-server --skill task-explorationgit clone --depth 1 https://github.com/adamancyzhang/claude-orchestrator-serverWrote 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/skills/adamancyzhang/claude-orchestrator-server/task-exploration)<a href="https://agentmods.dev/skills/adamancyzhang/claude-orchestrator-server/task-exploration"><img src="https://agentmods.dev/badge/skills/adamancyzhang/claude-orchestrator-server/task-exploration/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/skills/adamancyzhang/claude-orchestrator-server/task-exploration"><img src="https://agentmods.dev/badge/skills/adamancyzhang/claude-orchestrator-server/task-exploration.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 | $0.00111 | $0.01300 |
| Opus 5 | $0.00056 | $0.00650 |
| Sonnet 5 | $0.00022 | $0.00260 |
| Haiku 4.5 | $0.00011 | $0.00130 |
Grade A, and why
task-exploration 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 8d 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.
How it starts
The opening of the file, as written. The whole thing — 111 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Task Exploration
Exploration is not brainstorming. Every spawn must trace to evidence in the just-completed chain — never invent next steps the upstream artifacts do not support. This skill works alongside [[task-traceability]] so each spawn/close decision is auditable.
When to trigger
- The orchestrator runs with
--magicand the chain reached the explore link. - The previous five links (plan / execute / verify / review / accept) all produced result.md files in
<cache>/tasks/<task_id>/. - The Leader dispatches an
exploretask withchain_id,chain_depth, andmagic_max_chainspopulated. - (Re-entry case) A previous explore task was re-dispatched as feedback; re-read the prior
exploration-report.mdto avoid contradicting yourself.
Six-step process (Trace → Survey → Map → Evidence → Record → Decide)
Execute in order. Each step must pass before continuing; a failure at any step short-circuits to close_chain with a rationale (never silently to spawn_chain).
1. Trace — read every non-empty upstream artifact
Read in order:
{{upstream_plan_artifact}}(skip if null){{upstream_execute_artifact}}{{upstream_verify_artifact}}{{upstream_review_artifact}}{{upstream_accept_artifact}}— this is the most recent ground truth; start with the GO/NO-GO line.
If every artifact is empty or missing → write BLOCKED: no upstream artifacts to result_path and stop. The SelfEvaluator's fallback will emit reject.
2. Survey — read the cross-chain context
- Read the original requirement at
{{original_requirement_path}}. Look for chain drift: did the chain ship something materially different from what was asked? - If
parent_chain_summaryis non-empty (chain_depth > 0), read it. Note the parent's accept result so you don't recommend reverting the parent's own work. - Compare
chain_depth + 1againstmagic_max_chains:magic_max_chainsisunlimited→ no cap; freely consider spawn.chain_depth + 1 >= magic_max_chains→ the Leader will demote any spawn to close. Preferclose_chainwith a clarifying note over a wasted spawn.
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.
- 8d ago First seen · 111 lines · 111 tokens per session scan A 24a4e1cbec72
task-exploration is a skill published in the GitHub repository adamancyzhang/claude-orchestrator-server (2 stars, last pushed 1mo ago), licensed MIT. It adds 111 tokens to every session and 1,300 once invoked, about $0.0006 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 skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…
chronicle
Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…