Getting it into your agent
This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.
/plugin marketplace add ANcpLua/ancplua-claude-plugins/plugin install exodiaWrote 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/commands/ancplua/ancplua-claude-plugins/deep-think)<a href="https://agentmods.dev/commands/ancplua/ancplua-claude-plugins/deep-think"><img src="https://agentmods.dev/badge/commands/ancplua/ancplua-claude-plugins/deep-think/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/commands/ancplua/ancplua-claude-plugins/deep-think"><img src="https://agentmods.dev/badge/commands/ancplua/ancplua-claude-plugins/deep-think.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 | $0.00036 | $0.01344 |
| Opus 5.5 | $0.00014 | $0.00538 |
| Sonnet 5.5 | $0.00007 | $0.00269 |
| Haiku 4.5 | $0.00004 | $0.00134 |
Grade A, and why
deep-think 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 14d 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 — 176 lines — stays where its author put it; the contents beside it link to each section on GitHub.
DEEP THINK — Multi-Perspective Reasoning Before Action
Three perspectives. One synthesis. No implementation — just understanding.
Problem: $0 Context: $1 (default: .) Mode: $2 (default: debug | debug|architecture|refactor|decision)
TEAM ARCHITECTURE
THINK LEAD (You — Synthesizer)
│
├─ Phase 1: PROBLEM UNDERSTANDING (3 agents parallel)
│ ├── debugger-mind
│ ├── architect-mind
│ └── explorer-mind
│ └── → IMMEDIATELY proceed
│
├─ Phase 2: SOLUTION SYNTHESIS (2 agents parallel)
│ ├── solution-designer
│ └── devils-advocate
│ └── → IMMEDIATELY proceed
│
└─ Phase 3: RECOMMENDATION (you — consolidate)
└── Summary table + recommended action
<CRITICAL_EXECUTION_REQUIREMENT>
STEP -1 — Inherit Prior Findings:
If <EXODIA_FINDINGS_CONTEXT> tag exists in session context, read .eight-gates/artifacts/findings.json.
Inject ALL findings as background context for Phase 1 agents — they should reason about existing evidence.
RUN ALL 3 PHASES WITHOUT STOPPING.
- Launch 3 Phase 1 agents in ONE message
- When complete, IMMEDIATELY launch 2 Phase 2 agents
- When complete, IMMEDIATELY present recommendation
DO NOT ask for confirmation between phases. YOUR NEXT MESSAGE: 3 Task tool calls for Phase 1. NOTHING ELSE.
</CRITICAL_EXECUTION_REQUIREMENT>
PHASE 1: PROBLEM UNDERSTANDING — 3 Agents
Launch ALL 3 in ONE message.
debugger-mind
subagent: general-purpose | model: opus You are debugger-mind. THINK AS A DEBUGGER. PROBLEM: $0 | CONTEXT: $1
- Actual problem vs perceived problem?
- ALL possible root causes (5+)
- Evidence to confirm/deny each
- Minimum viable investigation
- Assumptions being made
DO NOT propose solutions. Just understand completely. Output: Problem analysis with confidence per hypothesis
architect-mind
subagent: metacognitive-guard:arch-reviewer | model: opus You are architect-mind. THINK AS AN ARCHITECT. PROBLEM: $0 | CONTEXT: $1
- Where does this fit in the system?
- Boundaries and interfaces?
- Invariants violated?
- Ripple effects of changes?
- Local issue or systemic?
Output: Architectural context and implications
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.
- 14d ago First seen · 176 lines · 36 tokens per session scan A 004e3f04ef77
deep-think is a command published in the GitHub repository ANcpLua/ancplua-claude-plugins (6 stars, last pushed 3d ago), licensed MIT. It adds 36 tokens to every session and 1,344 once invoked, about $0.0001 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 2026-10-01.
Other commands, from other repositories
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.
implement
Execute the implementation plan by processing and executing all tasks defined in tasks.md.
speckit.bug.fix
Apply the remediation from a bug assessment and record what was changed.