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/joaquimscosta/arkhe-claude-pluginsWrote 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/joaquimscosta/arkhe-claude-plugins/think)<a href="https://agentmods.dev/commands/joaquimscosta/arkhe-claude-plugins/think"><img src="https://agentmods.dev/badge/commands/joaquimscosta/arkhe-claude-plugins/think.svg" alt="Measured on agentmods" 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 | $0.00050 | $0.00306 |
| Opus 5 | $0.00025 | $0.00153 |
| Sonnet 5 | $0.00010 | $0.00061 |
| Haiku 4.5 | $0.00005 | $0.00031 |
Grade A, and why
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 7d 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
Think
Usage
/think <PROBLEM_OR_QUESTION>- Think through a specific problem/think- Think through the current context (what user is working on)
Context
Explicit problem (if provided): $ARGUMENTS
If no arguments provided: Analyze the current conversation context - what is the user working on? What problem, decision, or challenge are they facing? Use the conversation history to identify the thinking task.
Instructions
Use the Agent tool to spawn the deep-think-partner agent (subagent_type: "core:deep-think-partner") to collaboratively reason through either:
- The explicit problem provided in arguments, OR
- The implicit problem inferred from the current conversation context
The agent will:
- Restate the problem to confirm understanding
- Break it down into logical components
- Explore multiple angles and trade-offs
- Highlight uncertainties and assumptions
- Provide concrete recommendations
Let the agent lead the thinking process. Engage as a collaborative partner - build on insights, ask clarifying questions, and work toward a well-reasoned conclusion together.
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.
- 7d ago First seen · 38 lines · 50 tokens per session scan A 2a4183600d57
think is a command published in the GitHub repository joaquimscosta/arkhe-claude-plugins (21 stars, last pushed 24d ago), licensed MIT. It adds 50 tokens to every session and 306 once invoked, about $0.0003 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 2026-08-30.
Other commands, from other repositories
guard
Manually run the Hydra security and quality scan on specified files or directories.
cleanup
You are executing the /dogma:cleanup command. Your task is to find and fix AI-typical patterns in the codebase that reveal AI/agent usage.
lint
You are executing the /dogma:lint command. Your task is to detect the project type and run appropriate linting and formatting tools on staged files before commit.
perf
Structured performance investigation with baselines, profiling, and evidence-backed decisions.
p6-exploratory
Conducts unstructured, experience-based tests that automated tests and defined test cases do not cover. The goal is to find unexpected behaviours, usability issues, and hidden bugs that remain invisible in structured testing.
p8-ops
Analyses production errors and performance issues, evaluates incidents, and initiates countermeasures. Called reactively for specific incidents or proactively for regular operational reviews.