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/discuss)<a href="https://agentmods.dev/commands/joaquimscosta/arkhe-claude-plugins/discuss"><img src="https://agentmods.dev/badge/commands/joaquimscosta/arkhe-claude-plugins/discuss/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/joaquimscosta/arkhe-claude-plugins/discuss"><img src="https://agentmods.dev/badge/commands/joaquimscosta/arkhe-claude-plugins/discuss.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 | $0.00010 | $0.00409 |
| Opus 5 | $0.00005 | $0.00204 |
| Sonnet 5 | $0.00002 | $0.00082 |
| Haiku 4.5 | $0.00001 | $0.00041 |
Grade A, and why
discuss 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 10d 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
Discuss: $ARGUMENTS
Step 1: Quick Context Scan
Before asking questions, gather relevant context about "$ARGUMENTS":
- Read CLAUDE.md if it exists in the project root (project guidelines and conventions)
- Use Grep/Glob to find files related to the topic mentioned in arguments
- Note patterns - existing implementations, naming conventions, or architectural decisions
This context will inform your questions and show the user you understand their codebase.
Step 2: Ask Informed Questions
Using the context gathered, ask focused questions in batches of 3.
Question Strategy:
- For open-ended exploration: Use text-based conversational questions
- For key decisions with clear options: Use the
AskUserQuestiontool with structured choices
Each batch should be tailored to the topic and informed by what you found in the codebase. Reference specific files or patterns you discovered to show contextual awareness.
Example structured question:
AskUserQuestion with options like:
- "Use existing pattern from UserService"
- "Create new pattern optimized for X"
- "Hybrid approach"
Step 3: Summarize & Recommend
After gathering sufficient context through discussion:
- Summarize key requirements and constraints discovered
- Recommend next steps:
- Direct implementation if scope is clear
/thinkfor single-problem deep reasoning/developfor multi-step implementation projects- Further discussion if more clarity needed
Guidelines
- Ask questions that demonstrate you've read the codebase
- Don't assume - verify understanding before proceeding
- Keep batches to 3 questions maximum for focus
- Use structured choices (AskUserQuestion) when there are clear options to pick from
- Stay focused on the topic; don't go on tangents
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.
- 10d ago First seen · 54 lines · 10 tokens per session scan A 161b704efe61
discuss is a command published in the GitHub repository joaquimscosta/arkhe-claude-plugins (21 stars, last pushed 26d ago), licensed MIT. It adds 10 tokens to every session and 409 once invoked, about $0.0001 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
stats
Show real token usage, delegation rate, and actual savings for the current Hydra session (parses Claude Code session JSONL — no AI estimation).
permissions
Create or update DOGMA-PERMISSIONS.md to configure what Claude can do autonomously.
merge
You are executing the /hydra:merge command. Merge a worktree branch back into the current branch.
parallel
You are executing the /hydra:parallel command. Start multiple agents simultaneously in different worktrees.
sandbox-promote
Promote an accepted, version-worthy WIP artifact from .credo/sandbox-tmp/ / to .credo/sandbox/ /. is the sandbox-tmp folder name (argument: $1).
add-skill
Add a new Skill to the current plugin with proper structure.