crush

crush is a skill for Claude Code from jazz1x/honne. It costs 44 tokens per session (1,106 once invoked), scanned A, original, MIT.

A guided debate between three saved personas: an unwanted behavior pattern, a preferred personal style, and a judge. A persona is a written profile that represents a particular way of responding.

In plain words
What is it for?
It is for debating a chosen topic when the required persona files exist, and for reporting when those personas are missing or incomplete.
Why use it?
It gives conflicting viewpoints a defined structure so you can examine a topic through different patterns of behavior.

Skill for Claude Code

Written for Claude Code: ${CLAUDE_PLUGIN_ROOT} variable.

Runs only inside its plugin — its command needs a path that Claude Code sets for a plugin’s own hooks and for nothing else. Install the plugin, not this.

Part of the honne plugin — 5 skills, 1 hook shipped together

Install

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.

Claude Code
/plugin marketplace add jazz1x/honne
Claude Code
/plugin install honne

Made for: Claude Code.

Or install honne, the plugin that ships this one along with the rest of its 5 skills, 1 hook.

Wrote 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.

agentmods badge for crush

README.md
[![agentmods](https://agentmods.dev/badge/skills/jazz1x/honne/crush.svg)](https://agentmods.dev/skills/jazz1x/honne/crush)
Your own site
<a href="https://agentmods.dev/skills/jazz1x/honne/crush"><img src="https://agentmods.dev/badge/skills/jazz1x/honne/crush.svg" alt="Measured on agentmods" height="20"></a>
Per session 44 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,106 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00044 $0.01106
Opus 5 $0.00022 $0.00553
Sonnet 5 $0.00009 $0.00221
Haiku 4.5 $0.00004 $0.00111

Measured 6d ago against content hash a4e6c5aa0d06, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

crush 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 6d 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.

skills/crush/SKILL.md · 136 lines

How it starts

The opening of the file, as written. The whole thing — 136 lines — stays where its author put it; the contents beside it link to each section on GitHub.

honne — Personas Debate (Live)

When invoked, execute Step 1 through Step 6 in order immediately. If skill arguments are provided, use them as the topic; otherwise ask for one.

Step 1: Get Topic

If skill_args are non-empty: TOPIC = skill_args joined with spaces

Else: Ask plain-text question: "What topic do you want the two personas to debate?"

Set TOPIC from the reply.

Step 2: Validate Personas

Count which persona files exist:

bash "${CLAUDE_PLUGIN_ROOT}/scripts/honne" persona check --persona .honne/personas/antipattern.md
bash "${CLAUDE_PLUGIN_ROOT}/scripts/honne" persona check --persona .honne/personas/signature.md
bash "${CLAUDE_PLUGIN_ROOT}/scripts/honne" persona check --persona .honne/personas/judge.md

Each returns exit 0 (exists) or exit 66 (missing). Branch on the combined result:

  • All three exit 0 → proceed to Step 3.
  • All three exit 66 → tell user: "No personas found. Run /honne:persona first to generate them." Stop.
  • Mixed → tell user: "Debate requires both antipattern and signature personas plus a judge. Your persona has only one axis represented. Collect more sessions and re-run /honne:whoami + /honne:persona to generate a full set." Stop.

Step 3: Load Personas

Read all three files into your mental context:

  • .honne/personas/antipattern.md → extract system prompt and name from # header
  • .honne/personas/signature.md → extract system prompt and name
  • .honne/personas/judge.md → extract system prompt

Extract the name from each by reading the first # Name line after the header.

Step 4: Round 1 — Antipattern Attacks

Apply .honne/personas/antipattern.md system prompt mentally.

Produce a 2-3 sentence attack on TOPIC from the antipattern perspective.

Label output: **[antipattern — {name}]** followed by the attack.

Step 5: Round 1 + Round 2 — Signature & Counter

Apply .honne/personas/signature.md system prompt.

Produce a 2-3 sentence rebuttal to antipattern's attack.

Read the full file on GitHub · 136 lines

Files

What ships with it

2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

Changes

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.

  1. 6d ago First seen · 136 lines · 44 tokens per session scan A a4e6c5aa0d06

Subscribe to this mod's changes

crush is a skill published in the GitHub repository jazz1x/honne (3 stars, last pushed 3mo ago), licensed MIT. It adds 44 tokens to every session and 1,106 once invoked, about $0.0002 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.

Related

Other skills, from other repositories

mix-compression

Reduce mix output noise (5-15% token savings) by installing rtk filters that compress mix test/credo/dialyzer/compile output before it reaches Claude. Use when long mix output floods context.

oliver-kriska/claude-elixir-phoenix · 48 tokens

phx-mix-compression

Reduce mix output noise (5-15% token savings) by installing rtk filters that compress mix test/credo/dialyzer/compile output before it reaches Claude. Use when long mix output floods context.

oliver-kriska/claude-elixir-phoenix · 51 tokens

quick

Implement small Phoenix changes without planning — add validations, update routes, fix components, create migrations. Use for single-file edits under 50 lines.

oliver-kriska/claude-elixir-phoenix · 31 tokens

phx-freeze

Apply an advisory edit scope in this session. Use for read-only or directory-scoped work; no enforcement hook is installed.

oliver-kriska/claude-elixir-phoenix · 30 tokens

i-have-adhd

Shape output for a reader with ADHD: lead with the next action, number multi-step work, restate state across turns, suppress tangents, give specific time estimates, make wins visible. Invoke with /i-have-adhd; stays on until "stop adhd mode".

ayghri/i-have-adhd · 62 tokens

service-desk

Runs the IT service desk — intake, triage, prioritization, escalation, knowledge, and the metrics that improve service rather than distort it. Use this to set up or fix a service desk, design ticket priority and escalation, reduce repeat contacts, structure a knowledge base, or work out why a desk hitting its targets…

cbrock84/headcount · 73 tokens