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 jazz1x/honne/plugin install honneWrote 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/jazz1x/honne/crush)<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>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 | $0.00044 | $0.01106 |
| Opus 5 | $0.00022 | $0.00553 |
| Sonnet 5 | $0.00009 | $0.00221 |
| Haiku 4.5 | $0.00004 | $0.00111 |
Grade A, and why
crush scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 6d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 136 lines — stays where its author put it; the contents beside it link to each section on GitHub.
honne — Personas Debate (Live)
When invoked, execute Step 1 through Step 6 in order immediately. If skill arguments are provided, use them as the topic; otherwise ask for one.
Step 1: Get Topic
If skill_args are non-empty: TOPIC = skill_args joined with spaces
Else: Ask plain-text question: "What topic do you want the two personas to debate?"
Set TOPIC from the reply.
Step 2: Validate Personas
Count which persona files exist:
bash "${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:personafirst 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:personato generate a full set." Stop.
Step 3: Load Personas
Read all three files into your mental context:
.honne/personas/antipattern.md→ extract system prompt andnamefrom#header.honne/personas/signature.md→ extract system prompt andname.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.
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.
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.
- 6d ago First seen · 136 lines · 44 tokens per session scan A a4e6c5aa0d06
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.
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.
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.
quick
Implement small Phoenix changes without planning — add validations, update routes, fix components, create migrations. Use for single-file edits under 50 lines.
phx-freeze
Apply an advisory edit scope in this session. Use for read-only or directory-scoped work; no enforcement hook is installed.
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".
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…