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/seokan-jeong/team-shinchanWrote 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/seokan-jeong/team-shinchan/fierce-option-panel)<a href="https://agentmods.dev/commands/seokan-jeong/team-shinchan/fierce-option-panel"><img src="https://agentmods.dev/badge/commands/seokan-jeong/team-shinchan/fierce-option-panel/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/seokan-jeong/team-shinchan/fierce-option-panel"><img src="https://agentmods.dev/badge/commands/seokan-jeong/team-shinchan/fierce-option-panel.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 | $0.00025 | $0.00508 |
| Opus 5 | $0.00013 | $0.00254 |
| Sonnet 5 | $0.00005 | $0.00102 |
| Haiku 4.5 | $0.00003 | $0.00051 |
Grade A, and why
fierce-option-panel 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 12d 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
Fierce Option Panel Command
A main-loop Workflow that hardens interview recommendation options: N diverse generators produce structure-free candidate options, a SelfCheckGPT majority-vote consensus (≥ ceil(N/2+1) backing) filters hallucinations, a SteerConf cautious-confidence judge scores the survivors, and a deterministic top-K is returned. Falls back to the basic B-path on any failure (graceful degradation).
This is the single fierce-* skill that is ON by default — an explicit, intentional
exception to the fierce-* opt-in convention, made under quality-over-cost. Opt out via
.shinchan-config.yaml → interview.fierce_option_panel: false.
See skills/fierce-option-panel/SKILL.md for the full procedure and
docs/fierce-option-panel.md for the design rationale.
Usage
/team-shinchan:fierce-option-panel [the interview question to design options for]
Examples
/team-shinchan:fierce-option-panel "what is the primary failure mode we are solving?"
/team-shinchan:fierce-option-panel "which scope boundary should phase 1 cover?"
Config
| Key | Default | Purpose |
|---|---|---|
interview.fierce_option_panel |
true |
Master on/off (default-on exception). |
interview.fierce_panel_k_max |
6 |
Max options into the top-K / DINCO (O(K²) bound). |
interview.fierce_panel_generators |
3 |
Diverse generators; majority threshold = ceil(N/2+1). |
interview.fierce_panel_token_budget_per_turn |
60000 |
Per-turn DoS cap; over budget → basic path. |
Limitations
ECE/AUROC calibration transfers from factual-QA literature via a proxy (user's eventual
option selection = ground truth) and is unvalidated for design options. Gating bars
(ECE < 0.10, AUROC >= 0.70, Distinct-2 >= 0.55, self-BLEU <= 0.40) are pragmatic
targets, not universal guarantees.
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.
- 12d ago First seen · 48 lines · 25 tokens per session scan A 2c87f73a0ad8
fierce-option-panel is a command published in the GitHub repository seokan-jeong/team-shinchan (8 stars, last pushed 1mo ago), licensed MIT. It adds 25 tokens to every session and 508 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 2026-08-31.
Other commands, from other repositories
gbu-retro
Post-session retrospective — harvest this session's lessons into durable doctrine.
gbu
Run the tiered multi-agent orchestration loop on a large task.
gbu-audit
Scope-and-rank phase only — a ranked findings list, no delegation.
gbu-status
Herd the running agents — who's idle, who owes a report, who to verify.
typescript-fix
Run TypeScript type-checking and resolve all errors using the typescript-expert skill.
build-brand-kit
Produce a complete Brand Kit — positioning, voice rules, color palette, typography stack, visual vocabulary, example applications, don'ts — derived from the person's Genius Profile and Vision Architecture. Composes with frankx-brand, brand-voice, brand-guidelines, theme-factory, infogenius. Integrates with…