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-compete)<a href="https://agentmods.dev/commands/seokan-jeong/team-shinchan/fierce-compete"><img src="https://agentmods.dev/badge/commands/seokan-jeong/team-shinchan/fierce-compete/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-compete"><img src="https://agentmods.dev/badge/commands/seokan-jeong/team-shinchan/fierce-compete.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 | $0.00015 | $0.00357 |
| Opus 5 | $0.00008 | $0.00179 |
| Sonnet 5 | $0.00003 | $0.00071 |
| Haiku 4.5 | $0.00002 | $0.00036 |
Grade A, and why
fierce-compete 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 Compete Command
A main-loop Workflow runs a competitive tournament: N builder agents independently solve the same task and each returns an apply-ready patch (read-only — no collisions, nothing to merge), an Action-Kamen judge scores them head-to-head, and the winner is selected deterministically by total score and applied. Use when the best of N implementations is worth the cost.
See skills/fierce-compete/SKILL.md for the full procedure.
Usage
/team-shinchan:fierce-compete [the implementation task; optionally "best of N"]
Examples
/team-shinchan:fierce-compete "implement the rate limiter — best of 3"
/team-shinchan:fierce-compete "two approaches to the CSV parser, pick the cleaner one"
/team-shinchan:fierce-compete "refactor auth middleware; compete 3 designs"
When to use this vs /team-shinchan:debate (competitive-code mode)
| Use fierce-compete | Use debate competitive-code (Midori) |
|---|---|
| High-value contested implementation; you want a schema-validated, deterministically-scored tournament | Quick best-of-N is acceptable |
| Patch-return (read-only builders, winner applied + tested in the main loop) | Worktree-based, Task-orchestrated |
| Explicit opt-in (runs a Workflow, token-heavy) | Auto/keyword-triggered, cheaper |
The winner is recorded to .shinchan-docs/debate-decisions.md (shared ledger) and applied with git apply, then verified.
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 · 34 lines · 15 tokens per session scan A 1c4ca71a015a
fierce-compete is a command published in the GitHub repository seokan-jeong/team-shinchan (8 stars, last pushed 1mo ago), licensed MIT. It adds 15 tokens to every session and 357 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.
chronicle
One-time codebase onboarding — interactively extracts your team's conventions, identifies reference files, and generates CLAUDE.md sections so Claude codes the way your team does. Run once per project.