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-review)<a href="https://agentmods.dev/commands/seokan-jeong/team-shinchan/fierce-review"><img src="https://agentmods.dev/badge/commands/seokan-jeong/team-shinchan/fierce-review/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-review"><img src="https://agentmods.dev/badge/commands/seokan-jeong/team-shinchan/fierce-review.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 | $0.00016 | $0.00375 |
| Opus 5 | $0.00008 | $0.00187 |
| Sonnet 5 | $0.00003 | $0.00075 |
| Haiku 4.5 | $0.00002 | $0.00038 |
Grade A, and why
fierce-review 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 Review Command
A main-loop Workflow runs a non-skippable, multi-dimension review: dimension agents (correctness, security, performance, quality, tests, principles) fan out independently, every finding is challenged by a skeptic, a completeness critic hunts the files and rules nobody examined, and an Action-Kamen judge scores against the shared rubric. Use when a single-pass review risks stopping at "good enough" — pre-release diffs, security/payment/auth boundaries, data-loss paths.
See skills/fierce-review/SKILL.md for the full procedure.
Usage
/team-shinchan:fierce-review [paths, a feature description, or nothing for the current diff]
Examples
/team-shinchan:fierce-review # review the working-tree / branch diff
/team-shinchan:fierce-review "src/auth/" # review a path
/team-shinchan:fierce-review "the new payment webhook handler"
When to use this vs /team-shinchan:review
| Use fierce-review | Use review (Action Kamen) |
|---|---|
| High-stakes scope: pre-release, security/payment/auth boundary, data-loss path | Routine change, single file, quick check |
| You want guaranteed per-dimension coverage + adversarial per-finding verification + a completeness critic | A single thorough pass is acceptable |
| Explicit opt-in (runs a Workflow, higher token cost) | Auto-triggered or delegated, cheap |
An APPROVED fierce-review writes .shinchan-docs/reviews/REVIEW-{NNN}.json, which counts as code-review evidence for the verification-before-completion gate.
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 · 16 tokens per session scan A 528ed6c6f37d
fierce-review is a command published in the GitHub repository seokan-jeong/team-shinchan (8 stars, last pushed 1mo ago), licensed MIT. It adds 16 tokens to every session and 375 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-audit
Scope-and-rank phase only — a ranked findings list, no delegation.
audit
Audit an existing codebase. Detects stack, finds gaps, creates tasks, generates PROJECT.md.
release
Release manager for frontend and mobile. Writes App Store notes, user-facing changelog, flags stale docs and landing copy. Actions: notes | changelog | docs | sync.
discover
Run a full product discovery cycle — from outcome definition through opportunity mapping, prioritisation, and experiment design. Use when the team isn't sure what to build next, or before writing a PRD for a complex feature space.
migrate
Migrate existing PROJECT.md to the latest greatcto schema — appends missing fields without touching existing values.
exception
Signed gate-exception registry — replace ad-hoc --admin / --no-verify bypasses with an auditable, signed, expiring record (who · why · gate · scope · expiry). Create / list / check exceptions.