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.
npx agentmods add commands/fujigo-software/f5-framework-claude/f5-gategit clone --depth 1 https://github.com/Fujigo-Software/f5-framework-claudeWrote 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/fujigo-software/f5-framework-claude/f5-gate)<a href="https://agentmods.dev/commands/fujigo-software/f5-framework-claude/f5-gate"><img src="https://agentmods.dev/badge/commands/fujigo-software/f5-framework-claude/f5-gate.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 | $0.00006 | $0.11755 |
| Opus 5 | $0.00003 | $0.05878 |
| Sonnet 5 | $0.00001 | $0.02351 |
| Haiku 4.5 | $0.00001 | $0.01175 |
Grade A, and why
f5-gate 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 5d 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 — 1,651 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/f5-gate - Quality Gate Management Command
Manage and enforce quality gates (D1-D4, G2-G4) for Japanese outsource workflow with automated validation and evidence collection.
ARGUMENTS
The user's request is: $ARGUMENTS
STEP 0: RESOLVE LANGUAGE
resolve_language() {
if [ -f ".f5/config.json" ]; then
PROJECT_LANG=$(jq -r '.language // empty' .f5/config.json 2>/dev/null)
if [ -n "$PROJECT_LANG" ] && [ "$PROJECT_LANG" != "null" ]; then echo "$PROJECT_LANG"; return; fi
fi
if [ -f ~/.f5/preferences.yaml ]; then
GLOBAL_LANG=$(grep '^language:' ~/.f5/preferences.yaml 2>/dev/null | sed 's/language:[[:space:]]*"\{0,1\}\([^"]*\)"\{0,1\}/\1/')
if [ -n "$GLOBAL_LANG" ]; then echo "$GLOBAL_LANG"; return; fi
fi
echo "en"
}
ACTIVE_LANG=$(resolve_language)
i18n Labels
| Key | en | vi | ja |
|---|---|---|---|
| check_title | Gate Check | Kiểm tra Gate | ゲートチェック |
| status_title | Gate Status | Trạng thái Gate | ゲートステータス |
| prerequisites | Prerequisites | Điều kiện tiên quyết | 前提条件 |
| checklist | Checklist Verification | Xác minh danh sách | チェックリスト検証 |
| automated_checks | Automated Checks | Kiểm tra tự động | 自動チェック |
| evidence | Evidence Collected | Bằng chứng đã thu thập | 収集したエビデンス |
| passed | PASSED | ĐẠT | 合格 |
| failed | FAILED | KHÔNG ĐẠT | 不合格 |
| with_warnings | PASSED WITH WARNINGS | ĐẠT VỚI CẢNH BÁO | 警告付き合格 |
Gate Names by Language
| Gate | en | vi | ja |
|---|---|---|---|
| D1 | Research Complete | Nghiên cứu hoàn thành | 調査完了 |
| D2 | SRS Approved | SRS được duyệt | SRS承認済 |
| D3 | Basic Design Approved | Thiết kế cơ bản được duyệt | 基本設計承認済 |
| D4 | Detail Design Approved | Thiết kế chi tiết được duyệt | 詳細設計承認済 |
| G2 | Implementation Ready | Triển khai hoàn thành | 実装完了 |
| G2.5 | Verification Complete | Xác minh hoàn thành | 検証完了 |
| G3 | Testing Complete | Kiểm thử hoàn thành | テスト完了 |
| G4 | Deployment Ready | Sẵn sàng triển khai | デプロイ準備完了 |
STEP 1: PARSE ACTION
| Action | Description |
|---|---|
check <gate> |
Run comprehensive automated checks for a gate |
start <gate> |
Start gate review process |
complete <gate> |
Mark gate as complete |
status |
Show all gates status |
report <gate> |
Generate comprehensive gate report for stakeholders |
enforce <gate> |
Enforce gate requirements - block progress if not met |
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.
- 5d ago First seen · 1,651 lines · 6 tokens per session scan A d93c10d11750
f5-gate is a command published in the GitHub repository Fujigo-Software/f5-framework-claude (24 stars, last pushed 7mo ago), licensed MIT. It adds 6 tokens to every session and 11,755 once invoked, about $0.0000 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 2026-08-30.
Other commands, from other repositories
build
Guided feature development with approval gates at each phase.
plan
Project spec (no args) or feature FRD (with args).
ship
Autonomous spec-to-PR pipeline with zero approval gates.
debug
Structured debugging with parallel investigation agents.
init
Analyze codebase and generate CLAUDE.md with project conventions.
release
Generate changelog, bump version, and create git tag.