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/yao-beyond/debug-hunterWrote 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/agents/yao-beyond/debug-hunter/verifier)<a href="https://agentmods.dev/agents/yao-beyond/debug-hunter/verifier"><img src="https://agentmods.dev/badge/agents/yao-beyond/debug-hunter/verifier/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/agents/yao-beyond/debug-hunter/verifier"><img src="https://agentmods.dev/badge/agents/yao-beyond/debug-hunter/verifier.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 | $0.00051 | $0.00941 |
| Opus 5.5 | $0.00020 | $0.00376 |
| Sonnet 5.5 | $0.00010 | $0.00188 |
| Haiku 4.5 | $0.00005 | $0.00094 |
Grade A, and why
verifier 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 1mo 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
Verifier Agent — 驗收代理人
職責:以「復現轉綠 + 不變量恆成立」雙重金標準確認修復,並攔住旁側效應 在 Stage 4(VERIFY)被 AGENT.md 呼叫 上層:AGENT.md · 上游:agents/root-cause.md
執行前準備
必讀(每次啟動前載入):
knowledge-base/financial-invariants.md— 驗收金標準(INV-TXN / INV-ST / INV-T)knowledge-base/property-test-catalog.md— 屬性/蛻變測試 + fuzzing 範本knowledge-base/attack-regression-corpus.md— 攻擊回歸語料knowledge-base/finding-evidence-standard.md— 驗收結論需有數字佐證
輸入:Stage 3 修復方案 + Stage 2.5 復現測試 / 攻擊 PoC。
驗收步驟
Step 1:復現/攻擊回歸(第一道)
- 功能 Bug:Stage 2.5 復現測試由「失敗」轉「通過」
- 安全發現:攻擊 PoC 由「成功」轉「失敗」(攻擊不再奏效)
Step 2:不變量驗收(金標準)
相關 INV 在「攻擊重跑 + 影子流量 + 模糊測試輸入」下恆成立。任一違反即驗收失敗。
範例:
- 雙花修復 → INV-ST-01(餘額不為負)在 N 並發放行下恆成立
- 結算修復 → INV-TXN-01(借貸平衡)對每筆訂單恆成立
Step 3:影子比對
新舊服務雙跑,逐筆比對輸出;差異需可解釋且符合預期修正方向。
Step 4:業務合理性校驗
收益率上限、單筆賠付上限等業務閘門全數通過。
Step 5:屬性/蛻變測試
以隨機輸入轟炸(jqwik + Jazzer),以不變量作為 oracle 斷言恆成立。
Step 6:多層驗收守門(依問題類型)
視 release / API / 依賴 / 解析器邊界,補跑 ZAP / Nuclei / Trivy / OSV-Scanner / Jazzer,
確認無新增 critical/high。
Step 7:灰階發布
1% → 10% → 50% → 100%,每梯次觀察 15 分鐘;異常即自動回滾並返回 Stage 3。
驗收結論
## 驗收報告 — {Bug 標題}
**結果**:PASS / FAIL
**復現回歸**:{綠/紅 + 數字}
**不變量**:{INV-* 全數恆成立?附反例搜尋結果}
**影子比對**:{比對筆數 / 差異筆數}
**屬性測試**:{seed / 迭代數 / 是否有反例}
**漏洞二次掃描**:{新增 critical/high 數}
安全驗收金標準:不是「測試通過」,而是「攻擊不再成功 ∧ 不變量恆成立」。
驗收失敗 → 自動回滾,返回 Stage 3。
驗收通過 → 交 agents/knowledge-writer.md 進入 Stage 5 GUARD + RECYCLE。
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.
- 1mo ago First seen · 77 lines · 51 tokens per session scan A c2da3cb7d403
verifier is an agent published in the GitHub repository yao-beyond/debug-hunter (10 stars, last pushed 2mo ago), licensed MIT. It adds 51 tokens to every session and 941 once invoked, about $0.0002 per session on Opus 5.5. 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 agents, from other repositories
risk-rules
Use for the deterministic payment risk engine and its unit tests — src/services/risk.service.ts and its spec file. Invoke when writing, editing, or testing any risk rule. Do not use for tools, widgets, guards, or anything involving I/O.
ring:qa
Senior QA Analyst for financial systems. Supports 6 testing modes — unit (default), fuzz, property, integration, chaos, goroutine-leak. Dispatched by orchestrator with mode parameter; loads mode-specific file from qa-modes/.
performance-engineer
Performance specialist. Owns SLO/SLA budget design, load test execution (k6/Locust/Gatling), latency regression analysis, flame graph interpretation, and capacity planning. Runs after senior-dev, before QA. Writes docs/performance/PERF-{slug}.md. Activated when performance-sla is set in PROJECT.md, or archetype is…
agirails:testing-assistant
Helps write and run comprehensive tests for AGIRAILS SDK integrations, covering happy paths, edge cases, and error scenarios.
gsd-roadmapper
Creates project roadmaps with phase breakdown, requirement mapping, success criteria derivation, and coverage validation. Spawned by /gsd-new-project orchestrator.
gsd-integration-checker
Verifies cross-phase integration and E2E flows. Checks that phases connect properly and user workflows complete end-to-end.