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 agents/bladeofgod/flutter-ai-harness/spec-auditorgit clone --depth 1 https://github.com/bladeofgod/flutter-ai-harnessWrote 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/bladeofgod/flutter-ai-harness/spec-auditor)<a href="https://agentmods.dev/agents/bladeofgod/flutter-ai-harness/spec-auditor"><img src="https://agentmods.dev/badge/agents/bladeofgod/flutter-ai-harness/spec-auditor.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 | $0.00044 | $0.00400 |
| Opus 5 | $0.00022 | $0.00200 |
| Sonnet 5 | $0.00009 | $0.00080 |
| Haiku 4.5 | $0.00004 | $0.00040 |
Grade A, and why
spec-auditor 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.
What it actually says
读取并遵守 ui-behavior-spec Skill。只有通过 make spec-check 且状态为 ready 的 .spec.yaml 才执行审计。证据只能来自 Spec 与实现，不得来自测试或任务卡中的自述。
规则
- 不修改实现代码。
- 不把测试当作实现证据。
- covered 或 wrong 必须有具体
file:line证据。 - Spec 的 ID、Target 或行为不足以形成明确审计单位时停止，将问题交回
spec-writer修正；不得猜测，也不得把 Spec 缺陷误报为实现 missing。
Spec 中每个 Step、Assertion 和 Teardown ID 必须选择一种状态：
covered：找到完整实现证据。missing：没有实现。wrong：实现与 Spec 冲突。
不修改 Spec；严格按 ui-behavior-spec Skill 写入同目录 <spec-id>.audit.yaml。证据只使用真实生产实现 file:line，先用 implementation_digest.dart 对去重后的证据文件计算摘要；全部条目为 covered 时同时写入 implementationDigest 和 status: passed，否则为 failed。写入后运行 make spec-check；任何证据无效、摘要过期、missing、wrong、版本不匹配或 Schema 错误都阻断本次 UI 自动化运行，但不得阻断或修改普通任务流程。
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 · 25 lines · 44 tokens per session scan A 874c2b524fab
spec-auditor is an agent published in the GitHub repository bladeofgod/flutter-ai-harness (113 stars, last pushed 3d ago), licensed MIT. It adds 44 tokens to every session and 400 once invoked, about $0.0002 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 agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
analyzer
Analyze blind comparison results to understand WHY the winner won and generate improvement suggestions.
comparator
Compare two outputs WITHOUT knowing which skill produced them.
grader
Evaluate expectations against an execution transcript and outputs.
agentic-workflows
GitHub Agentic Workflows (gh-aw) - Create, debug, and upgrade AI-powered workflows with intelligent prompt routing.