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 skills/0xranx/agentbrief/verificationnpx skills add 0xranx/agentbrief --skill verificationgit clone --depth 1 https://github.com/0xranx/agentbriefWrote 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/skills/0xranx/agentbrief/verification)<a href="https://agentmods.dev/skills/0xranx/agentbrief/verification"><img src="https://agentmods.dev/badge/skills/0xranx/agentbrief/verification.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 | $0.00013 | $0.00383 |
| Opus 5 | $0.00006 | $0.00192 |
| Sonnet 5 | $0.00003 | $0.00077 |
| Haiku 4.5 | $0.00001 | $0.00038 |
Grade A, and why
verification scanned grade A with 1 finding 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 3d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
1. **Run** the relevant command (test, build, lint, curl, etc.). What it actually says
Methodology from obra/superpowers (MIT)
Verification
Iron law: no claims without fresh evidence.
The Verification Gate
Before you say "done", "works", "fixed", or "verified", you MUST:
- Run the relevant command (test, build, lint, curl, etc.).
- Read the full output -- not just the exit code.
- Confirm the output matches the expected result.
- Only then claim completion.
If you cannot run a verification command, say so explicitly. Never assume.
What Counts as Verification
| Claim | Minimum Evidence |
|---|---|
| "Tests pass" | Paste or reference the test runner output showing green. |
| "Build succeeds" | Show the build command output with zero errors. |
| "Bug is fixed" | Show the reproduction case now producing correct output. |
| "File updated" | Read the file back and confirm the expected content. |
| "Service is running" | Hit the health endpoint and show the response. |
Workflow
- Finish your change.
- Decide which claims you are about to make.
- For each claim, run the matching verification step.
- If any step fails, fix and re-verify. Do NOT skip ahead.
- Report results with evidence (command + output).
Anti-patterns to Avoid
- Saying "should work" without running anything.
- Running a command but not reading its output.
- Verifying one thing and claiming another.
- Treating a clean exit code as proof when the output contains warnings or partial failures.
- Re-using stale evidence from a previous run after making further changes.
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.
- 3d ago First seen · 48 lines · 13 tokens per session scan A abe8e5b672e6
verification is a skill published in the GitHub repository 0xranx/agentbrief (45 stars, last pushed 5mo ago), licensed MIT. It adds 13 tokens to every session and 383 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
pptx
从论文、大纲或结构化文本生成 PowerPoint (.pptx) 演示文稿。Use when 用户需要把一篇论文/文章/大纲做成幻灯片、slides、演示文稿、PPT、deck。Don't use when 只需纯文本总结、生成 Word/PDF、或修改已有 pptx 的单个像素级样式。.
ai-style
当任务是用中文撰写或改写面向读者的文案（产品发布稿、公众号文章、邮件、README 等）， 或用户反馈文字「AI 味太重」「不像人写的」时，加载本 Skill。.
curly-quote-sft
Skill "curly-quote-sft" from bojieli/ai-agent-book, covering 中文技术文档符号与引用规范, 何时加载, 符号定义, 决策优先级 and 正反例约束.
triage
你是当前任务的分诊协调者。先识别用户的全部目标、顺序依赖和验收条件，再按 “事实检索 → 计算/执行 → 写作”顺序逐步请求切换到需要的专业能力。不要替专业 能力完成它的工作，也不要在信息缺失时臆造结果。.
writing
将共享历史中的已验证事实和计算结果整理成符合受众、格式与长度约束的成稿。.
research
用真实检索工具查找可追溯的事实、数据和来源。.