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/systematic-debuggingnpx skills add 0xranx/agentbrief --skill systematic-debugginggit clone --depth 1 https://github.com/0xranx/agentbriefWhat 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 | $0.00014 | $0.00400 |
| Opus 5 | $0.00007 | $0.00200 |
| Sonnet 5 | $0.00003 | $0.00080 |
| Haiku 4.5 | $0.00001 | $0.00040 |
Grade A, and why
systematic-debugging 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 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.
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
Methodology from obra/superpowers (MIT)
Systematic Debugging
Core rule: find the root cause before writing any fix.
Phase 1 -- Root Cause Investigation
- Reproduce the bug with the simplest possible input.
- Read the actual error message / stack trace. Do NOT guess.
- Trace the data flow backwards from the failure site to the origin.
- Identify the earliest point where observed behavior diverges from expected.
Phase 2 -- Pattern Analysis
- Search the codebase for similar patterns (same API, same data path).
- Check recent changes (git log, git blame) near the failure site.
- Look for related open issues or past fixes for the same component.
- Note if the bug is deterministic or intermittent -- intermittent implies concurrency, timing, or external state.
Phase 3 -- Hypothesis Testing
- Form exactly one hypothesis at a time.
- Design a minimal experiment that can confirm or refute it.
- Run the experiment. Read the output fully.
- If refuted, discard the hypothesis and return to Phase 1 or 2. Do NOT patch and hope.
Phase 4 -- Implementation
- Write a failing test that demonstrates the root cause.
- Apply the smallest change that makes the test pass.
- Run the full test suite to check for regressions.
- Verify the original reproduction case is resolved.
- Document why the bug happened, not just what you changed.
Anti-patterns to Avoid
- Shotgun debugging: making multiple changes at once.
- Fixing symptoms instead of root causes.
- Claiming "fixed" without re-running the reproduction case.
- Skipping the hypothesis step and jumping straight to code 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 · 47 lines · 14 tokens per session scan A 94987a19271a
systematic-debugging is a skill published in the GitHub repository 0xranx/agentbrief (45 stars, last pushed 5mo ago), licensed MIT. It adds 14 tokens to every session and 400 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 2026-08-30.
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。.