Debug

What it does

When your agent uses it

• Silent failures
• Troubleshooting

Example prompts

• “/debug”

Requirements

• Pre-approved tools (allowed-tools): Read, Grep, Glob, Edit, Write, Bash, Skill, AskUserQuestion

Workflow steps

6 steps, taken from the step headings in SKILL.md.

1. 1Intake + Reproduce
2. 2Classify
3. 3Probe Loop
4. 4Root Cause Confirmation
5. 5Fix + Verify
6. 6Debug Report

What it can do on your machine

Read from SKILL.md and the folder at commit a4d4bc1. It shows what the files ask for, not the result of running them.

• Tool permissions

  Pre-approves these tools, so the agent can use them without asking each time:

  • Read
  • Grep
  • Glob
  • Edit
  • Write
  • Bash
  • Skill
  • AskUserQuestion

  From allowed-tools in the SKILL.md frontmatter.

• Runs code

  Shell commands in SKILL.md call:

  • git
  • curl

  From the folder's file list and the shell code blocks in SKILL.md.

• Network

  No URLs in SKILL.md. Its commands use git and curl, which can reach the network depending on how they are called.

  From URLs in SKILL.md, links to its own repository left out.

• Credentials

  Names no API keys, tokens, secrets or passwords.

  From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Debug loads about 2k tokens when it runs, and up to ~3.8k if it reads all its reference files. Until then it costs about 80 tokens; SKILL.md has 599 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it

~80

When it runs · the whole SKILL.md, loaded when a task matches

~2k

With references · SKILL.md plus every file in references/, read only if the agent opens them

~3.8k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

• NotePre-approves every shell command (allowed-tools: Bash)SKILL.md

  allowed-tools: Read, Grep, Glob, Edit, Write, Bash, Skill, AskUserQuestion

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from sd0xdev/sd0x-harness at commit a4d4bc1, republished under its MIT licence (© sd0xdev). 599 words, ~1,979 tokens.

name

debug

description

Interactive debugging workflow with hypothesis-driven probe loop. Use when: unknown bugs, script errors, silent failures, troubleshooting. Not for: known bugs (use bug-fix), GitHub issue analysis (use issue-analyze), code understanding (use code-explore). Output: debug report with probe journal + root cause + fix.

allowed-tools

Read, Grep, Glob, Edit, Write, Bash, Skill, AskUserQuestion

❌ git add | git commit | git push — per @rules/git-workflow.md

Phase 0    Phase 1     Phase 2          Phase 3           Phase 4        Phase 5
Intake  →  Classify →  Probe Loop   →   Root Cause    →   Fix +       →  Report
+ Repro    (Taxonomy)  (max 6)          Confirmation      Verify
  │          │           │                 │                │              │
  ▼          ▼           ▼                 ▼                ▼              ▼
Execute    refs/       Bash            /seek-verdict    Edit+test     --export
reproduce  failure-    /codex-         /code-investigate /bug-fix      (optional)
           taxonomy    brainstorm      (optional)

1. 定義假設 H
2. 設計探測命令 C
3. 預測「若 H 成立 → 期望 O」
4. 執行 C → 觀察實際結果
5. 更新假設集合
6. 選下一個最具鑑別力的探測

Fix → Review → Issues found → Fix again → ... → ✅ Pass → Next step

## Debug Report: <title>
- **Type**: <classification>
- **Root Cause**: <what + why>
- **Fix**: <change description>
- **Verdict**: <seek-verdict result>
- **Probe Rounds**: <N>

Input: /debug bash scripts/deploy.sh 回傳 exit code 1
Phase 0: 執行 bash scripts/deploy.sh → 確認失敗
Phase 1: Script Bug
Phase 2: R1: bash -x trace → 發現 line 42 curl 失敗
         R2: 直接 curl endpoint → 404
         R3: 檢查 URL → 路徑缺少 /api prefix → Stop
Phase 3: /seek-verdict confirm → ACTIONABLE
Phase 4: Edit line 42 + regression test
Phase 5: Debug Report

Input: /debug API 回傳空陣列但資料庫有資料
Phase 0: curl API endpoint → 確認回傳 []
Phase 1: Silent Failure（表面正常但結果錯誤）
Phase 2: R1: 檢查 query filter → 發現 status 欄位名稱不符
         R2: 直接 DB query → 有資料 → Stop
Phase 3: /seek-verdict confirm → ACTIONABLE
Phase 4: 修正 field name + unit test
Phase 5: Debug Report

Input: /debug ks-status.sh 回傳 ready:false 但 deployment 已就緒
Phase 0: 執行 bash ks-status.sh → ready:false, 缺少 replicas 欄位
Phase 1: Silent Failure（404 被 fallback 吞掉）
Phase 2: R1: 直接 curl API → invalid JSON → R2: 原始回應 → 404
         R3: 改用 apps/v1 路徑 → 200 + 完整資料 → Stop
Phase 3: /seek-verdict confirm → ACTIONABLE
Phase 4: api/v1 → apps/v1（1 word fix）+ test
Phase 5: Debug Report

© sd0xdev, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 3 other files (references) in skills/debug of sd0xdev/sd0x-harness.

• SKILL.md
• references/failure-taxonomy.md
• references/probe-protocol.md
• references/report-template.md

Open the folder on GitHubat commit a4d4bc1