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 commands/kyungseo/ai-workflow-harness/work-debuggit clone --depth 1 https://github.com/kyungseo/ai-workflow-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/commands/kyungseo/ai-workflow-harness/work-debug)<a href="https://agentmods.dev/commands/kyungseo/ai-workflow-harness/work-debug"><img src="https://agentmods.dev/badge/commands/kyungseo/ai-workflow-harness/work-debug.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 | $0.00022 | $0.00253 |
| Opus 5 | $0.00011 | $0.00127 |
| Sonnet 5 | $0.00004 | $0.00051 |
| Haiku 4.5 | $0.00002 | $0.00025 |
Grade A, and why
work-debug 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
/work-debug
이 파일은 Claude Code slash command adapter다. 상세 절차의 SSoT는 skills/workflow/work-debug.md다.
Step 0
먼저 skills/workflow/work-debug.md를 로드하고 그 절차를 따른다.
Hard Stops
skills/workflow/work-debug.md가 없거나 읽을 수 없으면 파일 수정, 상태 변경, commit, PR 생성, merge 전에 중단하고 누락된 canonical 파일을 보고한 뒤 사용자 확인을 받는다.- 파일 수정, 상태 변경, commit, PR 생성, merge 전에 branch isolation, Approval Matrix, validation-before-commit/PR gate를 확인한다.
- 이 adapter에는 상세 checklist나 cascade matrix를 복제하지 않는다. 세부 판단은 canonical 절차를 따른다.
Entry Mechanism
Claude Code에서 /work-debug slash command로 호출된다. 전달된 인자는 canonical 절차의 $ARGUMENTS로 해석한다.
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 · 24 lines · 22 tokens per session scan A 204be74088dd
work-debug is a command published in the GitHub repository kyungseo/ai-workflow-harness (13 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 22 tokens to every session and 253 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 commands, from other repositories
OPSX: Apply
Implement tasks from an OpenSpec change (Experimental).
prepare-proposal
Apply .agents/tasks/proposal-preparation.md.
localize-project
Create persistent project memory for this repo (spec, ADRs, session log) on top of the global Understudy team.
enhance-prompt
Command "enhance-prompt" from VoDaiLocz/Enhance-Prompt, covering enhance prompt workflow, 1. intake and scoring (enhance-prompt/skill.md), 5. ambiguity check and 8. iteration (enhance-prompt/references/iteration-mode.md).
test-review
Act as a software quality engineer and python expert.
run_tests
Use the text the user typed after the command name as the request for this command.