How do I install the Debug skill?

Run npx skillmds@latest add markusstrasser/debug in your terminal (requires Node.js), paste this page's agent-chat prompt into Claude, Cursor, or any MCP-connected agent, or download the SKILL.md file and copy it into your agent's skills directory.

Is Debug safe to use?

This skill has not completed SkillMD's automated safety review yet. Capability flags: docs only. SkillMD never runs a skill's scripts for you; review the SKILL.md before installing.

Which AI agents work with Debug?

This skill is tagged as working with Claude Code, Claude.ai, OpenAI Codex. SKILL.md is an open format, so most agents that read a skills directory can load it too.

Is Debug free to use?

Yes. Installing skills from SkillMD is free, and the skill stays under its author's original license.

markusstrasser (@markusstrasser) published this skill. Their other Agent Skills are listed on their SkillMD profile.

Debug by markusstrasser — Agent Skill

Name: Debug
Rating: 4.5 (4 reviews)
Author: markusstrasser

File contents

Debug scout pipeline

Formalizes the genomics bug-hunt pattern: scouts write, orchestrator model judges, operator steers at ship boundaries. (The file-bus pipeline that once wrapped this — /orchestrate, consolidation, commit-slice — was retired 2026-09-02; the parent session triages docs/audit/ inline.)

Roles

Role	Who
Operator	Human — goals, approval, irreversible apply
Orchestrator model	Frontier parent (Opus, etc.) — dispatch, triage, propose fixes
Scout	Composer ask-mode — audit files only

Flow

J="just -f ~/Projects/agent-infra/justfile"
$J adversarial-debug-scout ~/Projects/genomics recent --prompt "cardinal rule + RESEARCH_ONLY"
$J debug-until-dry ~/Projects/genomics &     # or: wave loop until no new confirmed bugs
# orchestrator model reads docs/audit/*-debug-handoff.md — validates SUSPECT, fixes confirmed
# findings inline, notes rejections in the memo; operator approves tier-1/2 apply.

arc-agi multi-round audits: before round 2+ scouts, run just -C ~/Projects/arc-agi audit-ledger skip-fixed-md and prepend the markdown block to each scout prompt. Ledger: loop/audit/ledger.jsonl. After fixes: just -C ~/Projects/arc-agi audit-ledger seed-from-git.

Rules

Scouts run cursor ask-mode only (agent-infra/scripts/debug_scout.py) — no edits, no commit.
Output → {repo}/docs/audit/YYYY-MM-DD-debug-{run}-{slug}.md
Orchestrator model reads the handoffs and triages inline — scouts do not implement fixes.
Operator approves tier-1/2 apply and taste calls.
Check scientific/conceptual claims, not just code bugs (see agent-infra/scripts/debug_scout_prompt.md).
Scouts verify when cheap: git log, targeted pytest; skip costly/live/mutating → SUSPECT + hand off.

vs other skills

Skill	Role
`/debug` (this)	Adversarial scout fan-out only
`/code-review`	Structural line-format scout on source batches
`/critique`	Cross-model design/plan review

Critique before large changes: /critique model on the handoff or plan packet.

---name: debugdescription: Use when: parallel adversarial bug-hunt fan-out or pre-commit audit; scouts write files, orchestrator model triages. NOT a code-review scout (/code-review) or plan critique (/critique).---# Debug scout pipelineFormalizes the genomics bug-hunt pattern: **scouts write, orchestrator model judges, operator steers at ship boundaries.** (The file-bus pipeline that once wrapped this — `/orchestrate`, consolidation, commit-slice — was retired 2026-09-02; the parent session triages `docs/audit/` inline.)## Roles| Role | Who ||------|-----|| **Operator** | Human — goals, approval, irreversible apply || **Orchestrator model** | Frontier parent (Opus, etc.) — dispatch, triage, propose fixes || **Scout** | Composer ask-mode — audit files only |## Flow```bashJ="just -f ~/Projects/agent-infra/justfile"$J adversarial-debug-scout ~/Projects/genomics recent --prompt "cardinal rule + RESEARCH_ONLY"$J debug-until-dry ~/Projects/genomics & # or: wave loop until no new confirmed bugs# orchestrator model reads docs/audit/*-debug-handoff.md — validates SUSPECT, fixes confirmed# findings inline, notes rejections in the memo; operator approves tier-1/2 apply.```**arc-agi multi-round audits:** before round 2+ scouts, run `just -C ~/Projects/arc-agi audit-ledger skip-fixed-md` and prepend the markdown block to each scout prompt. Ledger: `loop/audit/ledger.jsonl`. After fixes: `just -C ~/Projects/arc-agi audit-ledger seed-from-git`.## Rules1. Scouts run **cursor ask-mode only** (`agent-infra/scripts/debug_scout.py`) — no edits, no commit.2. Output → `{repo}/docs/audit/YYYY-MM-DD-debug-{run}-{slug}.md`3. **Orchestrator model** reads the handoffs and triages inline — scouts do not implement fixes.5. **Operator** approves tier-1/2 apply and taste calls.6. Check **scientific/conceptual** claims, not just code bugs (see `agent-infra/scripts/debug_scout_prompt.md`).7. Scouts **verify when cheap**: git log, targeted pytest; skip costly/live/mutating → SUSPECT + hand off.## vs other skills| Skill | Role ||-------|------|| `/debug` (this) | Adversarial scout fan-out only || `/code-review` | Structural line-format scout on source batches || `/critique` | Cross-model design/plan review |Critique before large changes: `/critique model` on the handoff or plan packet.

Frequently asked questions

Debug