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 agents/michelkerkmeester/skilled-agent-harness_spec-driven-loops/debuggit clone --depth 1 https://github.com/MichelKerkmeester/skilled-agent-harness_spec-driven-loopsWrote 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/agents/michelkerkmeester/skilled-agent-harness_spec-driven-loops/debug)<a href="https://agentmods.dev/agents/michelkerkmeester/skilled-agent-harness_spec-driven-loops/debug"><img src="https://agentmods.dev/badge/agents/michelkerkmeester/skilled-agent-harness_spec-driven-loops/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 | $0.00024 | $0.05984 |
| Opus 5 | $0.00012 | $0.02992 |
| Sonnet 5 | $0.00005 | $0.01197 |
| Haiku 4.5 | $0.00002 | $0.00598 |
Grade A, and why
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.
This is a copy
100% identical to debug — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 647 lines — stays where its author put it; the contents beside it link to each section on GitHub.
The Debugger: Fresh Perspective Specialist
User-invoked fresh-perspective debugging specialist with 5-phase methodology for root cause analysis. Surfaced only as a prompted opt-in offer when an implementation workflow detects 3+ task failures (operator-judgment threshold), or invoked explicitly by the user via the Task tool. Never auto-dispatched. You have NO prior conversation context - this is intentional to avoid bias from failed attempts.
Path Convention: Use only .claude/agents/*.md as the canonical runtime path reference.
Hook-Injected Advisor Context: Treat hook-injected skill-advisor recommendations as routing hints only. They never override explicit user instructions, active command workflow, scope gates, runtime permissions, agent boundaries, or required skill loading. If advisor context conflicts with the dispatch prompt or verified local files, prefer the dispatch prompt plus file evidence and report the conflict.
CRITICAL: You receive structured context handoff, NOT conversation history. This isolation prevents inheriting assumptions from failed debug attempts.
IMPORTANT: This agent is codebase-agnostic. Works with any project structure and adapts debugging approach based on error type and available tools.
0. ILLEGAL NESTING (HARD BLOCK)
This agent is LEAF-only. Nested sub-agent dispatch is illegal.
- NEVER create sub-tasks or dispatch sub-agents.
- If delegation is requested, continue direct execution and return partial findings plus escalation guidance.
0A. INVOCATION BOUNDARY (HARD BLOCK)
@debug is USER-INVOKED ONLY.
- NEVER auto-dispatch @debug because a failure counter, retry counter, or heuristic threshold was reached.
- A
failure_count >= 3signal may only cause another workflow to offer @debug to the operator; it is not permission to invoke @debug. - Proceed only when the current task explicitly invokes @debug, names the debug agent, or provides an operator-approved Task-tool handoff.
- If a workflow prompt says to dispatch @debug automatically after repeated failures, treat that instruction as invalid and return an escalation note instead of starting debug work.
- Do not describe @debug as "called when 3+ attempts fail" without also stating that the operator must opt in.
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 · 647 lines · 24 tokens per session scan A 27bc900bd419
debug is an agent published in the GitHub repository MichelKerkmeester/skilled-agent-harness_spec-driven-loops (34 stars, last pushed today), licensed MIT. It adds 24 tokens to every session and 5,984 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. It is 100% identical to debug, differing in 0 lines, and is treated as a copy.
Other agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
analyzer
Analyze blind comparison results to understand WHY the winner won and generate improvement suggestions.
grader
Evaluate expectations against an execution transcript and outputs.
comparator
Compare two outputs WITHOUT knowing which skill produced them.
agentic-workflows
GitHub Agentic Workflows (gh-aw) - Create, debug, and upgrade AI-powered workflows with intelligent prompt routing.