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/sylorei/claude-godmode/debugnpx skills add SyloRei/claude-godmode --skill debuggit clone --depth 1 https://github.com/SyloRei/claude-godmodeWrote 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/skills/sylorei/claude-godmode/debug)<a href="https://agentmods.dev/skills/sylorei/claude-godmode/debug"><img src="https://agentmods.dev/badge/skills/sylorei/claude-godmode/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 | $0.00043 | $0.01450 |
| Opus 5 | $0.00022 | $0.00725 |
| Sonnet 5 | $0.00009 | $0.00290 |
| Haiku 4.5 | $0.00004 | $0.00145 |
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.
How it starts
The opening of the file, as written. The whole thing — 147 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Structured Debugging
Find and fix bugs systematically using evidence, never guessing.
Auto Mode
Auto Mode suppresses confirmation prompts and proceed-pauses — not the one clarifying question that can matter here: if the symptom isn't reproducible and the exact error/repro steps aren't given, state your reading of it for the user to override (debugging the wrong symptom wastes the whole effort). Don't ask "what's the repro?" from blank — lead with your best-inferred symptom and repro and invite correction: "I read the failure as X on step Y — correct me if not." This is the clarifying rendering of the recommendation-backed-question convention (godmode:recommend-convention) in rules/godmode-recommend.md. Once you can reproduce, proceed: fix immediately after the root cause is found, surface assumptions inline, and treat course-corrections as normal input. Don't loop on trivia.
The Job
Follow the 4-step protocol strictly. Do NOT skip steps.
Step 1: REPRODUCE
- Get the exact error message, stack trace, or unexpected behavior
- Find minimal reproduction steps
- Identify: when did it last work? What changed since?
- If the bug is intermittent, identify conditions that trigger it
- Establish baseline: what is the EXPECTED behavior?
Output: "The bug is [X]. Expected [Y]. Triggered by [Z]."
Step 2: HYPOTHESIZE
- Form 2-3 hypotheses based on evidence (not intuition)
- Rank by likelihood
- For each, state what evidence would confirm or deny it
If stuck gathering evidence: use @researcher agent to search the codebase for related patterns, recent changes, or similar bugs.
Output:
H1 (most likely): [hypothesis] — confirm by [check]
H2: [hypothesis] — confirm by [check]
H3: [hypothesis] — confirm by [check]
Step 3: ISOLATE
- Test hypotheses one at a time, most likely first
- Add targeted logging or read code at suspect locations
- Narrow to the exact line/condition causing the failure
- DO NOT fix multiple things at once
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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 · 147 lines · 43 tokens per session scan A d166e6824d20
debug is a skill published in the GitHub repository SyloRei/claude-godmode (3 stars, last pushed 2mo ago), licensed MIT. It adds 43 tokens to every session and 1,450 once invoked, about $0.0002 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 2026-08-31.
Other skills, from other repositories
erpaval
Workflow for autonomous software development with the Kiro CLI (open Agent Skills standard). Classifiers route scope, complexity, directory state, and spec readiness before committing to Explore / Research / Plan / Act / Validate, then close the loop with a Compound step that persists lessons to .erpaval/solutions/…
product-discovery
File-first orchestrator for product discovery and spec frameworks. Frames the problem with a Discovery Lead, Product Analyst, or System Architect role. Spawns parallel framework agents (Double Diamond, How Might We, Jobs to Be Done, user stories with INVEST, EARS for AI-coder specs, Gherkin), synthesizes into a PRD or…
review
Use when DISCOVER or REFRESH has surfaced a proposal staged at -context.proposed/, to inspect it and record sign-off before applying it.
status
Use when picking up a contextualizer after a gap, or checking reference freshness and pending review work at a glance — read-only, safe to run anytime.
agent-ux-patterns
Agent UX patterns and human-in-the-loop design: Twilio A2H protocol, Levels of Autonomy (L0-L5), inbox pattern, progressive trust, decision journal, gate reviews, autonomous work reports. Six-phase methodology from vague pain point to concrete data model via landscape research and multi-direction brainstorming. Use…
meta-prompt-optimizer
Audit and rewrite prompts against Claude Opus 4.7 instruction-following best practices. Produces a scored audit plus a rewritten prompt. Use when the user asks to audit, review, critique, rewrite, improve, optimize, tighten, score, fix, migrate, or draft a prompt — including system prompts, CLAUDE.md files, Claude…