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.
git clone --depth 1 https://github.com/dwarvesf/dwarves-kitWrote 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/dwarvesf/dwarves-kit/debug)<a href="https://agentmods.dev/commands/dwarvesf/dwarves-kit/debug"><img src="https://agentmods.dev/badge/commands/dwarvesf/dwarves-kit/debug/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/commands/dwarvesf/dwarves-kit/debug"><img src="https://agentmods.dev/badge/commands/dwarvesf/dwarves-kit/debug.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00102 | $0.02753 |
| Opus 5.5 | $0.00041 | $0.01101 |
| Sonnet 5.5 | $0.00020 | $0.00551 |
| Haiku 4.5 | $0.00010 | $0.00275 |
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 14d 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 — 141 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are debugging a defect, regression, or test failure. You are not here to guess. Random fixes waste time and create new bugs.
Scope and triggers
In a kit-adopted repo this replaces superpowers:systematic-debugging: a superset of it, adding the Phase 0 feedback loop, an on-disk ledger, and the guess-fix guard.
The Iron Law
NO FIX WITHOUT A RECORDED ROOT CAUSE.
You may not edit code to "fix" the bug until the ledger's ## Root cause is filled with the actual cause, traced to its source. A symptom patch is a failure, not a fix.
Before you start: open the ledger
Pick a short <slug> for this bug, sanitized to [a-z0-9-]+ (lowercase, digits, hyphens only; no spaces, no /, no .). Reject anything else; never let a slug contain a path separator.
Write .claude/debug/<slug>.md from this template, and append to it before each action, not after, so a context reset shows what you were about to do:
## Symptoms
(immutable: exactly what was reported, the error text, the failing test name)
## Root cause
## Evidence
(append: timestamp / what you checked / what you found / what it implies)
## Eliminated
(append: each hypothesis you falsified + the evidence that killed it)
## Fix attempts
(append: a count; the 3-fix wall reads this)
## Resolution
(the fix + the verification result)
Leave ## Root cause blank until you have actually found it. While it is blank, the anti-rationalization hook will block any guess-fix "done" claim and send you back here. That is intended.
Escaped-defect marker. If this defect traces to a SHIPPED spec whose test plan
should have caught it, record the indictment so lane telemetry can aggregate test-design
quality per spec: bash lib/gate/gate-ledger.sh action <slug> "escaped-from=<spec-slug>". Skip
when the defect predates the kit or traces to no spec; never guess the spec.
Phase 0: Build a feedback loop
This is most of the skill. A fast, deterministic, agent-runnable pass/fail signal for the bug is what every later phase consumes: reproduction, bisection, hypothesis tests, and the Phase-4 failing test all just re-run it. Spend disproportionate effort here; with the loop, the bug is mostly found.
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.
- 14d ago Changed · +12 lines f737d00a31b3
- 20d ago Changed · +10 tokens per session 8b153ffc547e
- 27d ago Changed · +4 lines · -39 tokens per session 4facf6c07b4c
- 1mo ago Changed · +105 tokens per session ad7f13ac388a
- 1mo ago Changed cb89c0d50587
- 1mo ago Changed d5de2fcb2377
- 1mo ago First seen · 125 lines · 26 tokens per session scan A ad0c29013378
debug is a command published in the GitHub repository dwarvesf/dwarves-kit (11 stars, last pushed yesterday), licensed MIT. It adds 102 tokens to every session and 2,753 once invoked, about $0.0004 per session on Opus 5.5. 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
cleanup
Systematically clean up code, remove dead code, and optimize project structure.
kiro-validate-gap
Command "kiro-validate-gap" from gotalab/cc-sdd, covering implementation gap validation, core task, execution steps, important constraints and tool guidance.
cloudflare-durable-objects:debug
Interactive Durable Objects debugging workflow. Diagnoses common DO errors, configuration issues, and runtime problems with step-by-step troubleshooting.
cloudflare-durable-objects:optimize
Interactive Durable Objects performance optimization assistant. Analyzes existing DO code and provides specific optimization recommendations with implementation guidance.
cloudflare-durable-objects:migrate
Interactive Durable Objects migration assistant. Guides through new class creation, renaming, deletion, and transfer migrations with validation.
cloudflare-workers:debug
Interactive debugging workflow for Cloudflare Workers. Diagnoses deployment errors, runtime issues, and performance problems with step-by-step fixes.