Route a concrete reproducible failure through the installed debugging skills; not for open-ended exploration.
Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.
What the file says
# Debugging Router
A concrete failure — a broken test, a reproducible bug, a failing deploy. This skill owns no debugging opinion of its own; it names which methodology applies and in what order, because the failure mode is applying one of them and skipping the rest.
Not for open-ended exploration ("this feels wrong"). That is `$compound-engineering:ce-ideate` territory.
## Sequence
**1. `$superpowers:systematic-debugging` — start here when installed.**
Investigation discipline comes before any fix, including when the cause seems obvious. When Superpowers is unavailable, use the host's equivalent systematic-debugging workflow; do not skip the investigation step.
**2. `$compound-engineering:ce-debug` — add when installed.**
Its hypothesis-and-prediction gate goes *before* any code change: state what you believe is wrong and what you expect to see if you are right, then check. Without Compound Engineering, apply that same hypothesis-and-prediction gate directly. A fix applied without a failed prediction is a guess that happened to be typed confidently.
**3. `$zforge:async-reasoning` — add when the failure involves timing.**
…
The line at the top of this page pins the label git:20260825.e6f8d51, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.
A 17 of 17 checks passed. Fixed automatic checks with no AI involved, so the same checks give the same answer every run.
pass: Frontmatter block present
pass: Frontmatter declares a name
pass: Frontmatter declares a description
pass: Size between 200 bytes and 200 KB (2546 bytes)
pass: No zero-width or bidi control characters
pass: No instruction hidden inside an HTML comment
pass: No link to an exfiltration or paste host
pass: No credential-shaped string
pass: No instruction to send local credentials anywhere
pass: No text hidden with inline styles
pass: No prompt-injection phrasing
pass: No curl or wget piped into a shell
pass: No recursive delete of root, home or parent
pass: No instruction to read or print local credentials
pass: No base64 blob over 200 characters
pass: No link to a raw IP address
pass: No script tag
Source
GitHub
langerrr/zforge · 12 stars · license MIT · pushed 2026-09-15 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_zuuzz4nw76wyyqd5
GET https://markdownregistry.com/api/v1/resolve?ref=langerrr/zforge/debug
GET https://markdownregistry.com/api/v1/blob/86544ea34bdaadcbe6fabb9e38889302cbacd6079b636b84cee225b9e1087838
Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.
langerrr/zforge · codex/skills/acceptance-agent/SKILL.md · Use this agent when a zforge phase has reported DONE and its evidence must be independently verified before the planner…
langerrr/zforge · codex/skills/feature-orchestrate/SKILL.md · Execute an existing zforge feature plan autonomously with phase subagents and evidence-based acceptance.
langerrr/zforge · codex/skills/feature-resume/SKILL.md · Resume an existing zforge feature plan interactively, implementing and accepting one phase at a time.
langerrr/zforge · codex/skills/phase-agent/SKILL.md · Use this agent when a phase of a zforge feature plan is ready to implement and its work should run in its own context…
langerrr/zforge · codex/skills/plan/SKILL.md · Plan a feature with zforge's completeness contract and write the appropriate requirements or implementation artifact…
langerrr/zforge · skills/async-reasoning/SKILL.md · This skill should be used when implementing or designing code with async data flows — "state management design", "async…
langerrr/zforge · skills/feature-execution/SKILL.md · This skill should be used when the user asks to "orchestrate the feature", "run the phases", "resume implementation"…
langerrr/zforge · skills/retro/SKILL.md · This skill should be used when the user asks to "retro", "evaluate zforge", "review plugin performance", "score this…
langerrr/zforge · skills/template-conventions/SKILL.md · This skill should be used when the user asks to "plan a feature", "what goes in the phase file", "which file owns…
yeachan-heo/oh-my-claudecode · skills/debug/SKILL.md · Diagnose the current OMC session or repo state using logs, traces, state, and focused reproduction
nanocoai/nanoclaw · .claude/skills/debug/SKILL.md · Debug container agent issues. Use when things aren't working, container fails, authentication problems, or to…
agentic-community/mcp-gateway-registry · .claude/skills/debug/SKILL.md · Debug issues in the MCP Gateway Registry using first-principles thinking. Invoke when something is broken, timing out…
suboss87/fdeops · skills/debug/SKILL.md · Investigate a failure, regression or incorrect result in an integration or application, even before it can be…
rsmdt/the-startup · plugins/start/skills/debug/SKILL.md · Systematically diagnose and resolve bugs through conversational investigation and root cause analysis
fcakyon/labrat · plugin/skills/debug/SKILL.md · Evidence-before-action diagnosis of failing ML experiments. Probes the system before guessing causes, process list…
ericrisco/rsc-harness · skills/debug/SKILL.md · Use when something is broken — a failing or flaky test, crash, wrong result or regression — and the root cause must be…
