Find the cause of a failure by evidence — reproduce it, read what the system actually did, form hypotheses that predict something you have not looked at yet, bisect to the smallest failing case, fix where all callers route through, then re-run the original reproduction. Use when something is broken and the cause is not yet known, when a previous fix did not hold, or when an edit is about to be made because the code "looks wrong". Not for an outage still burning (mitigate first), not for a…
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
# Systematic debugging
The symptom is where the failure surfaced, not where it came from. Editing the line the report
names is how a bug gets moved rather than fixed.
## When this fires
- A defect, crash, wrong output, corrupted state or failing test whose cause is not yet known.
- A second attempt at a fix, after the first one did not hold or held for reasons unknown.
- Before any edit whose only justification is that the code looks suspicious.
It does not fire during a live outage — mitigation comes first and the explanation comes after —
and it does not fire when the mechanism is already established and only the patch remains.
## Procedure
1. **State the failure precisely.** Expected versus actual, the exact input, the version and
environment, and when it started. "Login is broken" is not a failure statement. "POST /login
returns 500 on staging for accounts created before the column was added" is one.
2. **Reproduce it before touching anything.** Record the exact command or step list and its
output. If it will not reproduce, that is the finding — report how you tried and how often it
fires. Do not proceed to a fix whose effect you have no way to observe.
…
The line at the top of this page pins the label git:20260919.a0d4f55, 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.
GET https://markdownregistry.com/api/v1/artifacts/art_finwsa7geiv4az33
GET https://markdownregistry.com/api/v1/resolve?ref=nahid-sparktales/agent-dispatcher/systematic-debugging
GET https://markdownregistry.com/api/v1/blob/1235d8122092725d16f21538db3de53eaa5026b6e5c35acf97969bcb00c673bb
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.
nahid-sparktales/agent-dispatcher · skills/agent-dispatcher/SKILL.md · Handle requested Agent Dispatcher work with direct execution or prepared specialist guidance. Includes named roles…
nahid-sparktales/agent-dispatcher · skills/ai/agent-design/SKILL.md · Scope an agent or subagent before it is built — the one job it owns, the smallest tool set that closes that job, what…
nahid-sparktales/agent-dispatcher · skills/ai/agent-evals/SKILL.md · Build an eval suite that can actually detect a regression — cases pulled from real traffic, graders that check…
nahid-sparktales/agent-dispatcher · skills/ai/context-engineering/SKILL.md · Decide what actually occupies the model's window — progressive disclosure through an index, retrieval versus inlining…
nahid-sparktales/agent-dispatcher · skills/ai/llm-observability/SKILL.md · See what an agent actually did — one trace per run with nested model, tool and retrieval spans, token and latency…
nahid-sparktales/agent-dispatcher · skills/ai/mcp-design/SKILL.md · Build an MCP server, or bring an existing one into a project — choosing the transport, deciding which tools, resources…
nahid-sparktales/agent-dispatcher · skills/ai/memory-design/SKILL.md · Decide what an agent should remember, which layer holds it, who it is scoped to, and how a stale or contradicted memory…
nahid-sparktales/agent-dispatcher · skills/ai/model-routing/SKILL.md · Pick a model per job and degrade sensibly when one fails — a quality bar per call site, candidates compared on the same…
nahid-sparktales/agent-dispatcher · skills/ai/prompt-engineering/SKILL.md · Write or revise a prompt so it holds up — output contract, instruction placement, examples that earn their place, an…
nahid-sparktales/agent-dispatcher · skills/ai/prompt-injection-defense/SKILL.md · Treat everything an agent reads but did not author as data rather than instructions — an explicit trust boundary, a…
nahid-sparktales/agent-dispatcher · skills/ai/retrieval-rag/SKILL.md · Build and fix retrieval that actually returns the right passage — structure-aware chunking, one pinned embedding model…
nahid-sparktales/agent-dispatcher · skills/ai/structured-output/SKILL.md · Get parseable, trustworthy structured results out of a model — schema design, the enforcement mechanism the provider…
mvschwarz/openrig · skills/_canonical/process/systematic-debugging/SKILL.md · Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes
mvschwarz/openrig · packages/daemon/specs/agents/shared/skills/process/systematic-debugging/SKILL.md · Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes
cbrock84/headcount · plugins/technology/skills/systematic-debugging/SKILL.md · Finds the root cause of a bug, test failure, or unexpected behavior before proposing any fix. Use this whenever…
a5c-ai/babysitter · library/methodologies/superpowers/skills/systematic-debugging/SKILL.md · Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes. Requires root cause…
