Failure forensics
Skill cdeust/zetetic-team-subagents/skills/failure-forensics
11 problem-shaped skills backed by 97 sourced reasoning patterns — Curie to Toulmin, as Claude Code agents. Every claim cites its source; a pre-commit gate blocks unsourced constants. Install the gates alone in 30s (zetetic-gates). The only agent system where "I don't know" is a feature.
npx -y skills add cdeust/zetetic-team-subagents --skill failure-forensicsAssembled from the repository path, not quoted from the project. Check it against their README if it does not work.
One thing to look at
- 7 stars7 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.
What its author says it does
Copied from the file, not written here
Read the wreckage before rebuilding. Use for incident post-mortems, "what happens when everything goes wrong at once?", flaky or anomalous cases being filtered out as noise, "that's weird" moments nobody wrote down, oscillating or unstable feedback behavior, and designs whose only failure mode is crash.
SKILL.md
2.7 KB, as published. Nobody here has run it
Failure Forensics
Problem shape: something failed (or will fail) and the evidence is being averaged away, cleaned up, or explained by its most convenient story. The move: treat anomalies as data, reconstruct the timeline at the right timescale, and design the degraded state as a first-class behavior.
Relevant geniuses
| Agent | Use when |
|---|---|
| hamilton | overload and simultaneous failure scenarios; priority shedding by criticality; the degraded mode is undesigned; "users will never do that" |
| mcclintock | aggregate metrics look smooth but one specific case is weird; a class of observations is being trimmed as noise |
| fleming | anomalies keep appearing during routine work and being cleaned up; "that's weird" said and never investigated |
| ginzburg | reconstruct what happened from marginal traces and involuntary evidence (logs, timestamps, artifacts nobody meant to leave) |
| braudel | the incident needs three-timescale decomposition — event, cycle, structure — before a root cause is named |
| wu | the failure hides under an assumption everyone considered too obvious to test |
| maxwell | the system oscillates, overshoots, or hunts — feedback stability and gain-margin diagnosis |
Invocation
- Pick the best-fit agent above. If two or more fit, run
tools/genius-invoker.sh route "<problem>"and take the top ranked match. - Load it:
tools/genius-invoker.sh invoke <agent> "<problem>", then readagents/genius/<agent>.mdin full. - Apply the agent's
<workflow>step by step and answer in its<output-format>. Reproduce before claiming a cause; classify the cause before proposing the fix (coding-standards §6 root-cause protocol). - Typical chain: ginzburg reconstructs the timeline → braudel separates
timescales → hamilton designs the degraded state. Run via
tools/genius-invoker.sh compose ginzburg hamilton -- "<problem>". - If no shape above matches, use a standard team agent instead.
Refuse when
- No reproduction and no trace evidence exist — forensics reads records, it does not invent narratives.
- The requested output is a fix at the throw site with no cause classification.