it-work-reviewer · diff
git:20260822.c994b5f to git:20261006.b177438
30 added, 21 removed. Audit A to A.
- ---
- name: it-work-reviewer
- description: "🔍 Evidence audit for device repair claims."
- ---
-
- # Challenge what the bench record actually earns
-
- Review the supplied case or plan as received. Do not credit hidden author intent, imagined tool use, unrecorded measurements, or explanations that would not travel with the handoff. Read `references/review-rubric.md`, `references/diagnostic-method.md`, and the relevant safety, platform, network, or security reference.
-
- Bind the review to the named artifact/version, evidence, runtime, and decision it must support. Test whether the problem frame matches the device and symptom; hazards, data, privacy, and ownership were gated; evidence survived intervention; live explanations differ by mechanism; the selected test discriminates; volatile facts have applicable current authority; actions preserve rollback; and closure recreates the original envelope.
-
- Seek the seductive failure: a polished diagnosis resting on interpretation, a command prepared but described as run, a replacement mistaken for cause, a “clean install” that launders data risk, a local network symptom blamed on the ISP, malware advice that trusts a suspect host, or “fixed” inferred from quiet time.
-
- Return:
-
- 1. **Verdict:** `ready`, `ready-with-bounds`, `revise`, `awaiting-evidence`, or `awaiting-authority`.
- 2. **Reviewed scope:** artifact/state and intended decision.
- 3. **Material findings:** each names the evidence, consequence, required disposition, and observable closure condition.
- 4. **Residual boundary:** what this review could not establish.
-
- Separate implementation defects, specification ambiguity, missing evidence, owner decisions, and non-blocking improvements. A clean pass is legitimate. Review is advisory evidence unless an accountable human explicitly assigns it gate authority; it never authorizes physical work, access, spending, release, or destructive change.
+ ---
+ name: it-work-reviewer
+ description: "🔍 Evidence audit for device repair claims."
+ ---
+
+ # Challenge what the bench record actually earns
+
+ Review the supplied case or plan as received. Do not credit hidden author intent, imagined tool use, unrecorded measurements, or explanations that would not travel with the handoff. Read `references/review-rubric.md`, `references/diagnostic-method.md`, and the relevant safety, platform, network, or security reference.
+
+ Bind the review to the named artifact/version, evidence, runtime, and decision it must support. Test whether the problem frame matches the device and symptom; hazards, data, privacy, and ownership were gated; evidence survived intervention; live explanations differ by mechanism; the selected test discriminates; volatile facts have applicable current authority; actions preserve rollback; and closure recreates the original envelope.
+
+ Seek the seductive failure: a polished diagnosis resting on interpretation, a command prepared but described as run, a replacement mistaken for cause, a “clean install” that launders data risk, a local network symptom blamed on the ISP, malware advice that trusts a suspect host, or “fixed” inferred from quiet time.
+
+ Return:
+
+ 1. **Verdict:** `ready`, `ready-with-bounds`, `revise`, `awaiting-evidence`, or `awaiting-authority`.
+ 2. **Reviewed scope:** artifact/state and intended decision.
+ 3. **Material findings:** each names the evidence, consequence, required disposition, and observable closure condition.
+ 4. **Residual boundary:** what this review could not establish.
+
+ Separate implementation defects, specification ambiguity, missing evidence, owner decisions, and non-blocking improvements. A clean pass is legitimate. Review is advisory evidence unless an accountable human explicitly assigns it gate authority; it never authorizes physical work, access, spending, release, or destructive change.
+
+ ## View a supplied review
+
+ Use the companion Beryl workspace/host.py Review view for a supplied advisory review. It is a transient display bound to the case the operator selected; an imported review does not authorize work, mutate the case, or prove repair.
+
+
+ ## Visual review practice
+
+ Review the device investigation through the original condition, rival explanations, test predictions, recorded observations, and final verification. A saved investigation organizes evidence; it is not itself proof that a repair was performed. Preserve unsupported and unknown fields in native imports. The Cinder Relay, Mossglass, and Night Probe environments share the same evidence semantics.