Condition Triage
Make scope decisions cheap to review without transferring ownership to the agent.
Procedure
- Read the complete inventory and
STATEFUL.md. Require the current iteration’s feature, platforms, commitments, constraints, and available evidence.
- For each condition, recommend:
- likelihood:
low, medium, or high;
- impact:
low, medium, or high;
- confidence:
hypothesis, informed, or measured;
- a one-sentence evidence-grounded rationale;
- scope:
in, out-with-implication, or out.
- Do not equate likelihood with priority. Elevate irreversible, safety, security, privacy, regulatory, or high-blast-radius conditions even when rare.
- For
out-with-implication, name the concrete constraint on in-scope copy, naming, policy, data, architecture, or testing.
- For
out, record why it is deferred and what would trigger reconsideration.
- Check dependencies and relationships. An in-scope condition cannot rely on an incompatible out-of-scope precondition without an explicit implication.
- Summarise high-impact hypotheses separately; they require evidence collection, not confident-looking prose.
- Present the full recommendation and stop. Ask the human to confirm or adjust.
- Only after confirmation:
- persist scope and priority;
- set
status: triaged unless a condition was already at a later status;
- update
STATEFUL.md;
- preserve deferred conditions.
Output
| ID | Condition | Likelihood | Impact | Confidence | Recommended scope | Rationale / implication |
|---|---|---|---|---|---|---|
## Totals
In: <n> · Out-with-implication: <n> · Out: <n>
High-impact hypotheses: <n>
## Consistency flags
- <dependency or scope conflict>
Confirm or adjust? No decisions will be persisted until you do.
Include layers and failure cause when present.
Failure modes
- Persisting agent recommendations before confirmation.
- Scoping by implementation difficulty rather than relevance.
- Treating
out as deletion.
- Omitting the implication.
- Assigning false precision unsupported by evidence.
- Allowing high-impact hypotheses to disappear into a total.
1---2name: state-triage3description: Recommend evidence-aware risk and scope decisions for a complete Stateful condition inventory, recording likelihood, impact, confidence, rationale, and one of in, out-with-implication, or out for human confirmation. Use after state-list or state-audit and before specification. Do not persist recommendations or continue to specification until a human confirms them.4---56# Condition Triage78Make scope decisions cheap to review without transferring ownership to the agent.910## Procedure11121. Read the complete inventory and `STATEFUL.md`. Require the current iteration’s feature, platforms, commitments, constraints, and available evidence.132. For each condition, recommend:14 - likelihood: `low`, `medium`, or `high`;15 - impact: `low`, `medium`, or `high`;16 - confidence: `hypothesis`, `informed`, or `measured`;17 - a one-sentence evidence-grounded rationale;18 - scope: `in`, `out-with-implication`, or `out`.193. Do not equate likelihood with priority. Elevate irreversible, safety, security, privacy, regulatory, or high-blast-radius conditions even when rare.204. For `out-with-implication`, name the concrete constraint on in-scope copy, naming, policy, data, architecture, or testing.215. For `out`, record why it is deferred and what would trigger reconsideration.226. Check dependencies and relationships. An in-scope condition cannot rely on an incompatible out-of-scope precondition without an explicit implication.237. Summarise high-impact hypotheses separately; they require evidence collection, not confident-looking prose.248. Present the full recommendation and stop. Ask the human to confirm or adjust.259. Only after confirmation:26 - persist scope and priority;27 - set `status: triaged` unless a condition was already at a later status;28 - update `STATEFUL.md`;29 - preserve deferred conditions.3031## Output3233```text34| ID | Condition | Likelihood | Impact | Confidence | Recommended scope | Rationale / implication |35|---|---|---|---|---|---|---|3637## Totals38In: <n> · Out-with-implication: <n> · Out: <n>39High-impact hypotheses: <n>4041## Consistency flags42- <dependency or scope conflict>4344Confirm or adjust? No decisions will be persisted until you do.45```4647Include layers and failure cause when present.4849## Failure modes5051- Persisting agent recommendations before confirmation.52- Scoping by implementation difficulty rather than relevance.53- Treating `out` as deletion.54- Omitting the implication.55- Assigning false precision unsupported by evidence.56- Allowing high-impact hypotheses to disappear into a total.
mskayyali