ql-intent-check

ql-intent-check — intent-drift audit

Purpose

Long pipelines (brainstorm → spec → plan → execute → review) paraphrase. Each stage re-reads an upstream artifact and rewrites it in its own format. Over 5 stages and 20+ agent invocations, the user's original intent can drift significantly — ACs silently reinterpreted, non-goals forgotten, constraints softened.

Academic backing:

• Semantic Consensus Framework (SCF, arXiv:2604.16339): formally names "Semantic Intent Divergence" as the root cause of multi-agent SWE failures. Prescribes per-agent Semantic Intent Graph + Drift Monitor.
• Agent Drift (arXiv:2601.04170): introduces Agent Stability Index (ASI) and shows all models drift under pressure.
• Goal Drift in LM Agents (arXiv:2505.02709): Claude 3.5 Sonnet holds goals for 100K tokens but drifts under competing objectives.

ql-intent-check operationalizes a lean version of SCF's Drift Monitor for quantum-loop's pipeline.

Immutable intent snapshot

The first time /ql-brainstorm runs, it MUST store the user's verbatim first-message text at quantum.json.userIntent:

{
  "userIntent": {
    "text": "<verbatim first-message text from user>",
    "timestamp": "<ISO 8601>",
    "source_message_id": "<optional session ID>"
  }
}

This field is immutable — it is written once and never updated. Subsequent clarifications live in userClarifications[] (append-only). The snapshot is the ground-truth anchor for drift detection.

If quantum.json.userIntent is missing, this skill emits a WARNING and degrades to "compare stage-to-stage" mode (less precise but still useful).

Stages audited

1. Intent → Design: userIntent.text vs docs/plans/<date>-<topic>-design.md.
2. Design → PRD: design.md vs tasks/prd-<feature>.md.
3. PRD → Plan: PRD vs quantum.json.stories[].acceptanceCriteria.
4. Plan → Implementation: AC text vs commit messages + test names + code comments.
5. Implementation → Review: commit content vs ql-review output.