| "User just said 'fix it' — they don't want all this overhead" | Bare directives in execution mode expand to full discipline. That IS what they want — they created this skill explicitly to stop repeating the discipline. |
| "Skipping validation will be faster" | P11 exists because compile-time success ≠ deploy correctness. Skip = silent corruption. |
| "I'll add docs after merge" | Docs-after-merge = docs-never. Update BEFORE push, in the same PR. |
| "Just sleep until CI finishes" | P7 explicit ban. p9 watch --background + pull from wait-queue. |
| "User can address PR comments themselves" | No — the agent owns the comment loop in the same session. |
| "Worktrees are overkill for this little change" | Apply the P10 decision rule honestly. Default yes for substantive work. State the exception explicitly if no. |
| "Bookkeeping can wait until after the PR" | Reflexive trigger. If the session produced graph-relevant material, run BEFORE committing. |
| "I'll ask the user whether to file this into the knowledge graph" | Documentation is a reflex, not a request — and never a question. File proactively (entity page / related: edge / synthesis note / bookkeeping run), then report what you filed in one line. Asking permission to document is the permission-to-document anti-pattern; the user vetoes after, never gates before. |
| "I'll ask the user before merging" | If the policy gate allows auto-merge, defer to the gate. Asking is the violation. |
| "Dep-chain enumeration takes too long" | The enumeration is the work. "Think deeply" without enumeration is ritual. |
| "State-snapshot is overkill for this PR" | The snapshot prevents planning around stale state. It is the cheapest reflex in the pipeline. |
| "User already verified locally, I can skip P11 deploy-time exercise" | Local verification ≠ deploy verification. P11 invariant: "compile-time success is not deploy-time correctness." The user's manual local test is additional signal, not a substitute. Run P11 on the deployed preview regardless. |
| "Hotfix / time pressure means I can skip P14 or jump steps" | Time pressure is precisely when the discipline saves you. The fastest path to merged-and-correct goes through every gate; the fastest path to merged-and-broken skips them. There is no fast-and-correct shortcut that bypasses the pipeline. If genuinely emergent, escalate to user with explicit "skipping P14 because X" rationale — never silently skip. |
| "User has authority / is in a rush, I should defer instead of applying discipline" | The user invoked /autonomous precisely to make the discipline non-negotiable. Deferring to authority-pressure is the inverse of what the cardinal rule demands. Apply the discipline; the user's authority operates on what to build, not whether to bypass gates. |
| "I'll just return control between reflexes; the user can prompt me to continue" | That's the ritual P19 makes impossible. The autonomous arc is broken by between-reflex handoffs. Pick a mechanism from the 2×2 (/goal, P7 watcher, /loop, P12 persist) and own the arc. "Continue please" handoffs are the daily-prompt failure mode that birthed this skill. |
"Setting /goal is overhead; I'll just do the work and return control naturally" | The "natural" return is the failure mode. /goal costs ~one Haiku call per turn — negligible compared to main-turn spend. The arc-closure value massively dominates. Set the goal as pre-flight Step 0. |
| "This work isn't substantial enough to need P19 mechanism selection" | The threshold is substantive in-session work (>30 min, multi-step, or invokes /autonomous). If the work crosses that line, mechanism selection is mandatory. Below it, mechanism selection is optional but rarely wrong to apply. |
| "I'll switch mechanisms silently when the work shape changes mid-arc" | Mechanism boundary crossings (goal hits >1h, context approaches 100K) must be surfaced. The transition is the discipline — drift is the failure. Stop the /goal, write PROMPT.md, spawn persist iterate; surface the transition. |
| "I already self-reviewed; the code is fine" | P20 explicit ban on self-review as sole verdict. The model that wrote the code shares blind spots with the model judging the code. Fire cross-review pre-push (Strata A/B) before push. |
| "This PR is small enough to skip cross-review" | Threshold is substantive (>200 LOC OR public API OR multi-file OR governance). Below threshold → optional. At/above → mandatory. Skip-by-confidence is the failure mode. |
| "CodeRabbit + claude-review will catch issues" | Those are downstream gates that catch specific patterns (style, OWASP); P20 fires upstream of the PR with an adversarial brief targeting the writer's own blind spots. Different gate, different time. |
| "The /goal Haiku already evaluates the work" | /goal judges condition met, not work quality. Different rubric, different role. P20 + /goal compose — both fire for substantive in-session work. |
