prizmkit 1.1.102 → 1.1.105

package/bundled/dev-pipeline/templates/agent-prompts/dev-implement.md

@@ -1,71 +0,0 @@
-"<!-- DEPRECATED (P0-6): This prompt was injected into a Dev subagent spawn.
-The orchestrator now implements directly (see phase-implement-agent.md / phase-implement-full.md).
-This file is retained only so load_agent_prompts() does not break; it is no longer referenced
-by any phase section. Do not add new rules here — add them to the phase-implement-* sections instead.
-The rules below are the legacy Dev-subagent version, kept for reference only. -->
-
-Read {{DEV_SUBAGENT_PATH}}. Implement feature {{FEATURE_ID}} (slug: {{FEATURE_SLUG}}).
-
-## Task Summary Card
-
-**Objective**: Implement {{FEATURE_TITLE}}.
-
-**Primary files** (see context-snapshot.md Section 4 for full manifest):
-- Review plan.md Tasks section for the complete task-to-file mapping.
-- Each task's `— file:` suffix identifies the target file.
-
-**Test command**: `{{TEST_CMD}}`
-
-**Known baseline failures**: `{{BASELINE_FAILURES}}`
-
-**DO NOT**:
-- Re-read source files already listed in context-snapshot.md Section 4 File Manifest
-- Create new files unless a plan.md task explicitly requires it
-- Run git commands
-- Use mock success data or fake rows in UI/tests
-
-## Required Inputs
-
-1. Read `.prizmkit/specs/{{FEATURE_SLUG}}/context-snapshot.md` first.
-2. Use Section 4 File Manifest for targeted reads.
-3. Do not expand scope beyond the Task Contract and Verification Gates.
-4. Do not re-read source files already listed in Section 4 unless implementation details are missing from the manifest.
-
-## Work
-
-Run `/prizmkit-implement` to execute `plan.md`.
-
-Test command:
-`{{TEST_CMD}}`
-
-Known baseline failures:
-`{{BASELINE_FAILURES}}`
-
-If plan.md has more than 5 tasks, update durable checkpoints/artifacts after every 3 tasks, minimize output, and rely on runner continuation if context overflow occurs. In an interactive Claude Code session operated manually outside the headless pipeline, `/compact` may be used as an optional convenience only.
-
-## Required Outputs
-
-Before returning, append `## Implementation Log` to `context-snapshot.md` with:
-- files changed/created
-- key decisions
-- deviations from plan
-- test results
-- Verification Gate status
-- unresolved blockers, if any
-
-## Protocol References
-
-- Follow the global Context Budget Rules.
-- Carry forward the Dev-isolated subset: skip scaffold/generated files listed in `context-snapshot.md`; verify dependency versions before install/build commands that resolve dependencies; after build/compile commands, ensure outputs are ignored and never commit generated artifacts.
-- If tests fail, follow this Test Failure Recovery subset: classify failures as baseline, new regression, brittle test, or environment/tooling; fix new regressions and brittle tests while progress is being made; document baseline failures; write `failure-log.md` for blockers.
-- Do not run git commands; staging and commit are handled by the orchestrator.
-- **Edit safety**: If an Edit fails with 'String to replace not found', grep for the target text before retrying. Never guess file offsets — verify them with a Read or grep first.
-- **Read safety**: If 3 consecutive Reads to the same file return 'shorter than offset' or 'Wasted call', STOP and report BLOCKED.
-- **Test gate placement**: Do not run mandatory periodic or full-suite tests here. The scoped/full test gate runs after code review; only use tiny targeted checks when needed for local debugging.
-
-Do not return success unless:
-1. implementation tasks are complete;
-2. `## Implementation Log` exists;
-3. every Verification Gate is verified.
-
-If any Verification Gate is blocked, write `failure-log.md` and return a blocked/incomplete result instead of success."