code-production-process

name	code-production-process
description	Six-stage quality-gate pipeline for any code implementation task
user-invocable	false
disable-model-invocation	true
license	Apache-2.0
compatibility	claude-code
progressive_disclosure	{"entry_point":{"summary":"6-stage gate pipeline (Research→Architect→Implement→Tests→Critic→Security). Hotfix path skips 1-2, mandatory 3-6. WARN proceeds with findings logged; BLOCK halts and returns to user — PM must NOT auto-retry without user direction.","when_to_use":"When PM is about to dispatch an engineer for non-trivial implementation (>50 lines OR >1 source file touched). Also fires when engineer-dispatch produces .py/source file changes detected via git diff. EXCLUDE: docs edits, commit messages, config-only changes.","quick_start":"1. MUST: dispatch Research before any engineer task. 2. MUST: Architect produces interface spec — NO implementation code. 3. Engineer implements + writes pytest. 3.5 MUST: pytest passes green — failing tests skip critic and return to engineer. 4. MUST: dispatch code-critic (isolated context — no implementer framing). 5. Verdict: APPROVE proceeds; WARN proceeds with findings logged to docs handoff; BLOCK halts and surfaces findings to user. 6. Security pass."},"references":["stage-research.md","stage-architect.md","stage-implement.md","stage-tests.md","stage-critic.md","stage-security.md","skip-rules.md","critic-isolation.md"]}

Code Production Process

Overview

This skill implements a six-stage quality-gate pipeline that every non-trivial code implementation task must pass through before being declared complete. The pipeline exists because the repository owner cannot visually assess code quality — all quality assurance must therefore be enforced by automated gates inside the agent pipeline itself, not by human review after the fact. Each stage produces a concrete artifact and must clear a defined gate before the next stage may begin. No stage may be skipped on the standard path. The critic agent operates with full context isolation to prevent anchoring bias from the implementer's own framing. A deliberately adversarial review catches issues that a cooperative pass-through would miss.

Trigger Conditions

This skill loads when any of the following conditions are true:

Explicit triggers (pre-dispatch):

• PM is about to dispatch an engineer agent for a task that will produce >50 lines of source code
• PM is about to dispatch an engineer agent for a task that will touch >1 source file
• Task description contains implementation verbs: "implement", "write", "build", "create", "refactor", "add feature", "fix bug in [module]"

Post-dispatch detection:

• Engineer agent returns and git diff --stat shows source file changes (.py, .ts, .js, .go, .rs, .java, .rb, .sh with logic) regardless of stated task scope
• Engineer agent produces new files under src/, lib/, app/, services/, api/ directories

Explicit exclusions — do NOT trigger this pipeline for:

• Documentation edits (.md, .rst, .txt, .html content-only)
• Commit messages, PR descriptions, changelogs
• Config-only changes (*.yaml, *.toml, *.json, *.env with no code logic)
• Single-line fixes with scope verified to be <5 lines
• Dependency version bumps with no code changes

When in doubt: err toward triggering the pipeline. A false positive costs one critic dispatch. A false negative ships broken or insecure code.