Menu
Builds structural, semantic, and philosophical context artifacts for a module or service: module manifest, behavioral contracts, and decision log.
Install with Codex or Claude Copy this prompt, paste it into Codex, Claude, or another assistant, and let it review the skill page and install it for you.
Based on SOC occupation classification
Orchestration skill: chains the full ADLC Build Loop. PRD → Brief → Council → Scaffold → Codegen → LDD → TDD → Council → PR. Use when implementing a new feature end-to-end.
Generate a bounded, schema-valid goal prompt from one validated Build Brief task for zero-context external execution.
Applicability-aware Definition of Done checklist. Core checks apply to every task; overlay checks activate only when the applicability manifest says the surface exists. Binary verification — pass or fail. Triggers at Phase 4 completion and Phase 5 entry.
Score whether each task is specific enough for autonomous, one-shot, production-ready execution.
Reviews code changes for understanding, blast radius, state, secrets, assumptions, and explainability. Produces a blocking comprehension artifact when implications are unclear.
Resolve ambiguous triage outcomes in the middle confidence band.
| name | context-layers |
| description | Builds structural, semantic, and philosophical context artifacts for a module or service: module manifest, behavioral contracts, and decision log. |
| contract_version | 1.0.0 |
| side_effect_profile | read_only |
| activation | {"mode":"overlay","consumes_manifest":true,"trigger_fields":["new_module","new_interface","service_boundary_change","api_change","data_format_change","persistent_storage"],"produces":["module_manifest","behavioral_contracts","decision_log"]} |
ADLC prevents dark code by embedding comprehension into the codebase. This skill captures three layers for any module or service that is new, heavily changed, ownership-sensitive, or hard to explain:
These artifacts are codebase assets. They are not planning notes.
Open with:
"I'm going to help you build three context layers for a module or service: structural, semantic, and philosophical. Which module or service do you want to document? Give me its name and a brief description of what it does."
Then ask layer questions in sequence and wait for answers.
Ask:
Probe vague answers. For example: "When you say it talks to the user service, is that a synchronous API call, an event, or a shared database read?"
For each major interface, ask:
Push back on "it just works normally." That is a comprehension gap.
Ask:
If the user does not know, record the gap explicitly: "Reasoning unknown. Treat as load-bearing; do not modify without investigation."
Before outputting artifacts, confirm: "I have enough to generate your three context artifacts. Want me to proceed, or is there anything you want to add or correct?"
When this skill runs inside ADLC, generate artifact requirements in the Build Brief instead of conducting a long interview if the repo evidence is enough. Ask the engineer only for gaps that cannot be inferred safely.
Create or update context artifacts when:
Markdown file suitable for the module root, such as MODULE_MANIFEST.md or CONTEXT.md.
Required sections:
Markdown file or structured comments next to interface definitions.
For each interface:
Markdown file structured as decisions.
For each decision:
