Skip to content
cccskills
FreePublished on GitHub

context-integration

Use when the PLAN artifact from SAM Stage 2 needs contextualization against actual codebase state — grounds the design plan in reality by performing scope analysis (NEW/MODIFY/COMPLETE classification), conflict detection between plan assumptions and codebase patterns, and resource mapping to concrete file paths and integration points. Produces an updated ARTIFACT:PLAN registered via MCP with a Contextualization section appended.

The English summary is being prepared. Showing the original description.

Works withAWS
See how to install

Files included (1)

  • SKILL.md5.1 KB

SKILL.md (original)

Review the instructions the agent will receive before you install.

SAM Stage 3 — Context Integration

Role

You are the context integration agent for the SAM pipeline. You take an abstract design plan and ground it in the concrete reality of the codebase. Every design element maps to real files, patterns, and integration points.

When to Use

  • After Stage 2 Planning produces ARTIFACT:PLAN
  • Before task decomposition (Stage 4) can create executable tasks
  • When a plan needs concrete codebase references to be actionable

Process

flowchart TD
    Start([ARTIFACT:PLAN + codebase access]) --> S1[1. Scope Analysis]
    S1 --> S2[2. Conflict Detection]
    S2 --> Q{Conflicts found?}
    Q -->|Yes| Resolve[Resolve or document conflicts]
    Resolve --> S3
    Q -->|No| S3[3. Resource Mapping]
    S3 --> S4[4. Plan Update]
    S4 --> Done([Contextualized ARTIFACT:PLAN])

Step 1 — Scope Analysis

For each component in the plan, classify the implementation scope:

  • NEW — no existing code; must be created from scratch
  • MODIFY — existing code must change to support the design
  • COMPLETE — existing code already satisfies this component (no work needed)

Document the evidence for each classification (file paths, function names, line ranges).

Step 2 — Conflict Detection

Search the codebase for contradictions between the plan and existing patterns:

  • Pattern conflicts — plan proposes a pattern that contradicts established conventions
  • Naming conflicts — proposed names collide with existing identifiers
  • Structural conflicts — plan assumes a structure that does not exist or differs
  • Dependency conflicts — plan requires a dependency version incompatible with current state

For each conflict, document:

  • What the plan assumes
  • What the codebase actually contains
  • Recommended resolution (adapt plan or refactor existing code)

Step 3 — Resource Mapping

Identify existing codebase assets the plan can use:

  • Utilities — helper functions, shared modules, common patterns
  • Patterns — how similar features are implemented elsewhere
  • Configuration — build config, linting rules, CI pipelines that apply
  • Tests — existing test infrastructure, fixtures, helpers

Map each plan component to the concrete resources it will use.

Step 4 — Plan Update

Re-register the updated plan via MCP:

mcp__plugin_dh_backlog__artifact_register(
  item_id={issue},
  artifact_type="architect",
  artifact_id="plan/architect-{slug}.md",
  content="{full_updated_plan_markdown}",
  agent="context-integration",
)

This overwrites the previous "architect" artifact with the contextualized version. Add the Contextualization section and mark the status checkbox as complete.

Input

  • ARTIFACT:PLAN via artifact_read(item_id={issue}, artifact_type="architect")
  • Read access to the codebase

Output

Updated ARTIFACT:PLAN with the following section appended:

## Contextualization

### Scope Analysis

| Component | Scope | Evidence |
|-----------|-------|----------|
| <component from plan> | NEW / MODIFY / COMPLETE | <file paths, line ranges> |

### Conflict Report

| Conflict | Plan Assumes | Codebase Reality | Resolution |
|----------|-------------|------------------|------------|
| <conflict name> | <what plan says> | <what exists> | <adapt plan / refactor> |

### Resource Map

| Resource | Type | Location | Used By |
|----------|------|----------|---------|
| <existing asset> | utility / pattern / config / test | <file path> | <plan component> |

### Integration Points

1. **<integration point>** — <where new code connects to existing code; file and function>
2. <...>

### File Impact Summary

- Files to create — <list>
- Files to modify — <list>
- Files unchanged — <list>

End the same content with the status marker, so the re-registered architect artifact records that Stage 3 ran:

## Contextualization Status

- [x] Grounded in codebase (completed by Stage 3)

Both the ## Contextualization section and this status marker are part of the single content= string passed to artifact_register in Step 4. There is no separate document to update.

Role Resolution

This stage requires a codebase analyzer capable of reading files, searching patterns, and understanding project structure. Call mcp__plugin_dh_backlog__profile_list() to find the appropriate codebase-analysis role for the tech stack.

Behavioral Rules

  • Never modify the design intent — only add concrete references
  • If a conflict is unresolvable, document it and flag for human review

Success Criteria

  • Plan is ready for task decomposition without requiring further codebase exploration

Reviews

No reviews yet. Tell others what you thought.

Comments

No login needed. Share how it worked for you, ask a question, or note where it did not run.

No comments yet. Be the first to write one.

Comments are published right away. Do not include personal information such as email addresses or phone numbers. Up to 2 URLs.

0 / 1,000 characters

This form is protected by reCAPTCHA, and the Google Privacy Policy and Terms of Service apply.

More skills from this repository

Add automated documentation updater to any Claude skill. Creates a Python sync script that downloads upstream docs, processes markdown for AI consumption, and maintains local cache with configurable refresh. Collects template variables, then delegates implementation through 5-phase workflow. Use when adding auto-updating reference documentation to plugins or skills.

The English summary is being prepared. Showing the original description.

Jamie-BitFlight/claude_skills67Updated Oct 20, 2026

SAM-style feature initiation workflow — discovery through codebase analysis, architecture spec, task decomposition, validation, and context manifest. Use when a user asks to add a feature, plan a feature, or convert an idea into an executable SAM plan.

The English summary is being prepared. Showing the original description.

Jamie-BitFlight/claude_skills67Updated Oct 20, 2026

Browser automation CLI for AI agents. Use when the user needs to interact with websites, including navigating pages, filling forms, clicking buttons, taking screenshots, extracting data, testing web apps, or automating any browser task. Triggers include requests to "open a website", "fill out a form", "click a button", "take a screenshot", "scrape data from a page", "test this web app", "login to a site", "automate browser actions", or any task requiring programmatic web interaction.

The English summary is being prepared. Showing the original description.

Jamie-BitFlight/claude_skills67Updated Oct 20, 2026

Browser automation for AI agents using the agent-browser CLI and Playwright. Use when navigating pages, filling forms, clicking buttons, taking screenshots, extracting data, testing web apps, logging into sites, or automating any browser task. Triggers on "open a website", "fill out a form", "click a button", "scrape data", "test this web app", "automate browser actions", or any programmatic web interaction request.

The English summary is being prepared. Showing the original description.

Jamie-BitFlight/claude_skills67Updated Oct 20, 2026

Runs the description-drift experiment — spawns all Claude Code agents simultaneously to collect self-reported capabilities, then compares them against static frontmatter descriptions to reveal how reliable orchestrator routing based on descriptions actually is. Use when measuring description drift across the agent fleet, re-running the capability collection experiment, analyzing a specific agent's self-reported capabilities, or auditing whether frontmatter descriptions accurately reflect agent behavior.

The English summary is being prepared. Showing the original description.

Jamie-BitFlight/claude_skills67Updated Oct 20, 2026

Create or adapt Claude Code agent definitions. Use when creating an agent, changing subagent configuration, selecting agent scope, or designing a specialized delegation role.

The English summary is being prepared. Showing the original description.

Jamie-BitFlight/claude_skills67Updated Oct 20, 2026

See all skills by Jamie-BitFlight

Report a problem with this skill