diegosouzapw/awesome-omni-skill / skills/ai-agents/agent-ops-context-map
agent-ops-context-map
VerifiedAnalyze the codebase to create a concise, LLM-optimized structured overview in .agent/map.md.
| File | Kind | Size |
|---|---|---|
| SKILL.md | skill md | 3.1 KB |
| metadata.json | config | 1.4 KB |
SKILL.md
View on GitHub---
name: agent-ops-context-map
description: "Analyze the codebase to create a concise, LLM-optimized structured overview in .agent/map.md."
category: analysis
invokes: [agent-ops-state]
invoked_by: [agent-ops-constitution, agent-ops-planning]
state_files:
read: [focus.md, constitution.md]
write: [map.md, focus.md]
---
# Context Map Generation
## Purpose
Create a high-level, token-efficient overview of the system (`.agent/map.md`) to allow reasoning about the whole project without reading every file.
## Confidence-Based Staleness Thresholds
**Map freshness requirements scale with confidence level:**
| Confidence | Max Age | Refresh Requirement |
|------------|---------|---------------------|
| LOW | 24 hours | MANDATORY before implementation |
| NORMAL | 7 days | RECOMMENDED if significant changes |
| HIGH | 30 days | OPTIONAL |
### Staleness Check
When invoked (or before low confidence work):
```
π CONTEXT MAP STALENESS CHECK
Map file: .agent/map.md
Last updated: {date} ({N} days ago)
Confidence level: {confidence}
Max age for confidence: {threshold}
{If stale:}
β οΈ Context map is STALE for {confidence} confidence work.
For LOW confidence, understanding the codebase is critical.
Refreshing map before proceeding...
{If fresh:}
β
Context map is current ({N} days old, threshold: {threshold} days)
```
### Low Confidence Refresh Requirements
For LOW confidence work:
1. **Check map age** β if > 24 hours, refresh is MANDATORY
2. **Check for recent changes** β git diff since last map update
3. **Partial refresh option** β focus on affected areas if full refresh is expensive
```
π LOW CONFIDENCE CONTEXT MAP REFRESH
Affected areas for {ISSUE-ID}:
- src/services/ (target of changes)
- src/models/ (dependencies)
- tests/services/ (test coverage)
Refresh options:
1. Full refresh (entire codebase)
2. Partial refresh (affected areas only)
3. Skip (NOT RECOMMENDED for low confidence)
Proceeding with partial refresh...
```
## Procedure
1. **Scan** the file structure (limit to 2-3 levels of depth).
2. **Identify** key architectural elements:
- Critical configuration files (package.json, pyproject.toml, docker-compose, etc.)
- Entry points (main.py, index.js, App.tsx)
- Core modules and their responsibilities.
3. **Summarize** architecture patterns and data flow.
4. **Write/Update** `.agent/map.md` with the following structure:
- **System Overview**: One paragraph summary of purpose and stack.
- **Key Components**: List of major modules/folders and what they do.
- **Patterns**: Architectural decisions (e.g., MVC, Repository pattern, Event-driven).
- **Key Files**: Table of critical files and their specific role.
- **Last Updated**: Timestamp for staleness tracking.
5. **Constraint**: Keep the file concise (target < 150 lines). It is a map, not a territory.
## Map Header Template
Include this header in map.md for staleness tracking:
```markdown
# Context Map
**Generated**: {YYYY-MM-DD HH:MM}
**Scope**: {full | partial: areas}
**Confidence**: {confidence level that triggered refresh}
---
```
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| reverse-engineer-anythingmorluto/reaReverse engineer native, managed, Electron/JavaScript, packaged, firmware, and browser targets with REA, and build agent environments (AgentEnv bundles) of web applications from a live instance or a capture, and of Linux desktop apps with a task from a request. Use shipped-artifact or requested runtime evidence to explain features, compare versions, decompile code, or guide a reconstruction. Skip REA for ordinary source-repository architecture analysis. | Stars: 472k | Updated | Claude CodeCodex | Verified | Install |
| diagnosing-superpowersobra/superpowersUse when a superpowers session went wrong and your human partner wants to know why β repeated work, ignored plans, stumbles, poor results, a skill that didn't fire, "it took too long", "why is it so expensive", "what is it doing" β or wants to build a bug report for the superpowers maintainers, for the current session or a past one identified by id or path, on any harness. | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| executing-plansobra/superpowersUse when executing an implementation plan in the current session as the implementer yourself β your human partner chose inline execution, or no subagent tool is available | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |