core-context-management-size-limits-mandatory

Sub-skill of core-context-management: Size Limits (MANDATORY) (+3).

5 stars

Best use case

core-context-management-size-limits-mandatory is best used when you need a repeatable AI agent workflow instead of a one-off prompt.

Sub-skill of core-context-management: Size Limits (MANDATORY) (+3).

Teams using core-context-management-size-limits-mandatory should expect a more consistent output, faster repeated execution, less prompt rewriting.

When to use this skill

  • You want a reusable workflow that can be run more than once with consistent structure.

When not to use this skill

  • You only need a quick one-off answer and do not need a reusable workflow.
  • You cannot install or maintain the underlying files, dependencies, or repository context.

Installation

Claude Code / Cursor / Codex

$curl -o ~/.claude/skills/size-limits-mandatory/SKILL.md --create-dirs "https://raw.githubusercontent.com/vamseeachanta/workspace-hub/main/.agents/skills/_core/context-management/size-limits-mandatory/SKILL.md"

Manual Installation

  1. Download SKILL.md from GitHub
  2. Place it in .claude/skills/size-limits-mandatory/SKILL.md inside your project
  3. Restart your AI agent — it will auto-discover the skill

How core-context-management-size-limits-mandatory Compares

Feature / Agentcore-context-management-size-limits-mandatoryStandard Approach
Platform SupportNot specifiedLimited / Varies
Context Awareness High Baseline
Installation ComplexityUnknownN/A

Frequently Asked Questions

What does this skill do?

Sub-skill of core-context-management: Size Limits (MANDATORY) (+3).

Where can I find the source code?

You can find the source code on GitHub using the link provided at the top of the page.

SKILL.md Source

# Size Limits (MANDATORY) (+3)

## Size Limits (MANDATORY)


| File | Max Size | Max Lines | Purpose |
|------|----------|-----------|---------|
| `~/.Codex/AGENTS.md` | 2KB | 50 | Global preferences |
| Workspace `AGENTS.md` | 4KB | 100 | Delegation patterns |
| Project `AGENTS.md` | 8KB | 200 | Project rules |
| `Codex.local.md` | 2KB | 50 | User overrides |

## Validation Command


```bash
# Run validation across all repos
./scripts/context/validate_context.sh

# Check single repo
./scripts/context/validate_context.sh digitalmodel
```

## Content Categories


**MUST be in AGENTS.md:**
- Mandatory behavioral rules (TDD, batching, etc.)
- Plan mode conventions
- Cross-review requirements
- File organization rules
- Key delegation patterns

**MUST be in .Codex/docs/ (reference):**
- Agent lists and descriptions
- MCP tool reference tables
- Execution workflow diagrams
- Code examples and patterns
- Memory namespace details

## Automated Improvement


The skill analyzes past work to suggest improvements:

1. **Pattern Detection**: Identifies frequently used instructions
2. **Redundancy Removal**: Flags duplicate content across files
3. **Usage Analysis**: Tracks which docs are actually loaded
4. **Suggestion Generation**: Proposes optimizations

---

Related Skills

test-oversized-skill

5
from vamseeachanta/workspace-hub

A test fixture skill that exceeds 200 lines with multiple H2/H3 sections for split testing.

context-compaction-handoff

5
from vamseeachanta/workspace-hub

Guardrails for resuming work after context compaction or transcript handoff blocks; prioritize the latest real user request over stale summarized tasks and verify before answering.

git-blob-size-filter-cleanup

5
from vamseeachanta/workspace-hub

Strip oversized blobs from unpushed commits using git filter-branch when GitHub's 100 MB limit blocks push

wiki-context

5
from vamseeachanta/workspace-hub

Auto-query llm-wiki domains for relevant context before executing domain tasks

cron-job-management

5
from vamseeachanta/workspace-hub

Patterns for creating, testing, debugging, and maintaining cron-driven automation in workspace-hub, including log strategy, failure analysis, and safe git-aware job design.

github-repo-management

5
from vamseeachanta/workspace-hub

Clone, create, fork, configure, and manage GitHub repositories. Manage remotes, secrets, releases, and workflows. Works with gh CLI or falls back to git + GitHub REST API via curl.

github-interaction-limits-hardening

5
from vamseeachanta/workspace-hub

Lock down public GitHub repositories so only collaborators can interact with issues, PRs, comments, discussions, and other user-generated surfaces using repository interaction limits; includes expiry verification and renewal handling.

data-context-extractor

5
from vamseeachanta/workspace-hub

Generate or improve a company-specific data analysis skill by extracting tribal knowledge from analysts

data-management

5
from vamseeachanta/workspace-hub

Comprehensive DataFrame loading, filtering, transformation, and data pipeline management from Excel, CSV, and multiple sources with YAML-driven configuration.

skill-chain-context-optimization

5
from vamseeachanta/workspace-hub

Refactor large or frequently-run skills into context-efficient chains using isolated execution, file-backed handoffs, minimal summaries, and runtime-aware command substitution.

task-management

5
from vamseeachanta/workspace-hub

Simple task management using a shared TASKS.md file for tracking commitments and action items.

memory-management

5
from vamseeachanta/workspace-hub

Two-tier memory system for decoding workplace shorthand, acronyms, nicknames, and internal language.