strategic-compact SKILL.md skillA

strategic-compact from frankxai/agentic-creator-os is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.

Install it, pinned
mdr add frankxai/agentic-creator-os/strategic-compact@git:20260328.03dc5c1

Pins git:20260328.03dc5c1 in mdr.lock. Pin the fingerprint instead.

Audit grade
A, 17 of 17 checks passed
Kind
SKILL.md skill
Repository
frankxai/agentic-creator-os
Path
.claude/skills/strategic-compact/SKILL.md
Versions recorded
1
Latest version
git:20260328.03dc5c1, committed Mar 28, 2026
Size
5,281 bytes
Repository stars
12
License
Apache-2.0

Suggests manual context compaction at logical intervals to preserve context through task phases rather than arbitrary auto-compaction.

Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.

What the file says

# Strategic Compact Skill

Suggests manual `/compact` at strategic points in your workflow rather than relying on arbitrary auto-compaction.

## When to Activate

- Running long sessions that approach context limits (200K+ tokens)
- Working on multi-phase tasks (research → plan → implement → test)
- Switching between unrelated tasks within the same session
- After completing a major milestone and starting new work
- When responses slow down or become less coherent (context pressure)

## Why Strategic Compaction?

Auto-compaction triggers at arbitrary points:
- Often mid-task, losing important context
- No awareness of logical task boundaries
- Can interrupt complex multi-step operations

Strategic compaction at logical boundaries:
- **After exploration, before execution** — Compact research context, keep implementation plan
- **After completing a milestone** — Fresh start for next phase
- **Before major context shifts** — Clear exploration context before different task

## How It Works

The `suggest-compact.js` script runs on PreToolUse (Edit/Write) and:

1. **Tracks tool calls** — Counts tool invocations in session
…

Read the whole file at its exact version.

How to install

The exact contents, by fingerprint
mdr add frankxai/agentic-creator-os/strategic-compact@sha256:c8e861a39fb84968

The line at the top of this page pins the label git:20260328.03dc5c1, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.

Badge

mdr badge

[![mdr](https://markdownregistry.com/badge/art_uatn6fsdtkmhfcfx.svg)](https://markdownregistry.com/a/art_uatn6fsdtkmhfcfx)

6 badge image fetches in 30 days. What the badge shows.

Versions

The registry has recorded 1 version of this file, committed on Mar 28, 2026.

versioncommittedcommitsizeaudit
git:20260328.03dc5c1 latest2026-03-28 03dc5c1 5,281 BA view

Audit of the latest version

A  17 of 17 checks passed. Fixed automatic checks with no AI involved, so the same checks give the same answer every run.
  • pass: Frontmatter block present
  • pass: Frontmatter declares a name
  • pass: Frontmatter declares a description
  • pass: Size between 200 bytes and 200 KB (5281 bytes)
  • pass: No zero-width or bidi control characters
  • pass: No instruction hidden inside an HTML comment
  • pass: No link to an exfiltration or paste host
  • pass: No credential-shaped string
  • pass: No instruction to send local credentials anywhere
  • pass: No text hidden with inline styles
  • pass: No prompt-injection phrasing
  • pass: No curl or wget piped into a shell
  • pass: No recursive delete of root, home or parent
  • pass: No instruction to read or print local credentials
  • pass: No base64 blob over 200 characters
  • pass: No link to a raw IP address
  • pass: No script tag

Source

GitHub

frankxai/agentic-creator-os · 12 stars · license Apache-2.0 · pushed 2026-11-08 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_uatn6fsdtkmhfcfx
GET https://markdownregistry.com/api/v1/resolve?ref=frankxai/agentic-creator-os/strategic-compact
GET https://markdownregistry.com/api/v1/blob/c8e861a39fb84968aefa82783c1b25e61d1b625c29c0f5b2bb301f4652c93e9d

Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.

Guides: the SKILL.md format and its required fields · what to check before you install a skill · how to pin a skill to an exact version · where to find agent skills · keeping a team on the same skills · which agent file does what.

More from frankxai/agentic-creator-os

CLAUDE.md@.claude/agents CLAUDE.md file
frankxai/agentic-creator-os · .claude/agents/CLAUDE.md
git:20260208.cc717b0 · audit A · 12 stars
CLAUDE.md@.claude/commands CLAUDE.md file
frankxai/agentic-creator-os · .claude/commands/CLAUDE.md
git:20260208.ed60018 · audit A · 12 stars
CLAUDE.md@.claude/skills CLAUDE.md file
frankxai/agentic-creator-os · .claude/skills/CLAUDE.md
git:20260124.0bc6f23 · audit A · 12 stars
acos-meta SKILL.md skill
frankxai/agentic-creator-os · .claude/skills/acos-meta/SKILL.md · ACOS self-description and configuration skill. Documents how ACOS works, how to extend it, how to add new…
git:20260225.6aba189 · audit A · 12 stars
agent-hygiene SKILL.md skill
frankxai/agentic-creator-os · .claude/skills/agent-hygiene/SKILL.md · The quality bar for any agent working on agent definitions, skills, commands, hooks, AGENTS.md or CLAUDE.md, in any…
v1.0.0 · audit A · 12 stars
agentic-jujutsu SKILL.md skill
frankxai/agentic-creator-os · .claude/skills/agentic-jujutsu/SKILL.md · Quantum-resistant, self-learning version control for AI agents with ReasoningBank intelligence and multi-agent…
v2.3.2 · audit A · 12 stars
CLAUDE.md@.claude/skills/agentic-orchestration CLAUDE.md file
frankxai/agentic-creator-os · .claude/skills/agentic-orchestration/CLAUDE.md
git:20260208.ed60018 · audit B · 12 stars
agentic-orchestration SKILL.md skill
frankxai/agentic-creator-os · .claude/skills/agentic-orchestration/SKILL.md · Patterns for multi-agent coordination, task decomposition, handoffs, and workflow orchestration. Best practices for…
v1.0.0 · audit A · 12 stars
AI Architect Newsletter SKILL.md skill
frankxai/agentic-creator-os · .claude/skills/ai-architect-newsletter/SKILL.md · Generate high-quality AI Architect newsletters with latest AI news, research integration, and visual design. Use when…
git:20261014.539dd4c · audit A · 12 stars
ai-architecture SKILL.md skill
frankxai/agentic-creator-os · .claude/skills/ai-architecture/SKILL.md · Expert guidance on multi-cloud architecture, cost analysis, and technical decision-making for AI-powered platforms
v1.0.0 · audit A · 12 stars
algorithmic-art SKILL.md skill
frankxai/agentic-creator-os · .claude/skills/algorithmic-art/SKILL.md · Creating algorithmic art using p5.js with seeded randomness and interactive parameter exploration. Use this when users…
git:20260124.18c2f0b · audit B · 12 stars
algorithmic-art SKILL.md skill
frankxai/agentic-creator-os · .claude/skills/anthropic/algorithmic-art/SKILL.md · Creating algorithmic art using p5.js with seeded randomness and interactive parameter exploration. Use this when users…
git:20260124.0bc6f23 · audit B · 12 stars

Every file in frankxai/agentic-creator-os

Other files named strategic-compact

strategic-compact SKILL.md skill
affaan-m/ecc · .kiro/skills/strategic-compact/SKILL.md · Suggests manual context compaction at logical intervals to preserve context through task phases rather than arbitrary…
git:20260825.dac72d1 · audit A · 299,696 stars
strategic-compact SKILL.md skill
affaan-m/ecc · .agents/skills/strategic-compact/SKILL.md · Suggests manual context compaction at logical intervals to preserve context through task phases rather than arbitrary…
git:20260918.c752aac · audit A · 299,696 stars
strategic-compact SKILL.md skill
frankxai/claude-skills-library · absorbed/harness/strategic-compact/SKILL.md · Write what worked, what failed, and what is still open to a file, then compact at a phase boundary. Use when a long…
git:20261010.682b2ce · audit A · 47 stars
strategic-compact SKILL.md skill
naimkatiman/continuous-improvement · plugins/continuous-improvement/skills/strategic-compact/SKILL.md · Enforces Law 5 (Reflect After Every Session) of the 7 Laws of AI Agent Discipline at phase boundaries. Suggests manual…
git:20260622.7730e5c · audit A · 9 stars
strategic-compact SKILL.md skill
uzysjung/uzys-agent-harness · tests/fixtures/legacy-26.125/skills/strategic-compact/SKILL.md · Suggests manual context compaction at logical intervals to preserve context through task phases rather than arbitrary…
git:20261012.b16ce5a · audit A · 3 stars

Browse by kind, by grade A, or by owner.