Home / jnpiyush / agentx · .github/skills/development/strategic-compaction/SKILL.md · GitHub

strategic-compaction skillA

strategic-compaction is agent-read markdown (skill) from jnpiyush/agentx: Decide when to compact, reset, or continue a long-running agent session. Use when context pressure rises, when a checkpoint boundary is reached, or when a clean handoff to a different agent is needed. Encodes the rule that compaction is safe between phases but dangerous mid-implementation, and that reset beats compaction once durable artifacts diverge from the chat transcript..

Indexed from public GitHub and served as immutable, content-addressed versions. Install it pinned to an exact SHA-256 with the mdr CLI, and every file is verified against the hash recorded here before it reaches your agent. The deterministic audit below grades the latest version, and the same file always earns the same grade.

What the file says

# Strategic Compaction

> **Purpose**: Choose between continue, compact, and reset without losing work or fabricating context.
> **Scope**: Long-running sessions, checkpoint transitions, agent handoffs, token-pressure events.

---

## When to Use This Skill

- Token budget is approaching the provider's compaction trigger.
- A workflow checkpoint just changed (Plan -> Work, Work -> Review, Review -> Compound Capture).
- The user explicitly says "compact", "reset", "start over", or "switch agent".
- The chat transcript and the repo state have begun to disagree.

## When NOT to Use

- Mid-implementation, halfway through editing a file. Finish the bounded slice first.
- During an active validation run (tests executing, command in flight).
- Inside a self-review iteration where the next step is already queued.

## Decision Order

Try these in order. Pick the first one whose preconditions hold.

1. **Continue in place** when the active issue, plan, slice, and blocker state are still coherent and the budget will hold for at least one more bounded step.
…

Read the whole file at its exact version.

How to install

Latest version
mdr add jnpiyush/agentx/strategic-compaction@v1.0.0
Exact content
mdr add jnpiyush/agentx/strategic-compaction@sha256:7e9be2a2a7ea5b32

Pin to a label to follow the author's releases, or to a sha256 to freeze the exact bytes forever. Either way the resolved hash is written to mdr.lock, and mdr install reproduces it on any machine.

Badge

mdr badge

[![mdr](https://markdownregistry.com/badge/art_a3hnm22zzrnt66sk.svg)](https://markdownregistry.com/a/art_a3hnm22zzrnt66sk)

1 badge views in 30 days

Versions

versioncommittedcommitsizeaudit
v1.0.0 latest2026-09-15 f17c505 7,594 BA view · diff
v1.0.02026-05-30 55f7137 7,588 BA view · diff
v1.0.02026-05-18 6c28d61 7,582 BA view

Audit of the latest version

A  17 of 17 checks passed. Deterministic, no model, 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 (7594 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

jnpiyush/agentx · 16 stars · license Apache-2.0 · pushed 2026-09-21 · branch master

API

GET https://markdownregistry.com/api/v1/artifacts/art_a3hnm22zzrnt66sk
GET https://markdownregistry.com/api/v1/resolve?ref=jnpiyush/agentx/strategic-compaction
GET https://markdownregistry.com/api/v1/blob/7e9be2a2a7ea5b32a5fa4da0cc18cde980d1d5e39d076848dd1317c84b5dfbd3

Your agent 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.

More from jnpiyush/agentx

000-frontier-core rules
jnpiyush/agentx · .cursor/rules/000-frontier-core.mdc · Frontier core operating contract for Cursor. Always applied.
git:20260915.f17c505 · audit A · 16 stars
ai rules
jnpiyush/agentx · .cursor/rules/ai.mdc · AI / agent / LLM workflow standards (Frontier)
git:20260915.f17c505 · audit A · 16 stars
csharp rules
jnpiyush/agentx · .cursor/rules/csharp.mdc · C# / .NET coding standards (Frontier)
git:20260915.f17c505 · audit A · 16 stars
python rules
jnpiyush/agentx · .cursor/rules/python.mdc · Python coding standards (Frontier)
git:20260915.f17c505 · audit A · 16 stars
react rules
jnpiyush/agentx · .cursor/rules/react.mdc · React / TSX frontend standards (Frontier)
git:20260915.f17c505 · audit A · 16 stars
typescript rules
jnpiyush/agentx · .cursor/rules/typescript.mdc · TypeScript / Node backend standards (Frontier)
git:20260915.f17c505 · audit A · 16 stars
agent-memory-systems skill
jnpiyush/agentx · .github/skills/ai-systems/agent-memory-systems/SKILL.md · Design agent memory beyond a single context window: short-term (working / scratchpad), long-term (episodic, semantic…
v1.0.0 · audit A · 16 stars
agent-observability skill
jnpiyush/agentx · .github/skills/ai-systems/agent-observability/SKILL.md · Instrument LLM agents with tracing, metrics, and evaluation telemetry. Use when adding OpenTelemetry GenAI semantic…
v1.0.0 · audit A · 16 stars
ai-agent-development skill
jnpiyush/agentx · .github/skills/ai-systems/ai-agent-development/SKILL.md · Build production-ready AI agents with Microsoft Foundry and Agent Framework. Use when creating AI agents, selecting LLM…
git:20260903.b3f2610 · audit A · 16 stars
ai-evaluation skill
jnpiyush/agentx · .github/skills/ai-systems/ai-evaluation/SKILL.md · Use when evaluating AI quality, safety, completeness and cost with held-out tasks, executable graders, calibrated…
v1.1.0 · audit A · 16 stars
ai-safety-and-red-teaming skill
jnpiyush/agentx · .github/skills/ai-systems/ai-safety-and-red-teaming/SKILL.md · Defend LLM systems against prompt injection, jailbreaks, data exfiltration, and unsafe output. Covers input/output…
v1.0.0 · audit B · 16 stars
anthropic-claude skill
jnpiyush/agentx · .github/skills/ai-systems/anthropic-claude/SKILL.md · Implement production applications with Anthropic Claude models -- Messages API, tool use, prompt caching, extended…
v1.0.0 · audit A · 16 stars

Every file in jnpiyush/agentx

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