context-mgmt SKILL.md skillA

context-mgmt from ariaxhan/kernel-claude is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.

Install it, pinned
mdr add ariaxhan/kernel-claude/context-mgmt@git:20261029.de0dd17

Pins git:20261029.de0dd17 in mdr.lock. Pin the fingerprint instead.

Audit grade
A, 17 of 17 checks passed
Kind
SKILL.md skill
Repository
ariaxhan/kernel-claude
Path
skills/context-mgmt/SKILL.md
Versions recorded
13
Latest version
git:20261029.de0dd17, committed Oct 29, 2026
First version recorded
May 15, 2026
Size
6,017 bytes
Repository stars
14
License
MIT

Context engineering: compaction, progressive disclosure, structured notes via AgentDB. Triggers: tokens, compaction, memory, handoff, summarize, context window.

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

<skill id="context-mgmt">

<purpose>
Context is finite. Every token competes for attention.
Longer context makes things WORSE (30%+ accuracy drop for middle info).
Progressive disclosure: load what's needed when it's needed.

**Reasoning fidelity is the real metric, not token count.** Quality degrades at ~60-70% fill, not at the limit.
</purpose>

<prerequisite>
Monitor context usage. Compact or hand off proactively at ~60% capacity — not 80%, not at limit.
Use native /context command to check usage. This skill is for methodology.
</prerequisite>

<reference>
Skill-specific: skills/context-mgmt/reference/context-mgmt-research.md
Architecture: _meta/research/context-graph-architecture.md
Graph telemetry (shadow): JSON receipts → `agentdb graph-project` / `graph-suggest` (see orchestration/agentdb/graph-project.py). Canonical JSON manifests remain authoritative.
</reference>

<core_principles>
1. COMPACTION: Summarize and reinitialize. Keep architecture decisions, discard noise.
2. STRUCTURED NOTES: AgentDB + active.md persist across context resets.
…

Read the whole file at its exact version.

How to install

The exact contents, by fingerprint
mdr add ariaxhan/kernel-claude/context-mgmt@sha256:e4fab492708a2830

The line at the top of this page pins the label git:20261029.de0dd17, 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_h6h5zvgljyvgokla.svg)](https://markdownregistry.com/a/art_h6h5zvgljyvgokla)

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

Versions

The registry has recorded 13 versions of this file, between May 15, 2026 and Oct 29, 2026, about one every 14 days.

versioncommittedcommitsizeaudit
git:20261029.de0dd17 latest2026-10-29 de0dd17 6,017 BA view · diff
git:20261027.d140bc22026-10-27 d140bc2 5,776 BA view · diff
git:20261019.4911d112026-10-19 4911d11 5,580 BA view · diff
git:20261018.74a259c2026-10-18 74a259c 5,178 BA view · diff
git:20261002.d999fd22026-10-02 d999fd2 4,826 BA view · diff
git:20260929.510ab002026-09-29 510ab00 4,529 BA view · diff
git:20260926.ef417622026-09-26 ef41762 4,395 BA view · diff
git:20260910.20bff722026-09-10 20bff72 3,941 BA view · diff
git:20260711.31c24882026-07-11 31c2488 3,979 BA view · diff
git:20260711.6a3ae5a2026-07-11 6a3ae5a 3,964 BA view · diff
git:20260711.c23e6cb2026-07-11 c23e6cb 3,872 BA view · diff
git:20260528.53798292026-05-28 5379829 3,789 BA view · diff
git:20260515.bb740fb2026-05-15 bb740fb 5,803 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 (6017 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

ariaxhan/kernel-claude · 14 stars · license MIT · pushed 2026-10-30 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_h6h5zvgljyvgokla
GET https://markdownregistry.com/api/v1/resolve?ref=ariaxhan/kernel-claude/context-mgmt
GET https://markdownregistry.com/api/v1/blob/e4fab492708a283010a5af2eb986006803757d812f0e25cad70a8b9b146720a6

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 ariaxhan/kernel-claude

AGENTS.md AGENTS.md file
ariaxhan/kernel-claude · AGENTS.md
git:20260914.b467c9d · audit A · 14 stars
CLAUDE.md CLAUDE.md file
ariaxhan/kernel-claude · CLAUDE.md
git:20260914.b467c9d · audit A · 14 stars
llms.txt llms.txt file
ariaxhan/kernel-claude · llms.txt
git:20260912.482f2bc · audit A · 14 stars
app-dev SKILL.md skill
ariaxhan/kernel-claude · skills/app-dev/SKILL.md · Mobile/web build pipeline: fastlane-first local builds, store submission, pre-submission checklists. Triggers: app…
git:20261026.56c9dc2 · audit A · 14 stars
architecture SKILL.md skill
ariaxhan/kernel-claude · skills/architecture/SKILL.md · Modular design, interface stability, dependency management, AI-code health. Triggers: architecture, design, structure…
git:20260910.20bff72 · audit A · 14 stars
checkpoint SKILL.md skill
ariaxhan/kernel-claude · skills/checkpoint/SKILL.md · Save bounded progress as kernel.checkpoint/v1 for exact resume after reset. Triggers: checkpoint, save progress…
git:20260828.e3ca514 · audit A · 14 stars
debug SKILL.md skill
ariaxhan/kernel-claude · skills/debug/SKILL.md · Diagnosis before prescription: reproduce, hypothesize, isolate, fix root cause, add a regression test; refactor mode…
git:20260920.7955cbf · audit A · 14 stars
dream SKILL.md skill
ariaxhan/kernel-claude · skills/dream/SKILL.md · Deep creative exploration engine. Competing perspectives, stress-tested by a 4-persona council, scored by integrity…
git:20260829.6827144 · audit A · 14 stars
eval SKILL.md skill
ariaxhan/kernel-claude · skills/eval/SKILL.md · Eval-Driven Development (EDD) for AI workflows. pass@k metrics, capability evals, regression evals. Triggers: eval…
git:20261017.fd085ca · audit A · 14 stars
experiment SKILL.md skill
ariaxhan/kernel-claude · skills/experiment/SKILL.md · Rules as hypotheses: falsifiable tests, confidence updates, graduate or kill. Triggers: experiment, hypothesis, prove…
git:20260910.20bff72 · audit A · 14 stars
forge SKILL.md skill
ariaxhan/kernel-claude · skills/forge/SKILL.md · Autonomous development with experimental self-correction. Iterates through quality gates until antifragile or blocked.
git:20260829.6827144 · audit A · 14 stars
frontend SKILL.md skill
ariaxhan/kernel-claude · skills/frontend/SKILL.md · Context-led frontend design: art direction derived from product, audience, brand and the existing system, not generic…
git:20260925.f52d02b · audit A · 14 stars

Every file in ariaxhan/kernel-claude

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