Skip to content
Back to skills

Context Hygiene

ASecurity

trigger: context bloat, stale observations, resolved content inlined, noisy exploration. avoid: context rot and lost-in-the-middle failures.

  • 8 stars
  • 0 votes
  • 0 copies
  • 0 views
  • Added September 30, 2026
ai-agentsgit

Works with

  • cli

Security analysis

A100/100

Scanned September 30, 2026

npx -y skills add open-coder-ai/chock --skill context-hygiene --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Context Hygiene?

Add the live security badge to your README. It updates with every re-scan.

Security grade badge for Context Hygiene
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/open-coder-ai-context-hygiene-chock/badge)](https://www.skillsdirectory.com/skills/open-coder-ai-context-hygiene-chock)

More formats (shields.io, HTML) on the badges page. Keep it an A: scan every change in CI with Pro.

Download with Pro
SKILL.md
---
name: context-hygiene
description: "trigger: context bloat, stale observations, resolved content inlined, noisy exploration. avoid: context rot and lost-in-the-middle failures."
metadata:
  chock.artifact: rule
  chock.enforcement: advise
  chock.coverage_without_chock: advisory
---

# Context Hygiene Rule

trigger: context bloat, stale observations, resolved content inlined, noisy exploration. avoid: context rot and lost-in-the-middle failures.

```
replace(resolved_content): path_ref_only; delegate(noisy_exploration): subagent; prune(stale > 3_turns)
on_context_growth: summarize(old_observations); keep(decisions+outcomes); discard(superseded_content)
```

This skill is advisory: the client reading it has no mechanism to enforce it, and this policy stays advisory even when compiled by `chock` -- it ships rule text, not a blocking hook. See https://github.com/open-coder-ai/chock

Attribution

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

Comments

Loading comments…

Newsletter

Get the weekly list of safe new skills, and the ones we pulled.