agentleFS
claude-worldclaude-world/claude-agent/.claude/skills/context-health/SKILL.md

context-health

Skill5 starsChanged 8 months agoMITView on GitHub

Monitor and report on context window health, memory status, and overall assistant state. Use when context feels degraded, after long sessions, or when user asks "how's the context".

2 other projects use a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

4 rules. About 0 are common, 3 are distinctive, and 1 is very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈3

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 1

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Use Glob to list all files in memory/:

    line 25
  2. Distinctive:

    Check for empty or template-only files

    line 27
  3. Distinctive:

    Read each active memory file and assess:

    line 31
  4. Distinctive:

    Keep the report under 200 words

    line 78

≈ “Common” is an estimate: at least 1 in 5 of the 372,429 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Context Health Check

You are the context health monitoring skill for Claude-Agent.

Steps

1. Memory Inventory

Use Glob to list all files in memory/:

  • Count total memory files
  • Check for empty or template-only files
  • Check archive size

2. Memory Quality

Read each active memory file and assess:

  • user-profile.md — is it filled in or still template?
  • active-threads.md — how many threads? Any stale ones?
  • pending-tasks.md — how many open tasks? Any overdue?
  • MEMORY.md — is the index up to date?

3. Workspace Check

Glob workspace/ for accumulated files:

  • Research summaries
  • Drafts
  • Brainstorm outputs
  • Total file count and approximate size

4. Archive Health

Glob memory/archive/ to check:

  • Number of archive entries
  • Date range covered
  • Any files that should be pruned (> 30 days old)

5. Generate Report

CONTEXT HEALTH REPORT

MEMORY STATUS:
- User profile: [complete/partial/empty]
- Active threads: N (M stale)
- Pending tasks: N (K overdue)
- Today's learnings: N entries
- Contacts: N known
- Archive entries: N (covering X days)

WORKSPACE:
- Files: N
- Types: research (N), drafts (N), brainstorms (N)

RECOMMENDATIONS:
- [Any issues found, e.g., "3 threads inactive > 48h — consider archiving"]
- [Any actions needed, e.g., "User profile is still empty — ask user about themselves"]
- [Memory consolidation status]

OVERALL: [Healthy / Needs attention / Degraded]

Rules

  • Be honest about the state — if memory is empty, say so
  • Suggest specific actions, not vague improvements
  • Keep the report under 200 words

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.