agentleFS
flonatflonat/flonat-research/skills/session-health/SKILL.md

session-health

Skill150 starsChanged 12 days agoMITView on GitHub

Check whether the current session has coherent guidance, focus, handoff state, working-tree ownership, and enough context to proceed safely. Use when starting, resuming, or diagnosing a confused session. Not for auditing the machine or deployed AI infrastructure; use $system-audit.

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

12 rules. About 0 are common, 10 are distinctive, and 2 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈10

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 2

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    If found: show filename, first 3 lines, and whether it contains "APPROVED" or is still "DRAFT"

    line 29
  2. Distinctive:

    If none: report "No active plan"

    line 30
  3. Distinctive:

    If found: show filename and first 3 lines

    line 35
  4. Distinctive:

    If none: report "No session log found"

    line 36
  5. Very specific:

    Check when .context/current-focus.md was last modified:

    line 40
  6. Very specific:

    If older than 3 days: warn "Focus file is stale — consider running update-focus"

    line 42
  7. Distinctive:

    If > 5: warn "Many open loops — consider triaging"

    line 53
  8. Distinctive:

    When context is high (>60%), include these reference tables in the output:

    line 86
  9. Distinctive:

    When the context monitor fires a warning

    line 112
  10. Distinctive:

    Before starting a large task (to check remaining capacity)

    line 113
  11. Distinctive:

    After resuming a session (to verify state was preserved)

    line 114
  12. Distinctive:

    When unsure if preservation hooks are working

    line 115

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 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 Status: Session Health Check

On-demand diagnostic showing context usage, preservation state, and open work items. Fast and lightweight — no vault queries.

What to Check

1. Context Usage Estimate (host-aware)

Use the active client's native context meter when it is exposed. A client adapter may provide a tool-call counter, but it is optional and must never be treated as shared memory. If no meter is available, report SKIPPED (client does not expose context telemetry); do not guess a percentage from conversation length.

Calculate:

  • Tool calls so far
  • Estimated percentage (calls / 150)
  • Which thresholds have fired (from the fired array)
  • Time since last warning

2. Active Plan

Find the latest file in log/plans/:

  • If found: show filename, first 3 lines, and whether it contains "APPROVED" or is still "DRAFT"
  • If none: report "No active plan"

3. Latest Session Log

Find the latest non-compact .md file in log/ (skip files with -compact in the name):

  • If found: show filename and first 3 lines
  • If none: report "No session log found"

4. Focus Freshness

Check when .context/current-focus.md was last modified:

  • Show the modification date
  • If older than 3 days: warn "Focus file is stale — consider running update-focus"
  • Show the first 5 lines (headline)

5. Preservation and Continuity

Verify the client-neutral continuity files first: applicable root guidance, .context/ai-handoff.md, .context/current-focus.md, latest approved plan, and portable memory index. Then read docs/reference/ai-surface-availability.md or run the staged AI-infrastructure doctor to report each client hook adapter as CONFIGURED, UNAVAILABLE, or NOT APPLICABLE. Missing optional lifecycle hooks are informational when the files-first layer is healthy.

6. Open Loops

Count unchecked items (- [ ]) in .context/current-focus.md:

  • Report the count
  • If > 5: warn "Many open loops — consider triaging"

Output Format

Present as a compact status panel:

## Session Health

| Metric | Value |
|--------|-------|
| Context usage | ~XX% (N/150 tool calls) |
| Thresholds fired | none / info / warning / critical |
| Active plan | filename (DRAFT/APPROVED) / none |
| Latest log | filename / none |
| Focus freshness | N days ago / stale warning |
| Open loops | N items |

### Preservation Hooks

| Hook | Status |
|------|--------|
| Files-first continuity | HEALTHY / DEGRADED |
| Current client lifecycle adapter | CONFIGURED / UNAVAILABLE / NOT APPLICABLE |
| Context telemetry | AVAILABLE / SKIPPED |

### Recommendations

[Only if there are issues — e.g., stale focus, missing hooks, high context usage]

7. Compaction Guidance

When context is high (>60%), include these reference tables in the output:

When to compact:

Phase TransitionCompact?Why
Research to PlanningYesResearch context is bulky; plan is the distilled output
Planning to ImplementationYesPlan is in a file; free up context for code
Implementation to TestingMaybeKeep if tests reference recent code
Debugging to Next featureYesDebug traces pollute context
Mid-implementationNoLosing file paths and partial state is costly
After a failed approachYesClear dead-end reasoning

What survives compaction:

PersistsLost
CLAUDE.md / AGENTS.md + rulesIntermediate reasoning
Task listFile contents previously read
MEMORY.md + .context/Multi-step conversation context
Git stateTool call history
Files on diskVerbal preferences
.context/ai-handoff.md—

When to Use

  • When the context monitor fires a warning
  • Before starting a large task (to check remaining capacity)
  • After resuming a session (to verify state was preserved)
  • When unsure if preservation hooks are working

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.