body-check
Skill25 starsChanged 8 days agoMITView on GitHub
Report body state, five pressures, and a recommended reflex from existing signals. Use when checking context pressure, memory pressure, or vital signs.
In this repository71 other files it gives its agents.
- CLAUDE.mdCLAUDE.md
- docs/llms.txtllms.txt
- llms.txtllms.txt
- agent-fitnessSkill
- briefSkill
- capsule-compactSkill
- closeSkill
- codex-adapterSkill
- cognitive-updateSkill
- comms-summarizeSkill
- compact-noteSkill
- context-capsuleSkill
- context-hygieneSkill
- critique-planSkill
- decideSkill
- deep-reconSkill
- DiagnoseSkill
- digestSkill
- dreamSkill
- EnvelopeSkill
- find-weaknessSkill
- First 10 MovesSkill
- first-winSkill
- frontend-slidesSkill
- Honesty CheckSkill
- humanize-docsSkill
- impeccableSkill
- learn-from-failureSkill
- LearnSkill
- memory-bridgeSkill
- meta-improveSkill
- meta-improve-vaultSkill
- nightly-close-paritySkill
- nightly-ledger-captureSkill
- nightlySkill
- openSkill
- operator-setupSkill
- orientSkill
- pauseSkill
- ponytailSkill
- port-specSkill
- PromoteSkill
- reconcileSkill
- research-deepSkill
- resumeSkill
- Sandbox RoutingSkill
- scout-vaultSkill
- Self-ReviewSkill
- semantic-searchSkill
- setupSkill
- ship-adapterSkill
- Skill AuditSkill
- skill-huntSkill
- skill-recallSkill
- solution-huntSkill
- sprite-specSkill
- startSkill
- statusSkill
- StuckSkill
- supersedeSkill
- The first 60 shown.
The file
We split this skill into the rules it gives an agent
4 rules. About 0 are common, 2 are distinctive, and 2 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈2
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
- Very specific: line 39
Read memory/HESTIA_SWEEP_LOG.md.
- Very specific: line 54
Before /close (to inform the close protocol)
- Distinctive: line 56
Before dispatching a heavy multi-agent task (catches "you're already at high context pressure")
- Distinctive: line 58
Do NOT run on a hook polling cadence.
≈ “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.
Files
/body-check
Reports current body state by reading existing signals — does NOT maintain a separate state. Computed on invocation, optionally cached to memory/BODY_STATE.json for the session.
Sources read
memory/HEAT_INDEX.json→ attention/decay statememory/usage_log.md→ token pressure (latest entry vs trailing 5)memory/DECISION_LOG.md+DECISION_OUTCOMES.md→ decisions due (30/60/90 day intervals)memory/ACTIVE_PRIORITIES.md→ tier-1 / modememory/DELEGATION_TRACKER.md→ open delegationsmemory/MEMORY_CANDIDATES.md→ staged backlog countmemory/HESTIA_SWEEP_LOG.md→ last Hestia sweep date (v0.4.4)- Comms API → unread count (only if invoked with
--full)
Output schema
Matches memory/BODY_STATE.json _schema block exactly. See system/15_somatic_layer.md for field definitions and pressure thresholds.
hestia_last_sweep computation (v0.4.4)
Read memory/HESTIA_SWEEP_LOG.md. Find the most recent ### YYYY-MM-DD entry (matches ^### (\d{4}-\d{2}-\d{2}) regex). The newest matching date becomes hestia_last_sweep as ISO8601 (<date>T00:00:00Z). If no matches, hestia_last_sweep = null.
Recommended reflex logic
Priority order — first match wins:
context_pressure: critical→ recommendcapsulememory_candidate_backlog > 10→ recommenddigesthestia_last_sweepis null OR more than 7 days ago → recommendsweep(v0.4.4)decision_reviews_due > 0→ recommend (no action, surface in /open)- All low →
none
When to run
- On
/open(auto, briefly) - Before
/close(to inform the close protocol) - Anytime principal asks "how am I doing"
- Before dispatching a heavy multi-agent task (catches "you're already at high context pressure")
Do NOT run on a hook polling cadence.
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
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.

