CruxExperts/LocalSetup / ls/skills/ls-codex-heartbeat-checks
ls-codex-heartbeat-checks
VerifiedOpt-in agent heartbeat harness for target repositories: initialize config, run transaction-safe checks, preserve artifacts, and wire cron only after explicit activation.
| File | Kind | Size |
|---|---|---|
| SKILL.md | skill md | 8.6 KB |
| references/artifacts.md | markdown | 1.3 KB |
| references/command-logging.md | markdown | 1.9 KB |
| references/config.md | markdown | 23.2 KB |
| references/process-control.md | markdown | 7.5 KB |
| references/recovery.md | markdown | 4.2 KB |
| references/transactions.md | markdown | 1.4 KB |
| scripts/codex_heartbeat.pyexecutable | script | 25.3 KB |
| scripts/codex_heartbeat_support.py | script | 17.7 KB |
| scripts/heartbeat_lscli.py | script | 4.6 KB |
| scripts/heartbeat_process.py | script | 5.9 KB |
| scripts/heartbeat_protocol.py | script | 4.1 KB |
| scripts/heartbeat_review.py | script | 5.8 KB |
| templates/HEARTBEAT.md | markdown | 728 B |
| templates/codex_heartbeat.yaml | config | 1.8 KB |
references/artifacts.md
View on GitHub---
status: ACTIVE
version: 3.4
---
# Heartbeat Artifacts
Ordinary transaction artifacts live under the configured heartbeat state directory
in the target repository (default `.localsetup/state/codex-heartbeat/`).
Each ordinary run starts as `runs/<run-id>.staged`. Promotion requires valid hashes for `manifest.json`, `heartbeat-result.json`, `command-log.json`, and every command sidecar referenced by the command log.
Pointers and lock evidence:
- `active.json`: points at the staged run while work is active.
- `latest.json`: points at the most recently promoted run and records the manifest hash.
- `heartbeat.lock`: prevents concurrent runs.
Pointers and artifact references must stay relative to their heartbeat-state base. Absolute paths and parent traversal are rejected.
[Reserved actions](config.md#running-a-reserved-action) share the heartbeat overlap
lock but do not create this staged artifact graph. Their private attempt result
lives at `state_root/heartbeat/binding/result.json`, with policy and charged
reservations under the explicit accounting root. See the
[reserved execution owner](process-control.md#reserved-execution-owner) and
[result acknowledgement recovery](recovery.md#reserved-result-acknowledgement-recovery)
for evidence validation and uncertainty handling.
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| reverse-engineer-anythingmorluto/reaReverse engineer native, managed, Electron/JavaScript, packaged, firmware, and browser targets with REA, and build agent environments (AgentEnv bundles) of web applications from a live instance or a capture, and of Linux desktop apps with a task from a request. Use shipped-artifact or requested runtime evidence to explain features, compare versions, decompile code, or guide a reconstruction. Skip REA for ordinary source-repository architecture analysis. | Stars: 472k | Updated | Claude CodeCodex | Verified | Install |
| diagnosing-superpowersobra/superpowersUse when a superpowers session went wrong and your human partner wants to know why — repeated work, ignored plans, stumbles, poor results, a skill that didn't fire, "it took too long", "why is it so expensive", "what is it doing" — or wants to build a bug report for the superpowers maintainers, for the current session or a past one identified by id or path, on any harness. | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| executing-plansobra/superpowersUse when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool is available | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |