بنقرة واحدة
context-checkpoint
Use when task completion or context usage requires a handoff readiness check
التثبيت باستخدام Codex أو Claude انسخ هذا Prompt والصقه في Codex أو Claude أو مساعد آخر ليراجع صفحة Skill ويثبّتها لك.
القائمة
Use when task completion or context usage requires a handoff readiness check
التثبيت باستخدام Codex أو Claude انسخ هذا Prompt والصقه في Codex أو Claude أو مساعد آخر ليراجع صفحة Skill ويثبّتها لك.
استنادا إلى تصنيف SOC المهني
Use when reviewing a spec or task graph for completeness before implementation
Use when the user needs to interact with websites, including navigating pages, filling forms, clicking buttons, taking screenshots, extracting data, testing web apps, logging in, or automating browser actions
Use when the user needs to interact with websites, including navigating pages, filling forms, clicking buttons, taking screenshots, extracting data, testing web apps, logging in, or automating browser actions
Use when decomposing a spec, design, or feature description into a task dependency graph with self-evaluating acceptance criteria
Use when doing creative product, feature, component, functionality, or behavior design work
Use when infrastructure or features are built but before declaring done -- verifies work is wired into the system and actively used
| name | context-checkpoint |
| description | Use when task completion or context usage requires a handoff readiness check |
| user-invocable | false |
Monitor context consumption and trigger proactive handoff before quality degrades. Called after every task completion in executing-beads.
Core principle: Better to hand off early than to lose context and produce bad work.
Layer 1 — Native context awareness (always present). Codex Sonnet 4.5+, Sonnet 4.6, and Haiku 4.5 receive context state after every tool call:
<system_warning>Token usage: 35000/200000; 165000 remaining</system_warning>
No hook needed — workers already know their context state from system_warning. Thresholds are loaded from thresholds.json at the project root:
| Model | Soft threshold | Hard threshold |
|---|---|---|
| Opus | 65% | 85% |
| Sonnet | 50% | 70% |
| Haiku | 40% | 60% |
Source of truth: thresholds.json.
The Go worker enforces the hard stop as a backstop: if the agent does not respond to the soft threshold, handleContextThreshold sends a handoff and kills the subprocess at hard threshold (soft + 20%).
These symptoms indicate context degradation regardless of token usage — treat as immediate handoff:
system_warning shows usage well below soft threshold. Proceed to next task.
Finish your current atomic step (complete the file edit, run its verification, record the result). Then:
Stop after your very next tool call. Write a minimal handoff (goal + files modified + next steps). Any in-progress work will be captured by the compaction safety net.
oro task update <id> --notes "Partial: <what's done, what remains>"create-handoff skill with tasks: sectiongit pull --rebase && git push
When handing off due to context checkpoint, add tasks: section to handoff YAML:
tasks:
completed: [oro-xxx, oro-yyy]
in_progress: [oro-zzz]
remaining: [oro-aaa, oro-bbb]
epic: oro-www
tasks: section