القائمة
Enforce AutoResearch loop cadence, attempt, token, time, sub-agent, remote-compute, and kill-switch limits.
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
Load and enforce AutoResearch loop constraints before triage, edits, remote work, or external writes.
Read AutoResearch run evidence and loop state, then propose one bounded next experiment or escalate. L1 is report-only.
从 Verl examples 脚本和示例 YAML 中维护“可控参数即特性”的中文情报库与 Excel 台账。Use when Codex needs to scan Verl examples/run scripts, extract all user-adjustable parameters and Hydra overrides, create or update per-parameter markdown explanation files under docs/verl/features/lists, use subagents to research unclear parameters from local explanation files, official Verl docs, and repo docs, and produce docs/verl/features/verl-example-parameters.xlsx with parameter name, category, Chinese explanation, common values, performance impact, accuracy impact, and example count.
Generate RMB task cost reports from Codex/OpenAI-style token usage, including total input tokens, cached input tokens, uncached input tokens, output tokens, and GPT plus DeepSeek API cost estimates. Use when the user asks to统计 token 消耗, API 费用, 人民币成本, cache hit 成本, GPT/DeepSeek 对比, or to produce an `RMB-Cost.md` report for a task, goal, session, or experiment. Use by default for any goal, experiment, remote run, long command, or automation whose expected or actual runtime exceeds 20 minutes.
Verl GRPO formal case adapter for AutoResearch. Use when building, running, or diagnosing autoresearch run verl-case; preparing Qwen/geo3k GRPO matrices; wiring Verl containers to model/data assets, W&B, Prometheus, reports, provenance, and numbered evidence bundles; or explaining val-only versus real GRPO training boundaries.
Generate, validate, inspect, and safely handle AutoResearch customer configuration files. Use when working on config init/show/validate commands, Pydantic config schema behavior, keyring or env secret placeholders, redacted display, or config/config.yaml templates.
| name | loop-budget |
| description | Enforce AutoResearch loop cadence, attempt, token, time, sub-agent, remote-compute, and kill-switch limits. |
| user_invocable | true |
Run at the start and end of every loop iteration.
loop-budget.md, STATE.md, and the last 24 hours of loop-run-log.md..loop-paused exists or state is paused.Append a structured record to loop-run-log.md with timestamp, trigger, evidence/run id, candidate count, actions, attempts, escalations, duration, token estimate, verdict, and stop reason. Never rewrite previous entries.
For L2, stop after three attempts for a hypothesis or two identical failure signatures, even if time/token budget remains.