Перевод: оболочка страницы на русском; тело навыка (SKILL.md) пока на английском — это исходные инструкции агента.
Progress Ledger
Keep a Magentic-style task and progress ledger.
Метаданные навыка
| Источник | Встроенный (установлен по умолчанию) |
| Путь | skills/research/progress-ledger |
| Версия | 1.0.0 |
| Автор | VibeOS |
| Лицензия | MIT |
| Платформы | linux, macos, windows |
| Теги | research, orchestration, multi-agent, kanban, planning |
| Связанные навыки | analysis-orchestration, professional-research, challenge-gate |
Справка: полный SKILL.md
Ниже полное определение навыка, которое VibeOS загружает при активации. Это инструкции, которые видит агент.
Progress Ledger Skill
Maintain a Task Ledger (facts, guesses, plan) and a Progress Ledger (current step, assignee, stall count, replan notes) for long jobs. Inspired by Magentic-One — without peer agent chat. Use files or a Kanban root-task comment; do not invent a new core tool.
When to Use
- Multi-step research, creative, or operate jobs longer than a few tool rounds.
delegate_taskbatches or Kanban swarms where the parent must replan on stall.- User asks to “track progress”, “don’t get stuck”, or “show the plan”.
Prerequisites
- Writable workdir (session cwd or Kanban workspace).
- Optional: Kanban board for durable jobs (
vibeos kanban/kanban_*tools). - Related:
analysis-orchestrationfor gatherer/critic/synthesizer roles.
How to Run
- Copy
templates/ledger.mdto the workdir asprogress-ledger.md(or pin the same JSON block as a Kanban comment on the root task). - At job start: fill Task Ledger — known facts, open guesses, ordered plan.
- Each major step: update Progress Ledger — current step, who owns it
(role/profile),
stall_count,last_progress_at, blockers. - If
stall_count≥ 2 with no new artifacts: replan (outer loop) — revise Task Ledger plan, reset stall, note what failed. - On finish: set
status: doneand point to final artifact paths.
Quick Reference
| Field | Where | Purpose |
|---|---|---|
facts | Task Ledger | Confirmed evidence |
guesses | Task Ledger | Unverified hypotheses |
plan | Task Ledger | Ordered steps |
current_step | Progress Ledger | What is in flight |
assignee | Progress Ledger | Role/profile owning the step |
stall_count | Progress Ledger | Consecutive no-progress ticks |
blockers | Progress Ledger | CAPTCHA, missing keys, waits |
Template path (relative to this skill): templates/ledger.md.
Procedure
Outer loop (Task Ledger)
When starting or after a stall replan:
- List facts you would bet money on (with source pointers).
- List guesses separately — never mix into facts.
- Write a short plan (5–12 steps). Prefer durable Kanban tasks for steps that must survive restart.
Inner loop (Progress Ledger)
After each child/delegate_task result or Kanban heartbeat window:
- Ask: did we gain a new artifact, finding, or decision?
- If yes → update
current_step, resetstall_countto 0. - If no → increment
stall_count; if ≥ 2, jump to outer-loop replan. - Record human gates (
assignee: human, ChallengeGate) as blockers — do not thrash tools behind a wall.
Persistence choices
| Job length | Store ledger in |
|---|---|
| Single chat turn / short batch | progress-ledger.md in workdir |
| Multi-hour / restart-safe | Kanban root task via CLI (below) + file copy |
| Cron / monitor | Job workdir file; optional archival memory later |
Kanban persistence (CLI)
Upsert the ledger onto the root task (survives restart):
vibeos kanban ledger <root_task_id> --set progress-ledger.md
vibeos kanban ledger <root_task_id> # print body
vibeos kanban ledger <root_task_id> --json # machine-readable
Dashboard: GET/PUT /api/plugins/kanban/tasks/{id}/ledger.
Marker: <!-- vibeos:progress_ledger v1 --> (upsert keeps a single comment).
Promote process-local work → Kanban (manual)
Background delegate_task is process-local — it dies on app restart.
When a job outlives a short batch (Fleet shows a promote hint after
delegation.promote_hint_after_seconds, default 600s), manually create a
durable task. Never auto-create Kanban rows without an explicit command.
# Flags
vibeos kanban from-delegation --title "Continue research" --goal "…" \
--context "constraints…" --summary "partial findings…" \
[--ledger-file progress-ledger.md] [--assignee profile] [--ready]
# Or JSON handoff file
vibeos kanban from-delegation --from-json handoff.json --json
Then keep updating the ledger on the new task id with vibeos kanban ledger.
Pitfalls
- Do not dump the full parent transcript into children — put decisions and
constraints into the ledger /
delegate_taskcontext package. - Do not treat peer agent chat as the ledger — comments drift; structured fields do not.
- Leaves cannot write
memory; durable facts go to the ledger / Board KB / parent promotion paths. - Avoid change-detector “progress” (rewriting the same paragraph) — require artifacts or verified findings.
Verification
-
progress-ledger.md(or Kanban comment) exists with both ledger sections. - After a deliberate stall,
stall_countrises and a replan note appears. - Final status is
doneorblockedwith human-readable blockers. - Fleet / user can open the ledger file without reading raw agent logs.