task-conductor.skeleton

A plan-first tool for turning several backlog tasks into ordered phases. A backlog is a list of unfinished work; the tool only makes changes when you explicitly choose run mode.

In plain words
What is it for?
Use it to select the highest-priority tasks, filter tasks by keyword or number, create an execution plan, run approved work, check progress, resume, or abort.
Why use it?
It prevents accidental code or task-status changes while planning. It also controls parallel work and can continue an interrupted run from saved state.

Command

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add commands/varienos/agentic-workflow/task-conductor.skeleton
Clone the repo
git clone --depth 1 https://github.com/varienos/agentic-workflow
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 6,404 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5 $0.00000 $0.06404
Opus 5 $0.00000 $0.03202
Sonnet 5 $0.00000 $0.01281
Haiku 4.5 $0.00000 $0.00640

Measured 2d ago against content hash 9ebfc7956e1a, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

task-conductor.skeleton scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

Agentbase/templates/core/commands/task-conductor.skeleton.md · 577 lines

How it starts

The opening of the file, as written. The whole thing — 577 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Task Conductor — Plan-First Faz Orkestratoru

Backlog'daki birden fazla gorevi once faz planina donusturur; yalnizca acik run modunda uygular. Kullanim: /task-conductor plan top 5, /task-conductor run top 5 --max-parallel 2, /task-conductor resume, /task-conductor status, /task-conductor abort


Temel Sozlesme

  1. Varsayilan mod PLAN'dir. Kullanici run yazmadikca kod, backlog status'u, state veya git degisikligi yapma.
  2. run acik niyet ister. Eski kullanimlar (top 5, 3,5,8, keyword auth) geriye uyumluluk icin plan ... gibi yorumlanir.
  3. run all sadece --confirm-all ile calisir. Tum acik backlog'u otonom calistirmak yuksek risklidir; bayrak yoksa plan uret ve dur.
  4. Paralel yazim sadece izole worktree/branch ile yapilir. Izolasyon yoksa veya dogrulanamiyorsa ayni fazdaki gorevleri sirayla isle.
  5. Puanlama sozlesmesi /task-master ile aynidir. Formul veya agirliklar degisecekse iki komut birlikte guncellenir.
  6. Resume sadece conductor state'inden devam eder. State yoksa veya schema uyumsuzsa yeni run baslatma; kullaniciya rapor ver.

Mod Cozumleme

Komut Ornek Davranis
Plan Top X plan top 5 En yuksek puanli X gorev icin faz/catisma plani uret, dur
Plan All plan all Tum acik gorevleri planla, run yapma
Plan Manuel ID plan 3,5,8 Belirtilen gorevler icin plan uret
Plan Keyword plan keyword auth Anahtar kelimeyle eslesen gorevleri planla
Run Top X run top 5 --max-parallel 2 Planla, on kontrolleri yap, uygun fazlari uygula
Run All run all --confirm-all Tum acik gorevleri yalnizca acik onay bayragiyla uygula
Run Manuel ID run 3,5,8 Belirtilen gorevleri faz planina gore uygula
Run Keyword run keyword auth Eslesen gorevleri faz planina gore uygula
Resume resume conductor-state.json dosyasindan kaldigi yerden devam et
Status status State ve lock dosyalarindan mevcut durumu oku, hicbir sey degistirme
Abort abort Aktif state'i aborted isaretle, lock'u kaldir, kod degistirme

Read the full file on GitHub · 577 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 2d ago First seen · 577 lines · 0 tokens per session scan A 9ebfc7956e1a

Subscribe to this mod's changes

task-conductor.skeleton is a command published in the GitHub repository varienos/agentic-workflow (58 stars, last pushed 2mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 6,404 tokens. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.