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.
npx agentmods add commands/varienos/agentic-workflow/task-plan.skeletongit clone --depth 1 https://github.com/varienos/agentic-workflowWhat 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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00000 | $0.05419 |
| Opus 5 | $0.00000 | $0.02710 |
| Sonnet 5 | $0.00000 | $0.01084 |
| Haiku 4.5 | $0.00000 | $0.00542 |
Grade C, and why
task-plan.skeleton scanned grade C with 1 finding 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.
Hidden instructionshighPrompt injection
Directives inside HTML comments, invisible characters or bidirectional overrides are read by the model and not by the person reviewing the file.
<!-- GENERATE: AC_TEMPLATES Aciklama: Bu bolum Bootstrap tarafindan manifest verileriyle doldurulur. Gerekli manifest alanlari: stack.primary, project.conventions, project.subprojects Ornek cikti: **Stack-Spesifik AC Orn How it starts
The opening of the file, as written. The whole thing — 448 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Task Plan — Yuksek Baglamli Gorev Olusturucu
Codebase'i derinlemesine analiz ederek kaliteli, uygulanabilir gorev olusturur. Kullanim:
/task-plan <istek>,/task-plan "login sayfasina remember me ekle"
ULTRATHINK MODE — Bu komut maksimum dusunme derinligi ile calisir.
- ACELE ETME. Her adimda once dusun, sonra hareket et.
- Yuzeysel analiz YASAK. Varsayimlarini sorgula, alternatiflerini degerlendir.
- Bir sey "bariz" gorunuyorsa, neden bariz oldugunu kanitla.
- Ilk aklina gelen cozum muhtemelen eksik — en az 3 alternatif dusun.
- Bu komut OPUS modeli ile calistirilmalidir. Sonnet ile task-plan calistirmak YASAKTIR.
Step 0 — Ultrathink: Derin Dusunme Fazi
Bu faz ZORUNLUDUR. Atlanamaz. Ciktisi kullaniciya gosterilmez ama tum sonraki adimlari yonlendirir.
Codebase'e dokunmadan ONCE, sadece dusun:
0.1 — Hipotez Uretimi
Istegin en az 3 farkli yorumunu uret:
- Hipotez A: En bariz yorum — kullanici buyuk ihtimalle bunu kastetmistir
- Hipotez B: Alternatif yorum — belki farkli bir aci var
- Hipotez C: En az bariz ama olasi yorum — gozden kacabilecek perspektif
Her hipotez icin: "Bu dogruysa ne yapilmali?" sorusunu cevapla.
0.2 — Varsayim Sorgulamasi
Her hipotezdeki gizli varsayimlari cikar ve sorgula:
- Hangi dosyalarin var oldugunu varsayiyorsun? (henuz dogrulamadin)
- Hangi pattern'lerin kullanildigini varsayiyorsun? (henuz okumadin)
- Kullanicinin gercekten ne istedigini varsayiyorsun? (kendi yorumun mu?)
- Kapsamin ne oldugunu varsayiyorsun? (belirtilmemis sinirlari eklemedin mi?)
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.
- 2d ago First seen · 448 lines · 0 tokens per session scan C b77e0387b36e
task-plan.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 5,419 tokens. A static security scan graded it C with 1 finding (hidden instructions). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other commands, from other repositories
status
Show current Craft progress — cycles, stories, backlog in a rich dashboard view.
story-archive
Move a story from a cycle back to the backlog.
project
Manage projects inside a topic wiki. Projects are folders under output/projects/ that group related outputs (playbooks, images, code, data) with a goal captured in WHY.md.
luda
Invoke Luda, your Scrum Master, for board integrity — orphan work items, plan-vs-tracker divergence, Done-without-negative-criteria, parked-without-a-trigger — plus ticket creation and team orchestration.
design-sprint
Orchestrate design-to-implementation workflow for a sprint or feature. Coordinates /ui (Aura) and /fe (Finn).
ledger-plan
Generate implementation plan with backlog, milestones, and test plan constrained by decisions and risks.