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 skills add atman-33/workhub --skill task-chaingit clone --depth 1 https://github.com/atman-33/workhubWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/atman-33/workhub/task-chain)<a href="https://agentmods.dev/skills/atman-33/workhub/task-chain"><img src="https://agentmods.dev/badge/skills/atman-33/workhub/task-chain/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/atman-33/workhub/task-chain"><img src="https://agentmods.dev/badge/skills/atman-33/workhub/task-chain.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00062 | $0.01116 |
| Opus 5.5 | $0.00025 | $0.00446 |
| Sonnet 5.5 | $0.00012 | $0.00223 |
| Haiku 4.5 | $0.00006 | $0.00112 |
Grade A, and why
task-chain 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 27d 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.
How it starts
The opening of the file, as written. The whole thing — 85 lines — stays where its author put it; the contents beside it link to each section on GitHub.
task-chain — Run an ordered list of tasks
The list and its order are the owner's. To get advice on the order, or on what
can run in parallel, use task-orchestrate first.
This session is the orchestrator: it holds the order, the dependencies and
the owner's choices, and hands each task to a fresh subagent that runs
task-start through task-report. The orchestrator does no task work itself.
State lives in _ai/state/task-chain.json, kept by scripts/task-chain.mjs
(TC below = node <plugin>/scripts/task-chain.mjs, same vault resolution as
task-cli).
Steps
-
Preflight.
TC preflight <ids in order>returns per task its status,confirm, and each open predecessor labelledearlier(in the chain),lateroroutside. Fix everyproblemfirst — drop the task, reorder, or ask the owner to unblock it. A chain with a problem does not start. Done when no task reports a problem. -
Ask the owner once, up front. Put each choice with a recommendation and its reason (decision policy first). Never start a task before all four are answered:
depends_onon anearliertask: detach it for the run (recommended: the orchestrator already holds the order, and the original list is restored at the end) or stop the chain before that task. Never usetask-cli start --force: only the owner may allow it, and an agent passing it is refused.confirm: truetask: relay (recommended: a subagent drafts the plan, the owner approves it here), delegate (the orchestrator approves the plan against the task's## Description; for low-risk, easily reverted tasks the owner names), or stop before it.- Merging: whether each task's PR is merged before the next starts. Without it the chain stops after the first task that opens a PR.
- Limit: the number of tasks to run unattended (default 5).
-
Initialise.
TC init <ids> --max <n> [--merge] [--detach <ids>] [--delegate <ids>]. This detaches the chosendepends_onand records the originals.
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.
- 27d ago Changed · +3 lines 2636befc3986
- 29d ago First seen · 82 lines · 62 tokens per session scan A 1565180217ed
task-chain is a skill published in the GitHub repository atman-33/workhub (3 stars, last pushed yesterday), licensed MIT. It adds 62 tokens to every session and 1,116 once invoked, about $0.0002 per session on Opus 5.5. 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 2026-10-02.
Other skills, from other repositories
expo-launchpad-status
Show the current expo-launchpad pipeline state — phase, round, next role, pause reason — read-only.
tasknotes
This skill should be used when the user asks to 'create a task', 'add a TODO', 'plan a sprint', 'organize tasks', 'track time', 'setup Kanban', 'create task from code', 'sync tasks with sprint', 'pomodoro session', 'start pomodoro', 'time estimate', or mentions TaskNotes, task management, or project planning in…
project-consolidation
Safely consolidate drifted/duplicate project folders in the memex vault — cwd-fragment folders (e.g. Apps-arena, GitHub-loom), duplicate/split projects (one project's content scattered across two folders), and name-mismatch folders. Trigger on "consolidate project folders", "merge duplicate projects", "fix project…
issue-hygiene
How to write an issue somebody can act on, how to triage a pile of them, and the label vocabulary that stays useful. Use when filing, triaging, labelling, closing or linking issues.
aetox-slice
Decomposes a technical specification or plan into vertical tracer-bullet tickets. Calculates directed dependency graphs (DAG), schedules prefactoring first, applies expand-contract sequencing for wide refactors, quizzes the user on ticket granularity, and emits atomic per-ticket files sized for optimal agent context…
roadmap-update
Produit un document de roadmap dans output/ en croisant l'état actuel des epics beads avec les décisions et priorités documentées dans le wiki. Applique les règles anti-lissage — ne jamais compléter avec des connaissances d'entraînement, citer le wiki pour chaque affirmation de scope ou de priorité. Triggers — mettre…