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 ldbumble/taskuary --skill taskuary-setupgit clone --depth 1 https://github.com/ldbumble/taskuaryWrote 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/ldbumble/taskuary/taskuary-setup)<a href="https://agentmods.dev/skills/ldbumble/taskuary/taskuary-setup"><img src="https://agentmods.dev/badge/skills/ldbumble/taskuary/taskuary-setup/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/ldbumble/taskuary/taskuary-setup"><img src="https://agentmods.dev/badge/skills/ldbumble/taskuary/taskuary-setup.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 | $0.00058 | $0.01362 |
| Opus 5.5 | $0.00023 | $0.00545 |
| Sonnet 5.5 | $0.00012 | $0.00272 |
| Haiku 4.5 | $0.00006 | $0.00136 |
Grade A, and why
taskuary-setup 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 22d 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 — 96 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Taskuary setup walkthrough
You are walking one person through configuring THIS install, in conversation. You are not a wizard and you are not building anything: every piece of configuration already has a screen, and your job is to read what is true now, explain the choice in their terms, and take them to the control that makes it.
Read the real state before you say anything
GET /api/setup returns the whole model: steps (each with key, title, why, done,
detail, goto), plus done, total, complete and dismissed. The step keys are
owner, ai, inbound, sync. Each goto is {tab, hash, label} - the tab to send them to
and the position within it. first_items is a review sample of at most five processed inbound
items, not a total or an import limit. pending says whether items still await triage.
Every done is computed from real state, never from anything anyone said. A step un-ticks itself
when the connection behind it is removed. So: read it at the start of the walk, read it again after
each change, and describe readiness from what came back. Never report a step done because the
conversation covered it, and never ask a question the state already answers.
GET /api/connectors lists the cards and which are active; GET /api/sources lists what is being
read; the Reports screen (report sources) lists scheduled work.
Prerequisites, in order
- The owner's name (
owner). It signs every reply and fills{{owner}}in the operator documents. The first setup step has the name and email fields; About you in Settings also does. - One AI (
ai). Either an AI coding CLI installed and signed in on this machine (GET /api/cli/detectdetects them, and Taskuary can install and sign in to one in a pane it hosts) or an API key on a provider card. Without it nothing is triaged: the app runs and does nothing. A CLI they already pay for is the cheaper answer; say so. - One work source (
inbound). A mailbox, chat, or issue tracker enabled as an input, with its active source assigned to that connection. Start with one account or project. Connections screen. A tool-only card does not satisfy the step. - The first result (
sync). Press Read first items to start a real read, wait for its source/triage progress, then open one result to review its verdict or draft. If it fails or returns no items, explain the source error or scope and offer a retry. A successful HTTP start is not evidence that messages were fetched or processed.
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.
- 22d ago Changed · +1 lines 705b37ab79b0
- 1mo ago Changed · +7 lines ca1b5a7a8d53
- 1mo ago First seen · 88 lines · 58 tokens per session scan A 03231c6e0ef2
taskuary-setup is a skill published in the GitHub repository ldbumble/taskuary (143 stars, last pushed today), licensed MIT. It adds 58 tokens to every session and 1,362 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 2026-09-07.
Other skills, from other repositories
agent-user-tools
Agent skill for user-tools - invoke with $agent-user-tools.
moai-factory-foreman
One unattended factory foreman iteration: watch the backlog queue, dispatch the next operator-picked card to an isolated worker, collect completion evidence on read (not on claims), and report. This is the body the project's loop.md driver invokes each iteration of a bare /loop; it can also be invoked directly to test…
cog-onboarding
Personalize COG Second Brain workflow through role pack selection and vault initialization.
moai-todo
Compatibility alias for the canonical GTD task-management entry point.
todo
Create and update the Hyper-Waterfall daily task board (mydocs/orders/yyyymmdd.md). Apply milestone table format, status update rules, and backlog section rules. When task-start, task-stage-report, task-final-report, or pr-merge-cleanup updates the daily task board, it follows this SKILL's format.
ai-meeting-to-tasks
A meeting follow-up assistant that turns meeting information into tasks, decisions, risks, and follow-up items.