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 skills/lirrensi/agent-sommelier/task-systemnpx skills add lirrensi/agent-sommelier --skill task-systemgit clone --depth 1 https://github.com/lirrensi/agent-sommelierWrote 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/lirrensi/agent-sommelier/task-system)<a href="https://agentmods.dev/skills/lirrensi/agent-sommelier/task-system"><img src="https://agentmods.dev/badge/skills/lirrensi/agent-sommelier/task-system.svg" alt="Measured on agentmods" 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 | $0.00173 | $0.02714 |
| Opus 5 | $0.00086 | $0.01357 |
| Sonnet 5 | $0.00035 | $0.00543 |
| Haiku 4.5 | $0.00017 | $0.00271 |
Grade A, and why
task-system scanned grade A 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 4d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
tasks add "Update README with API examples" --source inbox --priority low --tag docs --notes "Add curl examples for all 5 endpoints" How it starts
The opening of the file, as written. The whole thing — 277 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Task System
A lightweight, static, file-based task management system embedded in the repository. Tasks are permanent history — once created, never deleted. No database, no server, no internet.
This is separate from runtime/ephemeral task tools. Those disappear when the session ends. This task system lives in the repo. Its tasks are kept forever.
Core Philosophy
- Static, file-based, in-repo — Three files in
.agents/tasks/:inbox.md,tasks.yaml,closed.yaml. No database, no service, no setup beyondtasks init. - Tasks are permanent history — Nothing is ever deleted. Tasks flow from
tasks.yaml(active) toclosed.yaml(archive). - 12 statuses, any lifecycle —
todo,in-progress,done,blocked,postponed,cancelled,review,waiting,parked,deferred,backlog,abandoned. Move freely between them. - Counter-based IDs — Tasks get
TSK-NNNNIDs (e.g.TSK-0001). Auto-incrementing. - Numeric priorities (p0-p4) —
p0(critical) >p4(backlog). Named aliases also work. - Dependency system — Typed deps (
blocks,parent,child,discovered,relates).blocksaffects the ready queue. - Newest-first ordering in active list, oldest-first in archive.
⚠️ Golden Rule: YAML files are CLI-only. Inbox.md is free-form.
| File | Who edits it | How |
|---|---|---|
tasks.yaml |
Never by hand | CLI only (tasks add, tasks update, tasks close) |
closed.yaml |
Never by hand | CLI only (tasks close appends automatically) |
inbox.md |
Anyone, any time | Free-form text — humans dump ideas, agents paste notes, raw scraps live here |
File Layout
<project-root>/
.agents/tasks/
inbox.md # Raw dump zone — paste ideas, notes, scraps here
tasks.yaml # Active task list (any status, closed=false)
closed.yaml # Closed task archive (append-only, permanent)
All files are self-documenting — open any YAML file and the header explains the system.
What ships with it
2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 4d ago First seen · 277 lines · 173 tokens per session scan A bc8fc83c7ad9
task-system is a skill published in the GitHub repository lirrensi/agent-sommelier (5 stars, last pushed 1mo ago), licensed MIT. It adds 173 tokens to every session and 2,714 once invoked, about $0.0009 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
agile-product-owner
../../../product-team/agile-product-owner/skills/agile-product-owner/SKILL.md.
workthreads
SpecStory Workthreads - a weekly work-thread rollup across a team's repos from SpecStory coding histories (any agent - Claude Code, Codex, Cursor, Gemini, and more). It groups the window's sessions into threads of work per project and labels each new / open / recently closed, so a lead sees what shipped, what is still…
story-readiness
Validate that a story file is implementation-ready. Checks for embedded GDD requirements, ADR references, engine notes, clear acceptance criteria, and no open design questions. Produces READY / NEEDS WORK / BLOCKED verdict with specific gaps. Use when user says 'is this story ready', 'can I start on this story', 'is…
subagent-delegation
Canonical protocol for delegating GSD work to native Antigravity subagents — when to delegate, how to invoke, workspace isolation modes, and the inline fallback for older IDE versions.
projects
List all managed projects with status, branch, open PRs, and open issue counts — portfolio-level view.
project-init
Scaffold an unconfigured directory into a configured pi project. Interactive, profile-driven: previews the planned writes, then writes AGENTS.md, .pi/settings.json and prompt files — optionally also a knowledge base, an openspec/ scaffold, and user-global /.pi/agent/settings.json. Use on a bare directory, or when the…