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/luisalima/agent-policy-kit/opentasksnpx skills add luisalima/agent-policy-kit --skill opentasksgit clone --depth 1 https://github.com/luisalima/agent-policy-kitWrote 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/luisalima/agent-policy-kit/opentasks)<a href="https://agentmods.dev/skills/luisalima/agent-policy-kit/opentasks"><img src="https://agentmods.dev/badge/skills/luisalima/agent-policy-kit/opentasks.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 | $0.00048 | $0.04311 |
| Opus 5 | $0.00024 | $0.02155 |
| Sonnet 5 | $0.00010 | $0.00862 |
| Haiku 4.5 | $0.00005 | $0.00431 |
Grade A, and why
opentasks 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 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.
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 — 349 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/opentasks — docs/tasks/ convention manager
You are managing a lightweight repo convention in docs/tasks/, not an external task manager. The argument you received is:
$ARGUMENTS
Parse the intent and execute the appropriate operation below. If the argument is empty or ambiguous, run status.
Accept common aliases:
init→bootstrapcreate task,add task,task→new taskopen question,add question,question→new questionclose,finish,complete,mark done→done
Where an operation accepts <item>, resolve it before editing:
- Exact filename under
docs/tasks/, with optional.md. - Exact slug, meaning filename without
.md. - Task shorthand
T<N>/t<N>→ the unique task withid: T<N>ort<N>-*.mdfilename. - Question shorthand
Q<N>/q<N>→ the uniqueq<N>-*.mdfile. - Exact case-insensitive title match from the file heading or index line.
If resolution finds no item, stop and tell the user what was searched. If it finds multiple items, stop and ask for the exact slug.
Folder guard
Before executing any operation other than bootstrap / init, check whether docs/tasks/ exists. If it does not, stop and tell the user:
No
docs/tasks/folder found. Run/opentasks bootstrapto set up the system first.
Task sizing and agent behavior
A task should be small enough for one focused agent session or one coherent PR. Good tasks have one objective, concrete Done when criteria, independent verification, and no unresolved design choice hidden inside the scope.
Split a task when it has multiple outputs, multiple owners, unresolved decisions, or a title that naturally contains "and then." Do not create tasks for every tiny edit. Create them when work needs to survive chat context, coordinate across humans or agents, or show up in git history.
Agents should create tasks when breaking down a user-approved plan, discovering follow-up work that should not be done immediately, finding a blocker or dependency, extracting implementation work from an ADR, or leaving continuation work for another human or agent. Agents should not create tasks merely to describe work they are already completing in the same turn.
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 · 349 lines · 48 tokens per session scan A fec48b2f9a38
opentasks is a skill published in the GitHub repository luisalima/agent-policy-kit (2 stars, last pushed 2mo ago), licensed MIT. It adds 48 tokens to every session and 4,311 once invoked, about $0.0002 per session on Opus 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 2026-08-31.
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…