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 Abilityai/abilities --skill project-taskgit clone --depth 1 https://github.com/Abilityai/abilitiesWrote 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/abilityai/abilities/project-task)<a href="https://agentmods.dev/skills/abilityai/abilities/project-task"><img src="https://agentmods.dev/badge/skills/abilityai/abilities/project-task/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/abilityai/abilities/project-task"><img src="https://agentmods.dev/badge/skills/abilityai/abilities/project-task.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 | $0.00113 | $0.05252 |
| Opus 5.5 | $0.00045 | $0.02101 |
| Sonnet 5.5 | $0.00023 | $0.01050 |
| Haiku 4.5 | $0.00011 | $0.00525 |
Grade A, and why
project-task 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 6d 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 — 292 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Project Task
ℹ️ First, set expectations: before anything else, print one short line with this skill's version and its most recent change — e.g.
project-task v1.7.1 — recent: arguments no longer break the config resolver. Then proceed.
Purpose
Create a task in the uniform format — a GitHub task issue (external project) or a task file in the project's workspace (internal project, standard §16). This is the only sanctioned way to create tasks in a managed project — it enforces the full anatomy including the ## Validation section (the approval chain), applies the correct labels, and links the task into the parent epic's checklist.
Never create task issues directly via gh issue create outside this skill. The anatomy enforcement and epic linkage are the point.
Workspace path (standard §15 — read, never derived)
This skill writes GitHub, not workspaces. If a caller hands it — or it hands a caller — a workspace path, that path is the epic body's ## Workspace field resolved through the standard's §15 resolver (canon:projects/<slug>/ → through the x-canon clone; anything else → repo-relative; missing → no workspace), never project_files/<slug>/ derived from the slug. A shared project (ruling R21) sits in the canon and is otherwise identical: same epic, same task anatomy, same intake path.
Modes
Interactive mode (default): run as /project-task [project-slug]. Collects missing fields via AskUserQuestion. For human use.
Headless mode: run with --headless and all fields as arguments. Never calls AskUserQuestion. Returns just the created task reference on stdout (#NN, or <slug>/T-NNN for an internal project). For use by /project-intake, crons, and other skills that compose task creation programmatically.
Headless arguments:
| Argument | Required | Notes |
|---|---|---|
--project=<slug> |
yes | Project slug from project:<slug> label |
--title="..." |
yes | Plain imperative title |
--objective="..." |
yes | What this task accomplishes |
--dod="item1|item2" |
yes | Pipe-separated DoD items |
--owner=<actor> |
yes | Accountable party |
--priority=pN |
no | Default: inherit from epic |
--agent=<name> |
no | Executing agent label (if immediately assignable) |
--waiting-on=<actor> |
no | Parks the task as an open loop on an actor outside the registry — applies waiting-on:<actor> and posts the ### Waiting on comment (standard §14b) |
--context="..." |
no | Additional context beyond the epic link |
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.
- 6d ago Changed · +1 lines 1dd49d0f3bbe
- 7d ago Changed · +37 lines f737017f5073
- 9d ago Changed · +18 lines · +23 tokens per session ffd73146a5b5
- 11d ago Changed · +56 lines · +23 tokens per session 6ed12bd1637f
- 1mo ago First seen · 180 lines · 67 tokens per session scan A 7ade0fc5e7f4
project-task is a skill published in the GitHub repository Abilityai/abilities (12 stars, last pushed 3d ago), licensed MIT. It adds 113 tokens to every session and 5,252 once invoked, about $0.0005 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
story-readiness
Is a story implementation-ready? Checks clear acceptance criteria, open questions, ADR refs. READY/NEEDS WORK/BLOCKED/NOT ASSESSED.
recipe-create-meet-space
Create a Google Meet meeting space and share the join link.
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…
atmos-config
Atmos root configuration: atmos.yaml discovery, precedence, deep merging, basepath, imports, minimal bootstrap, and routing to narrower Atmos skills.
projects
List all managed projects with status, branch, open PRs, and open issue counts — portfolio-level view.
handle-linkedin-connection-request-signal
Use this skill when someone sends a team member an inbound LinkedIn connection request. An inbound request is a deliberate, ACTIVE first-party intent signal — meaningfully stronger than a passive profile view — and it deserves different scoring rules. The skill resolves and enriches the requester, gates them through…