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 sliamh11/Deus --skill linear-slicegit clone --depth 1 https://github.com/sliamh11/DeusWrote 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/sliamh11/deus/linear-slice)<a href="https://agentmods.dev/skills/sliamh11/deus/linear-slice"><img src="https://agentmods.dev/badge/skills/sliamh11/deus/linear-slice.svg" alt="Measured on agentmods" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00031 | $0.01849 |
| Opus 5 | $0.00015 | $0.00924 |
| Sonnet 5 | $0.00006 | $0.00370 |
| Haiku 4.5 | $0.00003 | $0.00185 |
Grade A, and why
linear-slice 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 — 153 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/linear-slice
Turn a plan or PRD into a set of thin, vertical, independently-shippable slices, each created as a Linear issue in dependency order, then released into Deus's autonomous dispatch pipeline.
This is the missing front-end to the Linear pipeline: the webhook gates (enrichment-gate →
bouncer-gate → dispatcher) describe how an issue flows through the board, but not how a good,
independently-grabbable issue gets created. This skill creates them.
Creating issues is a deliberate action with real side effects. Always preview and get explicit approval before creating anything.
How the pipeline works (the contract you must honor)
The board is Backlog → Todo → Ready for Agent → Agent Working → In Review → Done. Gates fire on
transitions into a state, never on issue creation:
- Backlog → Todo fires the enrichment gate, a mutating controller that writes the scope
block into the issue description itself (wrapped in
<!-- gate:enrichment-gate:start -->…<!-- gate:enrichment-gate:end -->). - Todo → Ready for Agent fires the bouncer gate, which validates that scope block.
- The dispatcher then picks up
Ready for Agentissues autonomously.
Consequences for this skill:
- Create issues in Backlog. A freshly created issue fires no gate, so it sits inert until moved.
- Never pre-write the enrichment scope block. It is gate-owned. Write a normal human
description; the enrichment gate generates the
## Scopeblock on the Backlog→Todo transition. - Never apply a
Scopedlabel. The dispatcher matchesScoped; applying it to a non-enriched issue would make the dispatcher pick up unscoped work. The gate manages that label. - Releasing = moving Backlog → Todo. That is how you start the pipeline on a slice.
Steps
1. Get the plan
Take the plan from one of, in priority order:
- An explicit argument (a file path, or pasted text).
- The current conversation (a plan just drafted/approved here).
- A parent Linear issue (
mcp__linear__linear_getIssueById) whose body is the plan to decompose.
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 · 153 lines · 31 tokens per session scan A bc4d9b813261
linear-slice is a skill published in the GitHub repository sliamh11/Deus (51 stars, last pushed 2d ago), licensed MIT. It adds 31 tokens to every session and 1,849 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 2026-09-03.
Other skills, from other repositories
roadmap-build
Build or repair a roadmap that agents can actually execute, not just read. Produces a single validated YAML source of truth, generated views, definitions of done with evidence kinds, a task pool linked on two axes, an idea intake queue, and three standing checks that keep it honest. Use when asked to "build a…
GTD for Datacore
Getting Things Done — task capture, inbox processing, and org-mode management.
Outbox for Datacore
Content routing — archive to server, search archived content.
todoist
Manage Todoist tasks, projects, and labels via official CLI.
asana
Manage Asana tasks, projects, and workspaces via MCP.
add-linear
Add Linear channel integration via Chat SDK. Issue comment threads as conversations.