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/colliery-io/metis/document-selectionnpx skills add colliery-io/metis --skill document-selectiongit clone --depth 1 https://github.com/colliery-io/metisWhat 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 | $0.00092 | $0.01232 |
| Opus 5 | $0.00046 | $0.00616 |
| Sonnet 5 | $0.00018 | $0.00246 |
| Haiku 4.5 | $0.00009 | $0.00123 |
Grade A, and why
document-selection 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 2d 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.
The source is not reproduced here
No licence file
A repository with no LICENSE is all rights reserved by default, so the body is not copied here. The metadata, the measurements and the link are.
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.
- 2d ago First seen · 143 lines · 92 tokens per session scan A 91de1b99e285
document-selection is a skill published in the GitHub repository colliery-io/metis (13 stars, last pushed 2mo ago), with no licence file. It adds 92 tokens to every session and 1,232 once invoked, about $0.0005 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 2026-08-30.
Other skills, from other repositories
collattice
Operate a Collattice kanban board through its Model Context Protocol (MCP) endpoint — connecting, authentication, the board model, identifier rules (board-level reads need a board GUID, not a slug), the Markdown a board renders, and the full tool reference: reading and creating cards, moving and reordering lanes…
tracker
Use when working with team tasks in the Vikunja tracker via the "tracker" MCP tools (nexttask/claim/advance/...) — queue discipline, stage gates, when to callhuman vs returntask.
aspire
Orchestrates Aspire distributed applications using the Aspire CLI for running, debugging, and managing distributed apps. USE FOR: aspire start, aspire stop, start aspire app, aspire describe, list aspire integrations, debug aspire issues, view aspire logs, add aspire resource, aspire dashboard, update aspire apphost.…
kanban-tui
Comprehensive kanban board and task management via ktui CLI. Use for project tracking, todo lists, task dependencies, workflow automation, and board management. Activates when user mentions boards, tasks, kanban, or project management. If the ktui command is not available, but uv is available utilize uvx kanban-tui…
codekanban-cli
Operate CodeKanban workflows, terminal sessions, and web sessions through the installable codekanban-cli command. Use when the user wants to create, inspect, control, watch, or continue CodeKanban AI work from a project path, project ID, or project name without relying on repository-local helper scripts. Prefer…
review-checklist
Creates a local checklist for code review notes provided in the current task.