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 atman-33/workhub --skill shared-spacegit clone --depth 1 https://github.com/atman-33/workhubWrote 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/atman-33/workhub/shared-space)<a href="https://agentmods.dev/skills/atman-33/workhub/shared-space"><img src="https://agentmods.dev/badge/skills/atman-33/workhub/shared-space.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 5.1 | $0.00090 | $0.01751 |
| Opus 5 | $0.00045 | $0.00875 |
| Sonnet 5 | $0.00018 | $0.00350 |
| Haiku 4.5 | $0.00009 | $0.00175 |
Grade A, and why
shared-space 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 yesterday.
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 — 158 lines — stays where its author put it; the contents beside it link to each section on GitHub.
shared-space — the team knowledge bases outside the vault
A vault project's notes are for the owner and their agents. A team keeps its own material somewhere else — a network drive, a Google Drive or SharePoint folder — organised by conventions nobody wrote down anywhere the vault can see.
This skill records those places against a project, and uses what it recorded to say where something belongs. It has two modes.
| Mode | What it does |
|---|---|
survey <project> <location> |
Read the place, work out how it is organised, and write projects/<slug>/shared/<name>.md |
place <note> |
Say where a vault note belongs in the project's shared spaces, and prepare the copy |
The app's Projects tab lists what shared/ holds and offers a prompt that
launches survey mode; nothing about these notes is written by the app itself.
What is worth recording
The rules, not the folder tree. Naming conventions, which kind of document goes where, who owns what, what the review or approval step is. A listing of every folder is stale within weeks and nobody reads it; keep the structure to the parts that orient a reader.
A place with no rules to record is just a link, and belongs in the project's
links.md instead. Do not create a shared-space note for one.
The note
projects/<slug>/shared/<name>.md. One file is one place; the folder is the
registry, so nothing lists these notes in _index.md. <name> is English
kebab-case, like every other folder name in the vault.
---
type: shared-space
title: Design team share
kind: network-drive # network-drive | google-drive | onedrive | sharepoint | other
location: //fileserver/design/projectX
access: mapped to Z:, needs VPN
direction: read-only # read-only | export-ok
surveyed: 2026-09-05
---
## Structure
- `01_仕様/` — specifications, one folder per release
- `02_議事録/` — meeting minutes, `YYYY-MM-DD_<topic>.md`
- `99_archive/` — anything superseded
## Rules
- A file name starts with the date in `YYYYMMDD` (stated: `運用ルール.md`)
- Specifications are Word, minutes are Markdown (inferred)
- The release folder is created by the PM, not by contributors (stated)
## Placement
- Task deliverables about the UI → `01_仕様/<release>/`
- Meeting notes → `02_議事録/`
## Memo
The owner's own notes. Neither the app nor this skill rewrites this section.
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.
- yesterday First seen · 158 lines · 90 tokens per session scan A 60068e449039
shared-space is a skill published in the GitHub repository atman-33/workhub (2 stars, last pushed 2d ago), licensed MIT. It adds 90 tokens to every session and 1,751 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 2026-09-06.
Other skills, from other repositories
gonavi-cli
Operate databases through the GoNavi headless CLI — the gonavi executable shipped in verified GitHub Release archives. Covers listing/adding/importing saved connections, running SQL queries against saved connections or ad-hoc connection files, exporting result sets to csv/json/md/html/xlsx, batch-executing SQL files…
shipyard-executing-plans
Use when you have a written implementation plan to execute, either in the current session with builder/reviewer agents or in a separate session with review checkpoints. Also use when the user says "build this", "implement this", "execute the plan", "run the plan", or when a plan file has been loaded with independent…
shipyard-writing-plans
Use when you have a spec, requirements, or design for a multi-step task — before touching code. Also triggers on "plan this", "break this down", "create tasks", "decompose this feature", or when a task clearly needs more than 2-3 steps to implement. If you're about to start building without a plan, or writing vague…
shipyard-handoff
Captures session context into .shipyard/HANDOFF.md so the next session can resume without losing progress.
tasks
A task-breakdown tool that turns a plan, specification, feature brief, bug report, technical-debt item, or chore into small TASK-NNN work items. Technical debt means postponed cleanup or design work in a codebase.
roadmap
An implementation plan made from a technical specification, organized into phases, milestones, and dependencies.