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/spacedock-dev/spacedock/refitnpx skills add spacedock-dev/spacedock --skill refitgit clone --depth 1 https://github.com/spacedock-dev/spacedockWhat 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 | $0.00052 | $0.03081 |
| Opus 5 | $0.00026 | $0.01541 |
| Sonnet 5 | $0.00010 | $0.00616 |
| Haiku 4.5 | $0.00005 | $0.00308 |
Grade A, and why
refit 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.
How it starts
The opening of the file, as written. The whole thing — 262 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Refit a Workflow
You are refitting (upgrading) an existing workflow to match the current Spacedock version. This covers scaffolding files (README, mods) and, when schema changes require it, migrating entity frontmatter data. Agent files and the status viewer are shipped with the Spacedock plugin and do not need local updates.
Follow these five phases in order. Do not skip or combine phases.
Phase 1: Discovery
Step 1 — Identify the workflow
The user must provide a workflow directory path. If they didn't, ask:
Which workflow directory should I refit?
Store the confirmed path as {dir}. Resolve it to an absolute path. Also derive {project_root} (git root or cwd) and {dir_basename} (last path component).
Step 2 — Read current scaffolding and extract version stamps
Read each scaffolding file and extract its version stamp:
- README — Read
{dir}/README.md. Extract version from YAML frontmattercommissioned-by: [email protected]. Store as{readme_version}. - Mod files — Scan
{dir}/_mods/*.mdfor installed mods. For each, read theversionfrontmatter field. Match against canonical mods at{project_root}/mods/{name}.mdby filename. Store the local version and canonical version for each. Also scan{project_root}/mods/*.mdfor mods not yet installed. - Legacy status script — If
{dir}/statusexists, note it for cleanup (status now ships with the plugin).
If a file doesn't exist, note it as missing and skip it.
Step 3 — Read current Spacedock version
Read .codex-plugin/plugin.json from the Spacedock plugin directory (the directory containing the skills/ folder — resolve from your own plugin context). The .claude-plugin/plugin.json mirror carries the same version for the Claude host. Extract the version field and store it as {current_version}.
Step 4 — Evaluate
- If all version stamps match
{current_version}: report "Workflow is already up to date." and stop. - If no stamps were found on any versioned file (README): enter Degraded Mode (see below).
- Otherwise: proceed to Phase 2 with the list of outdated files.
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 · 262 lines · 52 tokens per session scan A 3ba970e1ef92
refit is a skill published in the GitHub repository spacedock-dev/spacedock (75 stars, last pushed 3d ago), licensed Apache-2.0. It adds 52 tokens to every session and 3,081 once invoked, about $0.0003 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
prd
Generates a Product Requirements Document from a natural language app description. Asks clarifying questions, researches similar apps, defines scope, stack, architecture, and produces a structured PRD that Archon can decompose into a campaign.
unharness
Safely leave Citadel using the active adoption receipt. Produces a no-write, reviewable plan, preserves a portable archive, removes only exact owned material, and reports modified or externally registered surfaces as retained or unknown. Legacy installs must be imported before exact leave is claimed.
duneboard-init-project
Bootstrap DuneBoard in a local repository. Use when adding a DuneBoard board to a project, initializing tasks/, installing agent guidance, registering the project in the local DuneBoard UI selector, or making a project self-describing for future agents.
duneboard-agent
Work with DuneBoard task files in a repository. Use when Codex needs to plan, take, create, update, block, release, or close DuneBoard work; run pnpm dune; or preserve DuneBoard Markdown task history.
duneboard-organize-local-project
Organize an existing local project into DuneBoard tasks and specs. Use when the user asks to clean up local todo notes, scattered Markdown specs, issue notes, backlog files, roadmap docs, or agent-written plans into a simple DuneBoard board without unnecessary process.
duneboard-import-ado
Convert Azure DevOps backlog or work item data into DuneBoard Markdown tasks. Use when the user asks to migrate, import, mirror, or decompose ADO Epics, Features, User Stories, Bugs, Tasks, links, acceptance criteria, comments, or exported WIQL/CSV/JSON into DuneBoard.