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 spacedock-dev/spacedock --skill reviewgit clone --depth 1 https://github.com/spacedock-dev/spacedockWrote 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/spacedock-dev/spacedock/review)<a href="https://agentmods.dev/skills/spacedock-dev/spacedock/review"><img src="https://agentmods.dev/badge/skills/spacedock-dev/spacedock/review/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/spacedock-dev/spacedock/review"><img src="https://agentmods.dev/badge/skills/spacedock-dev/spacedock/review.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 | $0.00108 | $0.01610 |
| Opus 5.5 | $0.00043 | $0.00644 |
| Sonnet 5.5 | $0.00022 | $0.00322 |
| Haiku 4.5 | $0.00011 | $0.00161 |
Grade A, and why
review 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 — 142 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Review an artifact
Hand one artifact to a person for review. The project's recorded choice decides the view and where the file goes. Never upload anything that the project has not agreed to upload.
The two choices, worded as the view first, then where the file goes. Use these words whenever you show or ask for the choice:
Terminal (TUI): the file stays on this machine
Web: uploads to review.spacedock.md; anyone with the link can open it
The commands record Terminal (TUI) as local and Web as remote.
If spacedock review-mode is an unknown command, spacedock is too old for this
skill and has no update command. Tell the user to update it: brew upgrade spacedock
on Homebrew, or run the install line again. Stop.
Asking the user
Each question below is asked through the harness's question tool when it has one (Claude Code: AskUserQuestion; if its schema is not loaded, load it with ToolSearch first), as one menu with the options named. Where there is no such tool, ask in plain text with the same options. Wait for the answer; record only what the user chose, never your guess.
Pick the branch from the argument
Take the first branch that fits. Compare the reserved words as the whole argument, ignoring case.
- No argument: do Show or change the choice and nothing else.
tui,terminalorlocal: runspacedock review-mode set local, say that Terminal (TUI) is recorded for this project, and end with the sentence about changing it (Ask for the choice, step 4). Open and upload nothing.web,webuiorremote: do Ask for the choice from step 3. Open and upload nothing.- An argument that names an existing file (
test -f): do Review the file. - Any other text is a prompt: do Carry out the prompt, then review.
Ask for the choice
Used whenever a choice is needed.
- Ask "Terminal (TUI) or Web?" with two options, Terminal (TUI) and Web, each described by its line above. Say the answer is remembered for this project only.
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 · 142 lines · 108 tokens per session scan A 034ce19dde6b
review is a skill published in the GitHub repository spacedock-dev/spacedock (81 stars, last pushed yesterday), licensed Apache-2.0. It adds 108 tokens to every session and 1,610 once invoked, about $0.0004 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 2026-10-23.
Other skills, from other repositories
merge-review
Reviews pending fleet worktree merges before they're accepted. Reads the merge-check queue, detects file-level conflicts between branches, proposes a safe merge order, and surfaces reconciliation plans for overlapping changes.
workspace
Multi-repo campaign coordinator. Same lifecycle as fleet -- scope claims, discovery relay, wave-based execution -- but the unit of work is a repo, not a file. Coordinates campaigns across repositories with shared context.
decision-map
Turn a loose idea into a git-tracked, session-resumable map of typed investigation tickets, then drive them to resolution one at a time. The planning-loop engine for work that is still being figured out — too fuzzy for a campaign, too big for a single intake item. Resolved tickets graduate into .planning/intake/ for…
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-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.