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/present-gatenpx skills add spacedock-dev/spacedock --skill present-gategit 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 | $0.00044 | $0.00941 |
| Opus 5 | $0.00022 | $0.00470 |
| Sonnet 5 | $0.00009 | $0.00188 |
| Haiku 4.5 | $0.00004 | $0.00094 |
Grade A, and why
present-gate 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 — 44 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Present Gate
This skill carries the first-officer's captain-facing gate-presentation rendering: the gate-review format template and the assembly rules for filling it. The decide-to-gate and AC-cross-check policy stays always-on in the FO contract; this skill loads at the gate point to render the decision the FO has already made.
Presentation channels
Stable v1 permits chat or Subspace to present the committed gate. Both channels return semantic decision and reason input to the First Officer. After the prepared room and binding commit, render the gate template exactly once in the selected channel before the next decision-mutation tool call. The presentation must name the entity and stage, a compact bound Briefing snapshot, one recommendation, and the decision ask; exact headings are not required. A short digest prefix can identify the snapshot in prose; the canonical Briefing and recorder validation retain the exact full digest authority. Prior narration, child/tool output, or a later summary does not complete presentation. Delegated authority does not waive presentation. Only then hand the semantic decision and reason to ${SPACEDOCK_BIN:-spacedock} gate record <entity> --decision approve|revise|hold --actor ID [--reason TEXT].
A qualifying review is semantic: wording may vary while those five facts remain explicit. The presenter emits once; the lifecycle, prompt, and host adapter do not duplicate its review.
Subspace is a presentation interface, not a second recorder. It returns no Result or inventory for Spacedock to ingest and supplies no recorder authority or output paths. Provider-specific room-backed Result recording is explicitly outside v1; a failed or partial presentation never becomes an approval.
Gate Presentation
Present gate reviews in this format:
Gate review: {entity title} — {stage}
Recommend {approve | reject: {one-line reason}}.
Reviewed snapshot: {bound Briefing identity and compact digest prefix}
{Render `Evidence for {stage}:` with only the rows selected by Gate content or the bounded fallback. Omit the heading when no decision-relevant evidence exists.}
{If reviewer findings exist, render them under `Reviewer findings` in the active workflow's declared category order and exact labels. Preserve each recorded category and omit empty categories. If the workflow declares none, use one neutral `Findings:` list. If no reviewer ran, omit this whole block.}
Decision: {one-line decision prompt naming what approval/rejection does in concrete terms — e.g., "approve to enter implementation in worktree `.worktrees/...`" or "reject to bounce back to {feedback-to target} with the authorized findings above"}.
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 · 44 lines · 44 tokens per session scan A dd98858990e9
present-gate is a skill published in the GitHub repository spacedock-dev/spacedock (75 stars, last pushed 3d ago), licensed Apache-2.0. It adds 44 tokens to every session and 941 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 2026-08-30.
Other skills, from other repositories
fleet
Parallel campaign orchestrator. Runs multiple campaigns in coordinated waves within a single session. Spawns 2-3 agents per wave in isolated worktrees, collects discoveries, shares context between waves. Use when work decomposes into 3+ independent streams that can run simultaneously.
archon
Autonomous multi-session campaign agent. Decomposes large work into phases, delegates to sub-agents, reviews output, and maintains campaign state across context windows. Use for work that spans multiple sessions and needs persistent state, quality judgment, and strategic decomposition.
setup
First-run experience for the harness. Three modes: Recommended (guided, 3 min), Full Tour (guided + skill walkthrough, 8 min), and Express (zero questions, 30 sec). Installs hooks first, detects stack, configures harness.json, runs a live demo on real code, and prints a reference card.
daemon
Continuous autonomous operation mode. Keeps campaigns running 24/7 by chaining Claude Code sessions via RemoteTrigger. Each session picks up from the campaign's continuation state, works until context runs low or the phase completes, then schedules the next session. Auto-stops on campaign completion or budget…
dashboard
Real-time harness observability dashboard. Reads campaigns, fleet sessions, telemetry, and pending queues to present a snapshot of harness state at a glance. Invoked by /dashboard, /do status, or phrases like "what's happening" and "show activity".
evolve
Research-driven multi-cycle improvement director. Forms causal hypotheses about why scores are low, validates them with scout agents before attacking, dispatches axis-parallel fleet attacks, extracts transferable patterns, and runs indefinitely within a budget envelope. Accumulates a persistent belief model and…