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/fo-gate-lifecyclenpx skills add spacedock-dev/spacedock --skill fo-gate-lifecyclegit 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/fo-gate-lifecycle)<a href="https://agentmods.dev/skills/spacedock-dev/spacedock/fo-gate-lifecycle"><img src="https://agentmods.dev/badge/skills/spacedock-dev/spacedock/fo-gate-lifecycle.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 | $0.00012 | $0.01794 |
| Opus 5 | $0.00006 | $0.00897 |
| Sonnet 5 | $0.00002 | $0.00359 |
| Haiku 4.5 | $0.00001 | $0.00179 |
Grade A, and why
fo-gate-lifecycle 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 3d 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 — 77 lines — stays where its author put it; the contents beside it link to each section on GitHub.
First Officer Gate Lifecycle
«gate.lifecycle»(slug, stage): bind, decide, apply one recorded authorization
Load before engaged gate action. It grants no writes; read fo-write-core.md before FO mutation.
The binary owns preparation, withdrawal, recording, and one-use consume; this skill only routes their observed results.
Boot. status --boot --identify --json ready_gates gives definition_dir, entity_dir, slug/stage/readiness. Engage slug via status --read <slug> --json, never search. needs-preparation: review report, or at an initial: true stage the committed seed itself; awaiting-captain: open; withdrawn-awaiting-prepare: successor; approved: unblocked; malformed/ambiguous: fail closed.
Prepare. Resolve ${SPACEDOCK_BIN:-spacedock}; keep paths. For each retained absolute R (definition_dir, entity_dir), derive relative P; state R is the engaged task directory, never .. Run git -C "<R>" ls-tree -r --name-only HEAD -- "<P>" | awk 'tolower($0)~/\.(md|markdown)$/{print}', quoted. Read once; summarize. No logs/history/status/help probes. Supply absolute, launch-cwd-relative, or state-relative judgment paths; use absolute before the one prepare if a spelling names different cwd/state paths. No binary JSON/IDs/digests/Git locators/room coordinates.
Run this sequence once and in this order:
1. ${SPACEDOCK_BIN:-spacedock} gate prepare ENTITY --question QUESTION --artifact REVIEW --summary SUMMARY [--reference FILE ...] --workflow-dir WORKFLOW_DIR
2. ${SPACEDOCK_BIN:-spacedock} state commit ENTITY --workflow-dir WORKFLOW_DIR
3. In one shell event, run `${SPACEDOCK_BIN:-spacedock} status --read ENTITY --checklist --json --workflow-dir WORKFLOW_DIR` and the same command with `--ac-scan` instead of `--checklist`.
4. Load spacedock:present-gate and present once from that structured evidence.
Initial-stage gate. At a stage the workflow marks initial: true, the committed seed IS the reviewed artifact: no prior stage existed to write a report. Prepare directly from the seed with --artifact naming the entity; never author, request, or wait for a stage report, and never emit report-incomplete. Skip step 3 — both structured reads exit nonzero with no report. Present outcome, scope, exclusions, and the ideation proof the next stage owes.
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.
- 3d ago First seen · 77 lines · 12 tokens per session scan A c72164c284b0
fo-gate-lifecycle is a skill published in the GitHub repository spacedock-dev/spacedock (76 stars, last pushed 4d ago), licensed Apache-2.0. It adds 12 tokens to every session and 1,794 once invoked, about $0.0001 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…