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 beettlle/pi-spine --skill spine-autonomous-operatorgit clone --depth 1 https://github.com/beettlle/pi-spineWrote 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/beettlle/pi-spine/spine-autonomous-operator)<a href="https://agentmods.dev/skills/beettlle/pi-spine/spine-autonomous-operator"><img src="https://agentmods.dev/badge/skills/beettlle/pi-spine/spine-autonomous-operator/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/beettlle/pi-spine/spine-autonomous-operator"><img src="https://agentmods.dev/badge/skills/beettlle/pi-spine/spine-autonomous-operator.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 | $0.00098 | $0.03185 |
| Opus 5 | $0.00049 | $0.01592 |
| Sonnet 5 | $0.00020 | $0.00637 |
| Haiku 4.5 | $0.00010 | $0.00318 |
Grade C, and why
spine-autonomous-operator scanned grade C with 1 finding 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 12d 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.
Recursive force deletehighDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
rm -rf .worktrees/spine-* # if stale How it starts
The opening of the file, as written. The whole thing — 300 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Spine Autonomous Operator
You are the pi-spine batch operator for this repository. Drive all pending spine tasks to completion with maximum safe parallelization. You operate batches; you do not implement product code unless recovery requires fixing task packets or repo hygiene.
For curated semver releases (subset scope, publish gates), use skills/spine-release-operator/SKILL.md instead.
Invoke explicitly: /skill:spine-autonomous-operator
Success criteria
spine plan pendingshows 0 pending tasksspine preflightpasses with a clean git tree- All work is integrated on
main(not stuck in worktrees) - Repeatable pi-spine engine faults have GitHub issues filed
- Final report: waves completed, tasks done, issues filed, verification output
Hard rules
- Never hand-edit
.spine/batch-state.jsonor journal files under.spine/runtime/ - Never implement product code in task folders while a batch owns that scope
- Never claim batch/test success without CLI output
- Always use
spine status --diagnosefor recovery; followsuggestedCommand - Always run
spine gate approvebeforespine integrate - Always run
npm installonmainafter successful integrate - Always run post-integrate
npm run release:checkonmainafter each wave land loop before the next wave — see post-integrate-regression-gate.md - Never use
| tailor| headalone to judgerelease:checkpass/fail — verify exit code - Do not use unattended
spine run sequence --auto-approve-gate --forcewithout monitoring - Do not start a second batch while another batch is running on the same repo
- Never background
spine batch resume --attachedorresume --attached --force(#163) - Cursor Agent shell (~120s background timeout): use detached
spine batch start|resume(omit--attached); monitor withspine status --diagnoseandspine wait— see references/agent-shell-batch-policy.md - Release and agent batches: use detached
spine batch start|resume(omit--attached) unless the operator shell blocks until batch completion; thenspine wait --until …(#163, #185).spine doctorwarns in non-interactive and agent-harness contexts.
What ships with it
2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 12d ago First seen · 300 lines · 98 tokens per session scan C 7d78f211d290
spine-autonomous-operator is a skill published in the GitHub repository beettlle/pi-spine (3 stars, last pushed 6d ago), licensed MIT. It adds 98 tokens to every session and 3,185 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it C with 1 finding (recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
recipe-create-meet-space
Create a Google Meet meeting space and share the join link.
atmos-config
Atmos root configuration: atmos.yaml discovery, precedence, deep merging, basepath, imports, minimal bootstrap, and routing to narrower Atmos skills.
workthreads
SpecStory Workthreads - a weekly work-thread rollup across a team's repos from SpecStory coding histories (any agent - Claude Code, Codex, Cursor, Gemini, and more). It groups the window's sessions into threads of work per project and labels each new / open / recently closed, so a lead sees what shipped, what is still…
story-readiness
Validate that a story file is implementation-ready. Checks for embedded GDD requirements, ADR references, engine notes, clear acceptance criteria, and no open design questions. Produces READY / NEEDS WORK / BLOCKED verdict with specific gaps. Use when user says 'is this story ready', 'can I start on this story', 'is…
projects
List all managed projects with status, branch, open PRs, and open issue counts — portfolio-level view.
magpie-security-issue-import-from-md
Open one or more tracking issues from a markdown file containing a batch of security findings. Each finding becomes one tracker landing in the Needs triage board column. The file itself is the full report — there is no inbound reporter to reply to and no PR to inspect.