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 boringmarketer/kimi-first --skill ship-lanegit clone --depth 1 https://github.com/boringmarketer/kimi-firstWrote 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/boringmarketer/kimi-first/ship-lane)<a href="https://agentmods.dev/skills/boringmarketer/kimi-first/ship-lane"><img src="https://agentmods.dev/badge/skills/boringmarketer/kimi-first/ship-lane/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/boringmarketer/kimi-first/ship-lane"><img src="https://agentmods.dev/badge/skills/boringmarketer/kimi-first/ship-lane.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00064 | $0.00826 |
| Opus 5.5 | $0.00026 | $0.00330 |
| Sonnet 5.5 | $0.00013 | $0.00165 |
| Haiku 4.5 | $0.00006 | $0.00083 |
Grade A, and why
ship-lane 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 1mo 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 — 34 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Ship a lane (loop v3)
James, Sep 3 2026: "stop spending so much time on unnecessary review and ceremony … repeatable stuff … clear paths to productionizing." and "on other projects I've been stuck in endless loops instead of using repeatable smart workflows." This skill is the repeatable workflow. Apply it on every project.
0. Done means live
A feature is done when it is live for the real customer with a receipt (a row, a log line, a screenshot of the real account). Never when a review certifies it.
1. Classify before dispatch (never mix classes in one lane)
| Class | Contents | Proof column (all of it, every time) | Review |
|---|---|---|---|
| A rail | migration, RPC, worker/runner, provider read/write, receipts | acceptance at real cardinality · disposable-DB drill · runtime probe · red-first unit pins · apply + deploy same minute · post-apply script · one live receipt | one adversarial pass (money/provider-write/credentials/customer-messages: highest effort) |
| B surface | member-visible copy/cards/gestures | film on the final tree · record derived by script · digest pin · SSR pin per sentence · deploy · live film green | one design pass on frames (PASS/BLOCK) |
| C activation | flags, secrets, schedulers on, first run on the customer | runbook step · post-apply script · /ready · one live receipt |
none — the driver executes under standing authorization |
2. One pass, one fix
Builder (codex terra, flat-rate) → proofs → ONE review pass with a CHECKLIST (the proof column + the WO deliverables; verdict per item with the pin that holds it) → ONE fix → merge. Residue goes to a weekly punch batch (one lane, one design pass). A second round exists only for a truth/custody BLOCK, and then only that item is re-checked. Certification by inspection is worth nothing; a pin that goes red is the certification.
3. Activation is supervised-first
If the rail has produced real, owner-approved output, it runs on its scheduler under a database spend ceiling + kill switch + the existing quality decision + receipts. Any "accepted packet" is generated from that real evidence by the finalizer, never a separate dogfood ceremony.
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.
- 1mo ago First seen · 34 lines · 64 tokens per session scan A 9d9d398792b6
ship-lane is a skill published in the GitHub repository boringmarketer/kimi-first (49 stars, last pushed 1mo ago), licensed MIT. It adds 64 tokens to every session and 826 once invoked, about $0.0003 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 2026-09-04.
Other skills, from other repositories
paperclip
Use for Paperclip-managed tasks and heartbeats: reading task context, delivering task documents or files, updating completion or blockers, coordinating or delegating work, and following company governance. Includes control plane API operations for assignments, comments, approvals, and routines.
gh-file-issue
Use when filing a new Codewhale GitHub issue: turn a bug or idea into a well-formed, actionable issue with repro, acceptance criteria, labels, and milestone.
gh-treasure-hunt
Hunt the issue/PR queue for highest value-over-risk wins: clean focused community PRs, already-implemented issues to close, safe quick-fixes.
review-my-team
Review a connected Paperclip team's agents, tasks, blockers and pending approvals when the user asks for a team summary or what needs attention.
requirements-writer
Use when converting PM intake into a slice SPEC.md with observable acceptance outcomes, explicit scope, and advisory sibling build dependencies.
mission-control
Interact with Mission Control — AI agent orchestration dashboard. Use when registering agents, managing tasks, syncing skills, or querying agent/task status via MC APIs.