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/baleen37/bstack/shipnpx skills add baleen37/bstack --skill shipgit clone --depth 1 https://github.com/baleen37/bstackWhat 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 | $0.00060 | $0.02172 |
| Opus 5 | $0.00030 | $0.01086 |
| Sonnet 5 | $0.00012 | $0.00434 |
| Haiku 4.5 | $0.00006 | $0.00217 |
Grade A, and why
ship 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 — 200 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Ship
Overview
Deploy safely, observably, reversibly. Every launch goes through three phases: pre-deploy → deploy → post-deploy. Don't skip phases.
Automation Policy
Run safe read-only checks and local reversible work automatically (git/CI status, tests, lint, audits,
drafting rollout/rollback plans). Classify each finding AUTO-COMPLETED, NEEDS_APPROVAL, BLOCKED,
or READY_FOR_SHIP_REVIEW.
Ask for approval before anything that changes shared or external state: pushes, PR creation/merge, releases, deploys, infra/flag/config/secret/DB changes, external notifications, rollbacks, destructive commands, data migrations.
When to Delegate to Subagents
Fan-out is a tool, not a requirement.
- Delegate when 2+ independent analyses can run in parallel, a specialist fits
(
me:security-auditor,me:test-engineer,Explore), or output would pollute main context. - Run directly when a single command answers it, the result must be reasoned about immediately, or blast radius is small.
When delegating, batch independent calls in one message so they run in parallel.
Execution Workflow
Three phases: pre-deploy → deploy → post-deploy. Do not skip phases.
First, classify the change:
- Deployable (touches code/infra that runs in production) → full three-phase flow.
- Non-deployable (docs, skills, internal scripts, CI config without runtime effect) → run Phase 1 checks (tests/lint relevant to the change), commit/PR per normal flow, skip Phases 2–3. State explicitly: "Non-deployable change, skipping deploy/verify phases."
If unsure, ask the user once. Don't invent a deploy step for a doc change.
Phase 1 — Pre-deploy (배포 전 점검)
- Identify scope — launch type, changed files, blast radius, production systems touched.
- Read the deploy convention — see "Reading Deploy Convention" below. If the project has none, ask once and offer to record the answer.
- Run checks — local verification (tests, lint, type, build), CI/PR status, dependency/security audits, docs. For non-trivial changes consider fanning out per "When to Delegate".
- Draft artifacts — rollout stages, rollback triggers/procedure, monitoring targets, owners, post-deploy checks.
- Classify and decide — mark each item
AUTO-COMPLETED,NEEDS_APPROVAL,BLOCKED, orREADY_FOR_SHIP_REVIEW. Stop and report evidence if anything isBLOCKED. Present GO/NO-GO with the rollback plan.
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 · 200 lines · 60 tokens per session scan A 49ede3f288be
ship is a skill published in the GitHub repository baleen37/bstack (4 stars, last pushed 11d ago), licensed MIT. It adds 60 tokens to every session and 2,172 once invoked, about $0.0003 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 2026-08-31.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
babysit-pr
Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…
imagegen
Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…