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/jonnyton/tinyassets/shipping-and-launchnpx skills add Jonnyton/TinyAssets --skill shipping-and-launchgit clone --depth 1 https://github.com/Jonnyton/TinyAssetsWrote 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/jonnyton/tinyassets/shipping-and-launch)<a href="https://agentmods.dev/skills/jonnyton/tinyassets/shipping-and-launch"><img src="https://agentmods.dev/badge/skills/jonnyton/tinyassets/shipping-and-launch.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 5.1 | $0.00047 | $0.01330 |
| Opus 5 | $0.00023 | $0.00665 |
| Sonnet 5 | $0.00009 | $0.00266 |
| Haiku 4.5 | $0.00005 | $0.00133 |
Grade A, and why
shipping-and-launch 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 5d 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 — 112 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Shipping and Launch
Overview
Automate the gates that keep broken code out of production, then deploy safely: every launch reversible, observable, and incremental. Shift left (catch problems as early as possible — a bug in lint costs minutes, in production hours) and faster is safer (smaller, more frequent releases are easier to debug than big-bang ones).
CI quality gates
Every change passes these gates before merge, in order, none skippable (lint fails → fix lint, don't disable the rule; test fails → fix code, don't skip the test):
lint → type check → unit tests → build → integration → e2e (optional)
→ security audit (npm audit --audit-level=high) → bundle size
Run on every PR and push to main; failures block merge (branch protection, no force-push to main, ≥1 approval). Configure as parallel jobs (lint/typecheck/test separately) with dependency caching; if the pipeline exceeds ~10 min, optimize — cache deps, parallelize, path-filter unchanged areas, shard tests — don't skip.
Feed failures back to the agent: paste the specific CI error and have the
agent fix and verify locally before pushing (lint → --fix; type error → fix at
the cited location; test → find the root cause, don't patch the symptom;
build → check
config/deps). A Build Cop keeps CI green: when it breaks, fix or revert
rather than letting breakage accumulate.
Secrets/env: .env.example committed (template); .env never committed; CI
uses separate (non-production) secrets from a manager, never hardcoded; production
secrets only in the deploy platform/vault. Automate dependency updates
(Dependabot/Renovate) and give every PR a preview deployment.
Pre-launch checklist
- Code: all tests pass; build clean (no warnings); lint/types pass; reviewed
and approved; no stray
console.log/debug TODOs; error handling covers expected failures. - Security: no secrets in code;
npm auditclean of critical/high; input validation on user-facing endpoints; authn/authz in place; security headers (CSP/HSTS); rate limiting on auth; CORS scoped, not wildcard. (See the security checklist in this skill.) - Performance: Core Web Vitals "Good"; no N+1 in critical paths; images optimized; bundle within budget; DB indexes; caching configured.
- Accessibility: keyboard nav; screen-reader structure; WCAG AA contrast (4.5:1); focus management for modals; descriptive field-associated errors; no axe/Lighthouse a11y warnings.
- Infra: prod env vars set; migrations applied/ready; DNS+SSL; CDN; logging and error reporting; health-check endpoint.
- Docs: setup/README, API docs, ADRs for decisions, changelog, user docs.
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.
- 5d ago First seen · 112 lines · 47 tokens per session scan A 02a6c72bdbd9
shipping-and-launch is a skill published in the GitHub repository Jonnyton/TinyAssets (1 stars, last pushed today), licensed MIT. It adds 47 tokens to every session and 1,330 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 2026-08-31.
Other skills, from other repositories
ship
Ship workflow: detect + merge base branch, run tests, review diff, bump VERSION, update CHANGELOG, commit, push, create PR. (gstack).
agent-github-modes
Agent skill for github-modes - invoke with $agent-github-modes.
tutti-app-release
Set up, review, run, or debug external repositories that publish a Tutti workspace app through the reusable Tutti App Release GitHub Actions workflow. Use for caller workflows, tutti.app.json manifests, @tutti-os/app-release-tools, S3/CloudFront release hosting, latest.json, versions.json, catalog.json, catalog-only…
publish
Publish the Octop Python package: cut a release branch from develop, bump version, update CHANGELOG, open a PR to main; after merge, Actions tag on main (PyPI / Docker Hub + GHCR) and sync main into develop. Use when the user asks to publish, release, bump version, cut a release, or run /publish.
seed-snapshot-release
Drives the snapshot-release flow for the current branch's PR. Posts a /snapshot comment on the PR if one isn't already there (with confirmation), waits for the Continuous Releases workflow to finish, and reports the tarball URLs from the resulting 📦 Snapshot Release comment. Use for both triggering and waiting …
releasepr
Adopt, configure, run, or troubleshoot compozy/releasepr in a consuming repository, including Actions, beta/stable/legacy plans, notes, dry-runs, and publication. Excludes pr-release internals and general versioning advice.