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/laravel/package-skeleton/skeleton-developmentnpx skills add laravel/package-skeleton --skill skeleton-developmentgit clone --depth 1 https://github.com/laravel/package-skeletonWrote 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/laravel/package-skeleton/skeleton-development)<a href="https://agentmods.dev/skills/laravel/package-skeleton/skeleton-development"><img src="https://agentmods.dev/badge/skills/laravel/package-skeleton/skeleton-development.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 | $0.00057 | $0.00764 |
| Opus 5 | $0.00028 | $0.00382 |
| Sonnet 5 | $0.00011 | $0.00153 |
| Haiku 4.5 | $0.00006 | $0.00076 |
Grade A, and why
skeleton-development 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 4d 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 — 54 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Skeleton Development
Primary Goal
Evolve the starter kit without making it less useful for future package authors.
Workflow
- Preserve generic placeholders such as
:author_name,:package_name,:vendor_slug, and:package_sluguntil the configure flow replaces them. - Keep starter guidance minimal and split skeleton-maintenance rules from package-author rules.
- Use temporary phase scaffold tests when proving repository shape, file parity, or generated scaffolding; delete those tests before final validation.
- Maintain skeleton guidance in
AGENTS.md, package guidance inAGENTS_PACKAGE.md, and package-facing local skills in.agents/skills;configure.phpgenerates packageAGENTS.md, then linksCLAUDE.mdtoAGENTS.mdand.claudeto.agentsduring package configuration. - Keep
configure.phpfeature and tool pruning maps, opt-in non-interactive--[feature]and--[tool]flags, service provider wiring, Composer metadata,README_PACKAGE.md,AGENTS_PACKAGE.md, AI guidance, skills, and publishable files aligned. - Keep configure-only dependencies in
require-dev, include them in configure dependency checks, and prune them through the configurecomposer remove --no-installstep so the configured package'scomposer.jsonandcomposer.lockstay in sync. - Preserve the non-interactive contract: metadata validators run against flag and default values before any file changes, results print as single-line JSON on stdout, and
--no-interaction,COMPOSER_NO_INTERACTION=1, agent detection, and non-TTY stdin all trigger the mode. - Keep development-time authoring files out of Composer dist archives with
.gitattributeswhen they are not runtime package files.
References
AGENTS.mdAGENTS_PACKAGE.md- Linked
CLAUDE.md README.mdREADME_PACKAGE.md.agents/skills/- Linked
.claude/ configure.php.gitattributesPLAN.md,REQS.md, andphases/when present
Examples
- Add or rename local guidance under
AGENTS.md,AGENTS_PACKAGE.md, or.agents/skills, then update front matter names, root guidance, and any scaffold consistency checks. - Add temporary Phase tests to lock down generated file shape, run them to prove the change, then delete them before the final
composer test. - Update package-facing README content in
README_PACKAGE.md;README.mdshould stay focused on using this skeleton. - When adding a selectable package feature, add both the starter files and the matching configure pruning behavior so package authors can select or omit it cleanly.
- When adding or renaming a selectable feature or tool key, verify the derived non-interactive flag includes only the expected generated files.
- When adding a configure-only helper package, update
dependenciesAreInstalled(), theremoveConfigureDependencies()package list, and temporary copied-skeleton configure checks together.
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.
- 4d ago First seen · 54 lines · 57 tokens per session scan A b5c2cb2354ae
skeleton-development is a skill published in the GitHub repository laravel/package-skeleton (60 stars, last pushed yesterday), licensed MIT. It adds 57 tokens to every session and 764 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 2026-08-30.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
brainstorming
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
auto-perf-optimize
Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.
chat-perf
Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
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…