Borrowing it
Nothing to install: this file belongs to YosefHayim/launch-store. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/YosefHayim/launch-store/main/.claude/skills/add-a-provider/SKILL.mdgit clone --depth 1 https://github.com/YosefHayim/launch-storeWrote 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/yosefhayim/launch-store/add-a-provider)<a href="https://agentmods.dev/skills/yosefhayim/launch-store/add-a-provider"><img src="https://agentmods.dev/badge/skills/yosefhayim/launch-store/add-a-provider/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/yosefhayim/launch-store/add-a-provider"><img src="https://agentmods.dev/badge/skills/yosefhayim/launch-store/add-a-provider.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 | $0.00041 | $0.00424 |
| Opus 5.5 | $0.00016 | $0.00170 |
| Sonnet 5.5 | $0.00008 | $0.00085 |
| Haiku 4.5 | $0.00004 | $0.00042 |
Grade A, and why
add-a-provider 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 2mo 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.
What it actually says
Add a provider backend
Use this when
- adding a new storage / build / submit / credentials / compute backend
- wiring a new SDK behind one of Launch's provider interfaces
Steps
- Pick one of the five types in
src/core/types/providers.ts:BuildEngine/StorageProvider/CredentialsProvider/Submitter/ComputeHost. - Implement it as a named object in
src/providers/<kind>/<name>.ts, settingnameto the value users put inlaunch.config.ts. - Register it in
src/providers/index.ts(registerBuiltins()), which wires intosrc/core/services/registry.ts. The pipeline resolves a provider by itsname, so you never editsrc/core/build/pipeline.tsto add one. - Lazy-load any heavy or optional SDK through
requireOptionalinsrc/core/services/optionalDep.ts, so a missing package becomes an actionable install hint instead of a stack trace. - Add a
*.test.tsbeside the provider, then run the gate (see therun-the-gateskill).
Adding a backend never edits the pipeline - that is the whole point of the registry: implement the interface, register the name, done.
See AGENTS.md -> “Adding a backend = implement an interface + register it” for the worked S3 example.
Cautions
- All child processes go through
src/core/services/exec.ts(run/capture,shell: false, explicit argv) - never build a shell string or callspawn/execdirectly. - Secrets stay in the OS keychain;
~/.launchholds non-secret paths and ids only. Don't log, write, or commit key material.
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.
- 2mo ago First seen · 29 lines · 41 tokens per session scan A 8602a086f26a
add-a-provider is a skill published in the GitHub repository YosefHayim/launch-store (12 stars, last pushed 8d ago), licensed MIT. It adds 41 tokens to every session and 424 once invoked, about $0.0002 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 2026-08-31.
add-a-provider compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| add-a-providerYosefHayim/launch-store | Skill | 12 | 8d ago | MIT | A | 41 | Claude Code |
| cmp-firebase-connectkvdm-co-pilot/create-cmp | Skill | 0 | 16d ago | MIT | A | 195 | Claude Code |
| uniwinduni-stack/uniwind | Skill | 1.7k | yesterday | MIT | A | 130 | Claude Code, Codex |
| flutterericrisco/rsc-harness | Skill | 503 | 2d ago | MIT | A | 91 | Claude Code, Codex |
| react-nativeericrisco/rsc-harness | Skill | 503 | 2d ago | MIT | A | 90 | Claude Code, Codex |
| maui-networking-offline-datadotnet/maui-labs | Skill | 235 | yesterday | MIT | A | 87 | Claude Code, Codex |
| maui-aspire-clientdotnet/maui-labs | Skill | 235 | yesterday | MIT | A | 100 | Claude Code, Codex |