Borrowing it
Nothing to install: this file belongs to backblaze-labs/genblaze. 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/backblaze-labs/genblaze/main/.claude/skills/scaffold-provider/SKILL.mdgit clone --depth 1 https://github.com/backblaze-labs/genblazeWrote 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/backblaze-labs/genblaze/scaffold-provider)<a href="https://agentmods.dev/skills/backblaze-labs/genblaze/scaffold-provider"><img src="https://agentmods.dev/badge/skills/backblaze-labs/genblaze/scaffold-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/backblaze-labs/genblaze/scaffold-provider"><img src="https://agentmods.dev/badge/skills/backblaze-labs/genblaze/scaffold-provider.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 | $0.00000 | $0.02400 |
| Opus 5 | $0.00000 | $0.01200 |
| Sonnet 5 | $0.00000 | $0.00480 |
| Haiku 4.5 | $0.00000 | $0.00240 |
Grade A, and why
scaffold-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 9d 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 — 154 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Scaffold a New Provider Connector
Generate a complete provider connector package for: $ARGUMENTS
Parse the arguments:
$0— provider name (e.g.fal,hedra,picovoice); used for the package slug$1— modality:image,video,audio, ormusic$2— API style:sync(default — most providers) orpolling
If any argument is missing or ambiguous, ask the user before proceeding. Do not invent a name or modality.
Phase 1 — Learn current conventions
Read these files in order. Skipping this phase produces drift. The codebase is the source of truth; this skill must reflect what's already shipping.
- Base classes —
libs/core/genblaze_core/providers/base.pyBaseProvider(polling lifecycle:submit/poll/fetch_output)SyncProvider(singlegeneratemethod)validate_asset_url,validate_chain_input_url,classify_api_error
- Contributor guide —
docs/guides/new-provider.md(the canonical checklist; this skill scaffolds what the guide describes) - Two existing connectors matching the modality. Use Glob on
libs/connectors/*/and pick representative examples:- sync image/audio reference —
libs/connectors/elevenlabs/,libs/connectors/openai/(DALL-E, TTS) - polling video reference —
libs/connectors/replicate/,libs/connectors/luma/ - For each, read:
pyproject.toml,genblaze_*/__init__.py,genblaze_*/provider.py,genblaze_*/_errors.py, and the primary test file undertests/.
- sync image/audio reference —
Extract these patterns from what you read (do not assume — verify):
| Pattern | Where to look |
|---|---|
Package + module slugs (genblaze-{name} / genblaze_{name}) |
pyproject.toml [project] name, [tool.hatch.build.targets.wheel] packages |
Class naming {Name}Provider (or capability-suffixed: OpenAITTSProvider) |
provider.py, __init__.py |
Entry-point format under genblaze.providers |
pyproject.toml [project.entry-points."genblaze.providers"] |
Error mapper shape — delegate to classify_api_error vs SDK-specific checks |
_errors.py (compare LMNT minimal vs ElevenLabs verbose) |
Capability declaration via get_capabilities() |
provider.py |
Standard-name → native param mapping in normalize_params() |
provider.py |
Per-model ModelSpec and create_registry() classmethod |
provider.py |
Pricing strategy choice from genblaze_core.providers.pricing |
provider.py (look for per_unit, per_input_chars, per_output_second, tiered, bucketed_by_duration, by_param, by_model_and_param, per_response_metric) |
| Compliance harness wiring | tests/test_*.py (subclass of ProviderComplianceTests) |
| Standardization hooks (optional) | preflight_auth, probe_model — see libs/connectors/gmicloud/genblaze_gmicloud/_base.py |
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.
- 9d ago First seen · 154 lines · 0 tokens per session scan A bf4701d2def0
scaffold-provider is a skill published in the GitHub repository backblaze-labs/genblaze (559 stars, last pushed 4d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 2,400 tokens. 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
pr-to-video
Turn a GitHub pull request (a PR URL, owner/repo#N, or 'this PR' in a checked-out repo) into a code-change explainer video — changelog, feature reveal, fix, or refactor walkthrough built from the diff, commits, and files: the input is a code change, not a website. Not a product promo (/product-launch-video) or a no-PR…
general-video
Author or edit a custom HyperFrames composition when no specialized workflow fits, or when BRIEF.md sets flow: companion. Use for longer or multi-scene pieces, brand and sizzle reels, montages, static loops, static title cards, footage remixes, and freeform builds. Use motion-graphics instead for a short unnarrated…
motion-graphics
A short, design-led motion graphic where motion is the message — kinetic typography, stat count-up, chart/data-viz hit, logo sting / brand lockup, lower-third / callout / social overlay, animated map (highlight regions, connect places, zoom to a location), animated tweet / news-article / headline, webpage / UI…
parse-document
Convert a PDF, scan, image of a page, or office file to clean markdown through the connected Superlinked MCP edge, so the source document is not read into model context directly. Use when the user asks to read, parse, OCR, extract from, summarize, or answer questions about a document.
horse-integration-tests
Guide for writing automated integration tests for Horse endpoints using DUnit/DUnitX and THTTPClient.
motion
How an agent turns a character mesh into a usable animated FBX — and how to judge whether the result is shippable.