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/verify-docs/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/verify-docs)<a href="https://agentmods.dev/skills/backblaze-labs/genblaze/verify-docs"><img src="https://agentmods.dev/badge/skills/backblaze-labs/genblaze/verify-docs/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/verify-docs"><img src="https://agentmods.dev/badge/skills/backblaze-labs/genblaze/verify-docs.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 | $0.00051 | $0.00894 |
| Opus 5.5 | $0.00020 | $0.00358 |
| Sonnet 5.5 | $0.00010 | $0.00179 |
| Haiku 4.5 | $0.00005 | $0.00089 |
Grade A, and why
verify-docs 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.
How it starts
The opening of the file, as written. The whole thing — 79 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Verify docs freshness
Run the four checks below and produce a single report. Do NOT auto-fix — surface findings for human review (stale docs usually need a human to decide whether behavior is still accurate).
1. Stale last_verified stamps
Every canonical doc in this repo carries <!-- last_verified: YYYY-MM-DD --> near the top.
- Glob:
README.md,ARCHITECTURE.md,AGENTS.md,CLAUDE.md,CONTRIBUTING.md,docs/**/*.md. - For each file, extract the stamp. Flag as P1 stale when:
- Stamp is absent (canonical docs must have one), OR
- Stamp is >60 days old, OR
- Stamp date is earlier than the most recent commit touching the file's owning module
per the Doc Update Mapping in
docs/dev-workflows.md.
Owning-module lookup (from docs/dev-workflows.md):
| Doc | Owning module |
|---|---|
docs/features/pipeline.md |
libs/core/genblaze_core/pipeline/ |
docs/features/provider-system.md |
libs/core/genblaze_core/providers/ |
docs/features/media-embedding.md |
libs/core/genblaze_core/media/ |
docs/features/object-storage.md |
libs/core/genblaze_core/storage/ + libs/connectors/s3/ |
docs/features/parquet-sink.md |
libs/core/genblaze_core/sinks/ |
docs/features/manifest-provenance.md |
libs/core/genblaze_core/canonical/ + libs/core/genblaze_core/models/manifest.py |
docs/features/cli.md |
cli/ |
ARCHITECTURE.md |
whole repo — use root mtime |
docs/app-workflows.md |
libs/core/ |
docs/dev-workflows.md |
Makefile + .github/workflows/ |
Use git log -1 --format=%cs -- <path> to get last-touched date for a module.
2. Python example syntax
Every Python fenced block in docs/features/*.md should at minimum be parseable.
- For each code block (
python3 -c "import ast; ast.parse(open(p).read())". - Report parse errors only. Ignore import-resolution failures (examples use real API keys that aren't available in the audit env).
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 · 79 lines · 51 tokens per session scan A d31b9aec4b00
verify-docs is a skill published in the GitHub repository backblaze-labs/genblaze (550 stars, last pushed today), licensed MIT. It adds 51 tokens to every session and 894 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 2026-08-30.
Other skills, from other repositories
glass-shard-title
Glass shards fly in through fog and tile themselves into the headline. HyperFrames block, 1920×1080, 12.16s, 19 variables.
investigate
Investigate a specific issue report with strict, evidence-driven diagnosis.
review
Comprehensive security and correctness audit. Use for review, deep review, thermo nuclear, or thermonuclear requests and branch or PR diff audits.
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.
motion
Reconstruct a skeleton from calibrated mesh projections and sequential VLM joint annotations, then fit joints and skin weights. Generate motion from joint-position trajectories, rhythm and contact constraints through IK; refine bone orientation against the action, then export, retarget and validate on the target mesh.
image
Use this Skill when a game plan needs a single-subject concept image, a character reference cleaned for image-to-3D, or a front-facing transparent T-pose image for downstream character reconstruction. T-pose generation is an image-generation and image-editing task; it is not a separate asset category.