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/canonical/workshop/documentation-verifynpx skills add canonical/workshop --skill documentation-verifygit clone --depth 1 https://github.com/canonical/workshopWhat 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 | $0.00044 | $0.00712 |
| Opus 5 | $0.00022 | $0.00356 |
| Sonnet 5 | $0.00009 | $0.00142 |
| Haiku 4.5 | $0.00004 | $0.00071 |
Grade A, and why
documentation-verify 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 2d 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.
The source is not reproduced here
Licensed GPL-3.0
The repository is licensed GPL-3.0, which this catalogue does not treat as permission to reproduce the file. Read it at the source.
What ships with it
2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 2d ago First seen · 81 lines · 44 tokens per session scan A b66cd3ec85fe
documentation-verify is a skill published in the GitHub repository canonical/workshop (105 stars, last pushed 4d ago), licensed GPL-3.0. It adds 44 tokens to every session and 712 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 2026-08-30.
Other skills, from other repositories
toolset-design
Design and validate new MCP toolsets, tools, and tool changes. Use when planning a new toolset, adding tools to an existing toolset, reviewing a toolset PR, or deciding whether a new tool is warranted. Covers the full lifecycle: eval-first validation, tool design methodology, consolidation patterns, and review…
cast-refine
Help a Cast agent become more itself — read across its blueprint, runtime state, memory, and operator-action history to surface blueprint refinement proposals. Use after the agent has weeks of real run history and the operator senses drift, friction, or untapped potential. Output is proposals (a dated artifact), not…
dockerfile-slimming
Reduce container image size and build time with multi-stage builds and ordered layer caching.
cast-debug
Diagnose Cast behavior end-to-end — agent misbehavior (why did the agent do X? why no reply?) or Cast-server / pipeline issues (why isn't this message arriving? why won't the container start?). Reads gateway DB, agent.db messagelog, agent-runner log, session transcripts, and host server logs layer by layer. When the…
cast-build
Author Cast agent code in advanced mode — blueprint files (identity, channels, props, assets) and per-agent service code under blueprint/service/. Use when the operator wants to write or change something inside one or more agent folders that the in-Cast consoles can't reach (custom service code, scripted blueprint…
write-dockerfile
Creates or updates an optimized, production-ready Dockerfile and .dockerignore. Focuses on image build strategy, runtime hardening, caching, and minimal production images. Invoked when the user asks to write a Dockerfile, improve container image quality, or harden image builds.