Canonical Copilot Collections is a repository for organizing and distributing GitHub Copilot instructions, prompts, agents, and skills across Canonical repositories. Teams configure repositories to subscribe to shared collections, such as Python, documentation, or Juju development guidance, and keep those assets synchronized.
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 skills add canonical/copilot-collections --skill documentation-verifygit clone --depth 1 https://github.com/canonical/copilot-collectionsWrote 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/canonical/copilot-collections/documentation-verify)<a href="https://agentmods.dev/skills/canonical/copilot-collections/documentation-verify"><img src="https://agentmods.dev/badge/skills/canonical/copilot-collections/documentation-verify/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/canonical/copilot-collections/documentation-verify"><img src="https://agentmods.dev/badge/skills/canonical/copilot-collections/documentation-verify.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Excessive Agency · line 73 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
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 | $0.00044 | $0.00712 |
| Opus 5.5 | $0.00018 | $0.00285 |
| Sonnet 5.5 | $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 1mo 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 — 81 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Documentation Accuracy Verification
Scope
Accuracy verification only: cross-reference documentation claims, commands, API names, and configuration keys against source code in the same repository. Flag anything that cannot be verified.
Inputs
- Changed documentation files (from
git diff). Ifgit diffis unavailable or empty, use files explicitly provided for review; otherwise, treat all documentation files underdocs/as changed. - Full codebase.
- Test files, configuration schemas.
- Documentation structure.
Workflow
Follow this three-stage process to verify documentation accuracy:
Stage 1: Discovery Scan
Objective: Identify documentation claims and form initial hypotheses.
- Run
git diffto list changed documentation files. - Categorize changes into claim types (behaviour, CLI, API, config, examples, error messages, etc.).
- Form initial hypotheses: Supported, Unsupported, Speculative, Ambiguous, or Outdated.
For detailed categorization and hypothesis formation procedures, see references/verification_procedures.md → Discovery Scan.
Stage 2: Verification Pass
Objective: Verify every hypothesis with code evidence. Code is the source of truth.
CRITICAL: Complete verification before reporting any claims.
- Use at least two search strategies per claim (direct search, entrypoint tracing, test evidence, schema/validation search).
- Apply claim-type-specific verification checklists (behaviour, CLI, API, config, examples, errors, terminology).
- Document evidence for each finding (file paths, line numbers, search commands).
- Reclassify hypotheses based on verification results.
- Apply false-positive prevention rules.
- Cross-check documentation coverage.
For comprehensive verification checklists and classification rules, see references/verification_procedures.md → Verification Pass.
Stage 3: Report Generation
Objective: Present verified findings with evidence and conservative recommendations.
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.
- 1mo ago First seen · 81 lines · 44 tokens per session scan A b66cd3ec85fe
documentation-verify is a skill published in the GitHub repository canonical/copilot-collections (31 stars, last pushed 7d ago), licensed Apache-2.0. It adds 44 tokens to every session and 712 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
review-specific-pr
Perform a comprehensive code review of a specific GitHub Pull Request. Analyzes code changes, checks for bugs, security issues, test coverage, and coding standards compliance. Use when a user provides a PR URL or asks to review a specific pull request.
review-open-pull-requests
List and analyze all open pull requests across GitHub repositories. Shows review status, CI/CD check results, age, and reviewers. Use when triaging PRs, checking team velocity, or identifying stale reviews that need attention.
pull-request-ready
Take a finished Backstage change to reviewer-ready — audit the diff for churn and leaked secrets, confirm changesets, API reports and config schema, and draft the PR title and body.
autoreview
Structured code review through the shared OpenClaw agent-skills installation.
revdiff-plan
Review the last Codex assistant message (plan, analysis, or proposal) with inline annotations in a TUI overlay. Extracts the most recent response from Codex rollout files and opens it in revdiff for review and annotation. Activates on "revdiff-plan", "review plan with revdiff", "annotate plan", "review last response"…
asplos-writing-style
Use when drafting or revising ASPLOS prose — engineering the first two pages that rapid review actually reads, stating the cross-layer insight as one quotable sentence, structuring per-layer mechanism sections, writing bounded claims, and fitting everything into 11 self-contained pages that include figures and…