canonical/charm-tech is a shared repository that stores the common standards, decisions, specifications, style guides, and templates used across Canonical Charm Tech repositories. The Charm Tech team uses it as a central source so its repositories can reference or reuse the same documentation, Python and Go conventions, security policies, and CI configuration.
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/charm-tech --skill ct-code-reviewgit clone --depth 1 https://github.com/canonical/charm-techWrote 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/charm-tech/ct-code-review)<a href="https://agentmods.dev/skills/canonical/charm-tech/ct-code-review"><img src="https://agentmods.dev/badge/skills/canonical/charm-tech/ct-code-review/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/charm-tech/ct-code-review"><img src="https://agentmods.dev/badge/skills/canonical/charm-tech/ct-code-review.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 | $0.00043 | $0.00808 |
| Opus 5.5 | $0.00017 | $0.00323 |
| Sonnet 5.5 | $0.00009 | $0.00162 |
| Haiku 4.5 | $0.00004 | $0.00081 |
Grade A, and why
ct-code-review 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 — 82 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Canonical Code Review Guidelines
These guidelines define how code reviews should be conducted at Canonical. They focus on broadly applicable review techniques that are relevant to all projects.
Soft Skills
Tone
- Review the submission, not the author. Avoid "you did this wrong."
- Prefer "this could be improved by…" or "this doesn't seem right to me…"
- Be constructive — suggest how something may be improved
- For non-critical suggestions, make clear it's informational, not a change request: "I might have done this differently for these reasons…"
- Avoid being overtly negative, even if something is poor quality
- Remember: review is a learning experience for both author and reviewers
Label comments by intent
Prefix each comment with its intent so the author can tell blocking issues from optional ones at a glance (see Conventional Comments):
blocking:— must be resolved before mergesuggestion:— a proposed improvement; the author decidesnit:— minor/stylistic; non-blocking by definitionquestion:— seeking clarification, not necessarily a changepraise:— call out something done well Add(non-blocking)to any label when the distinction isn't obvious from the prefix.
Procedures
- If CI isn't passing, investigate why before approving
- Commits/PRs should reference their tracking ticket where one exists (e.g. a link to the issue)
- Pull request descriptions must be usefully descriptive — "Fixed Bug 12345" is not sufficient; include a sentence or two about what changed and why
Code Quality
- All patches must follow the code style and conventions of the appropriate project
- Look for cases where end-user function behaviour diverges from upstream — ask for clarification and push for upstreamable implementations
Changeset Size and Scope
Size
- Large changesets are complex and difficult to review
- Large changesets can usually be split into smaller commits or separate tickets
- They tend to combine related but not strictly connected changes
- Use pragmatism — sometimes a large changeset is genuinely necessary
- When a changeset is too large, still review it in full, but recommend splitting it (a
suggestion:, not a blocker) — note where the natural seams are
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 · 82 lines · 43 tokens per session scan A fed662e9b3e7
ct-code-review is a skill published in the GitHub repository canonical/charm-tech (4 stars, last pushed 7d ago), licensed Apache-2.0. It adds 43 tokens to every session and 808 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.
Other skills, from other repositories
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…
re0-merge
Review and land an external contribution the way this suite does: gate it against the thesis, land it with the author's credit intact, complete a new skill rather than merging it raw, then approve, credit, and explain before closing. Use when reviewing a pull request, as any collaborator or maintainer, not only the…
ring:mapping-feature-relationships
Mapping how features relate and phasing the work: categorizing PRD features, grouping them into domains, charting cross-feature journeys, dependencies, and integration points, and defining the binding Phases that plan.md mirrors one-to-one at Gate 7. Gate 2 of ring:planning-large-features; runs after…
code-reviewer
Code review specialist focused on patterns, bugs, security, and performance.