Borrowing it
Nothing to install: this file belongs to mdesalvo/Morgana. 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/mdesalvo/Morgana/main/.claude/skills/code-commentation/SKILL.mdgit clone --depth 1 https://github.com/mdesalvo/MorganaWrote 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/mdesalvo/morgana/code-commentation)<a href="https://agentmods.dev/skills/mdesalvo/morgana/code-commentation"><img src="https://agentmods.dev/badge/skills/mdesalvo/morgana/code-commentation/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/mdesalvo/morgana/code-commentation"><img src="https://agentmods.dev/badge/skills/mdesalvo/morgana/code-commentation.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 | $0.00048 | $0.01746 |
| Opus 5.5 | $0.00019 | $0.00698 |
| Sonnet 5.5 | $0.00010 | $0.00349 |
| Haiku 4.5 | $0.00005 | $0.00175 |
Grade A, and why
code-commentation 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 — 148 lines — stays where its author put it; the contents beside it link to each section on GitHub.
code-commentation
Guidelines for clear, pragmatic code commentary in C# projects. Comments exist to document and to clarify; they are applied consistently to all code written in a session.
Trigger
Every write or modification of C#, without explicit invocation: a new file, a refactor or even a single statement inside an existing body — see Retrofit policy.
Loading this skill before the first edit is mandated by the repository's CLAUDE.md.
Philosophy
- Every declaration (class, property, field, method, parameter) deserves a short comment
- The subject of a comment is what this instruction achieves in the domain and why. Never the language construct it achieves it with
- Comments explain the WHY and the constraints, not the syntactic WHAT — the name and the signature already show the mechanics
- Never more than 6 lines per comment block
- Comments are flowing prose, not telegraphic notes; they read naturally in sequence
- Comments are always in English — consistency across the codebase
- Never a comma before
and/orin a series (the Oxford comma): writetitle, subtitle and components, nevertitle, subtitle, and components. Where removing it makes the sentence ambiguous, rewrite the sentence — typically split it in two — never restore the comma - Precision over verbosity; every word counts
- No wall of text explaining the obvious; assume a competent reader
Naming rules
- Speaking names only: every identifier (class, property, field, method, parameter) must be readable and well contextualised
- No cryptic abbreviations: avoid acronyms or shortened forms inferred while reasoning and comprehensible only to you
- Contextualise, do not truncate: a full, clear name instead of a clipped form or an initialism
- Naming is not the place to be terse; clarity beats brevity
- A name needing a comment to be understood is renamed, not justified
Scope rules
Classes and records
- One-liner preferred: state the role or the lifecycle responsibility
- Multi-line (2-3): add constraints (threading model, initialization order, persistence behaviour)
- Never: explain what the name already says
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 · 148 lines · 48 tokens per session scan A 38e8f7d368dd
code-commentation is a skill published in the GitHub repository mdesalvo/Morgana (10 stars, last pushed yesterday), licensed Apache-2.0. It adds 48 tokens to every session and 1,746 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 2026-09-09.
code-commentation compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| code-commentationmdesalvo/Morgana | Skill | 10 | yesterday | Apache-2.0 | A | 48 | Claude Code |
| opentelemetry-net-instrumentationAaronontheweb/dotnet-skills | Skill | 1.3k | 9d ago | MIT | A | 56 | Claude Code |
| otel-dotnetollygarden/opentelemetry-agent-skills | Skill | 125 | yesterday | Apache-2.0 | A | 187 | Claude Code |
| vertical-slice-architecturethangchung/agent-engineering-experiment | Skill | 28 | 23d ago | MIT | A | 192 | Claude Code, Codex |
| dotnet-inspectthangchung/agent-engineering-experiment | Skill | 28 | 23d ago | MIT | A | 54 | Claude Code |
| software-architecturethangchung/agent-engineering-experiment | Skill | 28 | 23d ago | MIT | A | 42 | Claude Code, Codex |
| aspnet-minimal-api-openapithangchung/agent-engineering-experiment | Skill | 28 | 23d ago | MIT | A | 19 | Claude Code |