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 AgentureHQ/agenture-loop --skill code-commentgit clone --depth 1 https://github.com/AgentureHQ/agenture-loopWrote 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/agenturehq/agenture-loop/code-comment)<a href="https://agentmods.dev/skills/agenturehq/agenture-loop/code-comment"><img src="https://agentmods.dev/badge/skills/agenturehq/agenture-loop/code-comment/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/agenturehq/agenture-loop/code-comment"><img src="https://agentmods.dev/badge/skills/agenturehq/agenture-loop/code-comment.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 | $0.00051 | $0.00638 |
| Opus 5.5 | $0.00020 | $0.00255 |
| Sonnet 5.5 | $0.00010 | $0.00128 |
| Haiku 4.5 | $0.00005 | $0.00064 |
Grade A, and why
code-comment 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 — 74 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Code Comment
Add meaningful comments to source code without altering its behavior.
Workflow
- Determine scope — identify what the user wants commented: a specific function, a file, a selection, or a set of files.
- Read the code — understand the logic, control flow, and data structures before writing anything.
- Add comments — apply the rules below, using the correct comment syntax for the language.
- Verify — confirm the code is unchanged aside from added comments. Run linters if available.
What to Comment
- Why, not what — explain intent, trade-offs, and constraints the code itself cannot convey.
- Non-obvious algorithms or business logic.
- Assumptions, invariants, and known limitations.
- Important side effects (I/O, mutations, external calls).
- Edge cases and error-handling rationale.
- Public API surface: function/class purpose, parameters, return values.
What NOT to Comment
- Obvious operations (
i += 1 // increment i). - Code that is self-documenting through clear naming.
- Restating the code in English (
// loop through itemsabove a for-loop). - Commented-out code — remove dead code instead.
- Change history — that belongs in version control.
Comment Style
- Use the language's idiomatic comment syntax and doc-comment conventions:
- Python:
#inline,"""docstrings"""for modules/classes/functions - JS/TS:
//inline,/** JSDoc */for exports - Go:
//with godoc conventions - Rust:
///doc-comments,//inline - Java/Kotlin:
/** Javadoc */for public API,//inline - Other languages: follow their standard conventions
- Python:
- Keep comments concise — one or two sentences per block.
- Place comments on the line above the code they describe, at the same indentation level.
- For multi-line explanations, use a block/doc-comment rather than stacking single-line comments.
Safety Rules
- NEVER modify code logic, formatting, or structure — only add comments.
- NEVER remove or rewrite existing comments unless they are demonstrably wrong.
- Preserve all original whitespace and line breaks.
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 · 74 lines · 51 tokens per session scan A c8b584ec5aec
code-comment is a skill published in the GitHub repository AgentureHQ/agenture-loop (2 stars, last pushed 4mo ago), licensed Apache-2.0. It adds 51 tokens to every session and 638 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
connect
Install the scoped Antigravity permission hook.
hook-template
Generate hook script from template. Use when adding a new hook, wiring a PreToolUse/PostToolUse/Stop/Notification hook, or scaffolding hook config for settings.json.
check-environment
Verify Claude, Codex, and Grok availability plus Director guidance, relay, agents, and skills. Audit optional hooks only when selected. Use after installation or when a native surface misbehaves.
agents
List all available agents (core, expert, self-evolving). Use when the user asks what agents are available or runs /agents.
handoff-gemini
Delegate long-context analysis, research, and large-document summarization to Google Gemini CLI (1M-token context) via non-interactive gemini -p, preserving Claude context. Use when the user says 'use gemini'/'hand off to gemini' or a task needs 100K+ tokens of context.
test-runner
Test execution reference: framework detection (pytest/jest/vitest/go/cargo/junit) and correct run/coverage commands, plus failure-analysis steps. Use when running tests, analyzing test failures, or verifying coverage after code changes.