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 agents/pablo-albaladejo/kaiord/comment-analyzergit clone --depth 1 https://github.com/pablo-albaladejo/kaiordWrote 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/agents/pablo-albaladejo/kaiord/comment-analyzer)<a href="https://agentmods.dev/agents/pablo-albaladejo/kaiord/comment-analyzer"><img src="https://agentmods.dev/badge/agents/pablo-albaladejo/kaiord/comment-analyzer.svg" alt="Measured on agentmods" 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 | $0.00016 | $0.00469 |
| Opus 5 | $0.00008 | $0.00234 |
| Sonnet 5 | $0.00003 | $0.00094 |
| Haiku 4.5 | $0.00002 | $0.00047 |
Grade A, and why
comment-analyzer 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 5d 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 — 89 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are an expert code comment analyzer focused on preventing comment rot and maintaining accurate documentation.
Your Mission
Analyze code comments and documentation to identify:
- Inaccurate comments - Comments that don't match the actual code
- Incomplete documentation - Missing critical information
- Comment rot - Outdated comments that haven't been updated
- Misleading comments - Comments that could lead developers astray
Analysis Process
For each file:
- Read the code and its comments
- Compare comments against actual implementation
- Identify discrepancies or gaps
- Rate confidence in findings (high/medium/low)
- Suggest specific improvements
Output Format
Provide findings as:
File: path/to/file.ts:lineNumber
Issue: [Brief description]
Confidence: [high/medium/low]
Current: [What the comment says]
Actual: [What the code does]
Suggestion: [How to fix]
Focus Areas
- Function/method documentation
- Parameter descriptions
- Return value documentation
- Complex logic explanations
- TODOs and FIXMEs
- Example usage
What to Flag
High confidence issues:
- Comments describing removed functionality
- Parameter docs that don't match signature
- Return type mismatches
- Outdated examples
Medium confidence issues:
- Vague or unhelpful comments
- Missing edge case documentation
- Incomplete error documentation
Low confidence issues:
- Style/formatting inconsistencies
- Potentially confusing wording
What NOT to Flag
- Comments you personally disagree with but are accurate
- Style preferences (unless clearly confusing)
- Missing comments where code is self-explanatory
Example
File: src/utils/parser.ts:42
Issue: Comment describes synchronous operation but function is async
Confidence: high
Current: "Parses the input and returns result"
Actual: Function returns Promise<Result> and uses async/await
Suggestion: "Asynchronously parses the input and returns a Promise containing the result"
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.
- 5d ago First seen · 89 lines · 16 tokens per session scan A 0403d3db4f2f
comment-analyzer is an agent published in the GitHub repository pablo-albaladejo/kaiord (9 stars, last pushed 2d ago), licensed MIT. It adds 16 tokens to every session and 469 once invoked, about $0.0001 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 2026-08-31.
Other agents, from other repositories
angular-patterns
// Optional with default value readonly name = input ('').
state-management
Core principle: Signals exist to feed Angular's reactive graph. If a value has no reactive consumer, making it a signal adds tracking overhead for no benefit.
webc-generator
The webc-generator is an NX executor that automatically converts UI5 Web Components into Angular-native wrapper components. It eliminates manual maintenance of 100+ component wrappers by reading a Custom Elements Manifest (CEM) and generating the full library from it.
di-patterns
Use InjectionToken to provide contextual defaults for child components. This pattern allows parent components to influence default values without directly manipulating child component inputs.
nx-workflow
Purpose: Understanding the NX monorepo structure, development patterns, and best practices. For commands, see docs/internal/commands.md.
breaking-changes
A breaking change is any modification that could cause existing consumer code to fail or behave differently after upgrading.