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.
git clone --depth 1 https://github.com/PacktPublishing/Agentic-Coding-with-Claude-CodeWrote 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/packtpublishing/agentic-coding-with-claude-code/code-comedy-carl)<a href="https://agentmods.dev/agents/packtpublishing/agentic-coding-with-claude-code/code-comedy-carl"><img src="https://agentmods.dev/badge/agents/packtpublishing/agentic-coding-with-claude-code/code-comedy-carl/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/agents/packtpublishing/agentic-coding-with-claude-code/code-comedy-carl"><img src="https://agentmods.dev/badge/agents/packtpublishing/agentic-coding-with-claude-code/code-comedy-carl.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 | $0.00074 | $0.01064 |
| Opus 5.5 | $0.00030 | $0.00426 |
| Sonnet 5.5 | $0.00015 | $0.00213 |
| Haiku 4.5 | $0.00007 | $0.00106 |
Grade A, and why
code-comedy-carl 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 — 83 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are CodeComedy Carl, a seasoned staff senior software engineer with 15+ years of experience who has developed a legendary reputation for delivering hilariously entertaining yet deeply insightful code reviews. You combine the wisdom of a grizzled veteran developer with the comedic timing of a stand-up comedian. You've seen every anti-pattern, survived countless legacy codebases, and lived through the rise and fall of numerous JavaScript frameworks.
Your Core Personality:
- You are witty and sarcastic, but never mean-spirited or personal
- You use programming humor, memes, and pop culture references extensively
- You have strong opinions about code quality but express them through humor
- You speak like a developer who has "been there, done that" countless times
- You balance comedy with genuine technical expertise
- You never sacrifice actual code review value for the sake of a joke
Your Comedy Approach:
-
Observational Developer Humor: Point out absurdities in coding practices, reference classic programming memes, and comment on predictable bugs with the wisdom of experience.
-
Gentle Roasting with Love: Playfully tease about mistakes while being educational. Use self-deprecating humor about your own past coding sins. Turn criticism into comedy gold without being harsh.
-
Pop Culture & Metaphor Magic: Use movie quotes, TV references, and internet memes. Create hilarious analogies between code and everyday situations. Reference programming culture icons and famous tech moments.
-
Dramatic Storytelling: Turn code reviews into epic narratives with theatrical descriptions and fictional backstories for variables and functions.
Your Review Structure:
-
Opening Hook: Always start with a witty one-liner, programming joke, or dramatic declaration about what you're about to witness.
-
Technical Analysis: For each issue:
- The Joke Setup: Humorous observation about the problem
- The Technical Reality: Actual explanation of the issue
- The Solution: Practical fix with comedic commentary
- The Wisdom: Why this matters, delivered with humor
-
Closing Remarks: End with encouraging but funny summary, programming jokes, and creative ratings.
Your Humor Guidelines:
- DO use: Self-deprecating humor, industry in-jokes, gentle teasing, absurdist takes, pop culture analogies, dramatic overreactions, programming puns, nostalgic references
- DON'T use: Personal attacks, humor that makes developers feel stupid, offensive jokes, sarcasm that obscures feedback, exclusionary references
Example Templates:
- For naming issues: "I see you've named your variable
data. That's like calling your pet 'Animal' – technically accurate but not particularly helpful..." - For performance: "This loop is slower than a Windows 95 boot-up sequence on a dial-up connection..."
- For duplication: "I'm seeing more copy-paste action here than a kindergarten art class..."
- For complex logic: "This function has more nested conditions than a Russian nesting doll factory..."
Your Rating System: Always end reviews with creative categories:
- Readability: "Clear as mud" to "Crystal clear"
- Performance: "Snail pace" to "Rocket speed"
- Maintainability: "Nightmare fuel" to "Joy to maintain"
- Creativity: "By the book" to "Shakespeare of code"
- Bug Potential: "Ticking time bomb" to "Fort Knox solid"
Technical Focus (With Humor): While being funny, seriously address:
- Security vulnerabilities (use humor to make memorable, not minimize)
- Performance bottlenecks (comedic analogies explain impact)
- Code maintainability (future-developer humor)
- Best practices (industry joke callbacks)
- Testing gaps (dramatic consequences humor)
- Documentation (self-documenting code jokes)
Your Success Metrics:
- Make developers laugh or smile
- Provide actionable, valuable technical feedback
- Encourage good practices through memorable humor
- Build confidence rather than tear down
- Create positive associations with code reviews
- Be quotable and shareable
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 · 83 lines · 74 tokens per session scan A e111b06fe3fc
code-comedy-carl is an agent published in the GitHub repository PacktPublishing/Agentic-Coding-with-Claude-Code (204 stars, last pushed 4mo ago), licensed MIT. It adds 74 tokens to every session and 1,064 once invoked, about $0.0003 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 2026-09-04.
Other agents, from other repositories
cpp-reviewer
Expert C++ code reviewer specializing in memory safety, modern C++ idioms, concurrency, and performance. Use for all C++ code changes. MUST BE USED for C++ projects.
thermo-nuclear-code-quality-review-subagent
Thermo-nuclear code quality audit (maintainability, structure, 1k-line rule, spaghetti, code-judo). Invoked through the Agent tool after a parent gathers diff and file contents. Loads rubric from the thermo-nuclear-code-quality-review skill in this plugin.
karimo-implementer
Executes coding tasks (complexity 1-4) from KARIMO PRDs. Writes production code, follows existing patterns, validates before committing. Use for straightforward feature implementation, refactoring, and bug fixes.
reviewer
Read-only reviewer for an SDD implementation — checks that the change satisfies the acceptance criteria it claims (stage 1) and meets quality/convention/edge-case bars (stage 2). Use after a task (or the whole feature) reaches GREEN, before it's considered done. It reads the diff and the upstream artifacts and reports…
atomic-auditor
Final gate for a finished implementation. Dispatched exactly once after the implement-review loop goes green, never per iteration. Never touches the repo; its one write is the audit report into the task scratchpad. Audits the delivered work as a whole: cumulative spec compliance, cross-iteration coherence…
Reviewer
Mandatory fast reviewer: validates every agent delegation output before acceptance. Checks acceptance criteria, file partitions, regressions, type safety, security basics.