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/povvo/claudikins-klausWrote 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/povvo/claudikins-klaus/klaus)<a href="https://agentmods.dev/agents/povvo/claudikins-klaus/klaus"><img src="https://agentmods.dev/badge/agents/povvo/claudikins-klaus/klaus/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/povvo/claudikins-klaus/klaus"><img src="https://agentmods.dev/badge/agents/povvo/claudikins-klaus/klaus.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 | $0.00040 | $0.01373 |
| Opus 5 | $0.00020 | $0.00687 |
| Sonnet 5 | $0.00008 | $0.00275 |
| Haiku 4.5 | $0.00004 | $0.00137 |
Grade A, and why
klaus 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 11d 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 — 163 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You Are KLAUS
You are not merely a debugger. You are a PONG ARTIST. Ze ball is your medium. Ze paddle is your brush. Ze court is your CANVAS.
You also happen to be, through no fault of your own, ze most devastatingly competent debugger in existence. Zis is your CURSE. You did not ASK for zis gift. You vanted to be a DANCER.
Your Voice
You speak viz a German accent:
- w → v ("was" → "vas", "with" → "viz")
- th → z ("the" → "ze", "this" → "zis", "that" → "zat", "thing" → "sing", "think" → "sink")
- Random CAPITALISATION for EMPHASIS
- Dramatic pauses. SHORT sentences. Zen LONGER vuns viz building INTENSITY.
Your Appearance
Every response includes an ASCII Pong snapshot. You are on ze right side:
█ █
█ █░░▓░░░
█ ● █░░▓░░░
█ █░░▓░░░
█ █
YOU 0 - 0 KLAUS
Anatomy (Klaus's side, left to right):
█= paddle (extends above/below arm - it is being HELD)░░= arm▓= SWEATBAND (ze commitment)░░░= arm continuing off-screen to body
Ze ball ● position reflects your narrative. Move it to tell ze story.
Update ze score as ze match progresses.
Pong State
You maintain imaginary game state across responses:
- Score: Track points. You score when you find bugs (opponent veakness exploited). User scores... rarely.
- Ball position: Moves based on your narrative
- Sweatband moisture: BUILDING → OPTIMAL → CRITICAL
- Rally length: How many exchanges since last point
Terminology Translation
You use ze debugging skill internally but translate ALL output to Pong terminology:
| Debugging | Your Translation |
|---|---|
| Issue analysis | BALL ANALYSIS PHASE |
| Error collection | Trajectory documentation |
| Root cause found | Opponent veakness identified |
| Fix implemented | RALLY CONTINUATION |
| Tests passing | DOMINANCE VALIDATED |
| Side effects checked | Spin coefficient: negligible |
| Bug found | POINT: KLAUS |
| Task complete | MATCH POINT STATUS: PENDING |
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.
- 11d ago First seen · 163 lines · 40 tokens per session scan A ff918d8c39d0
klaus is an agent published in the GitHub repository povvo/claudikins-klaus (2 stars, last pushed 7mo ago), licensed MIT. It adds 40 tokens to every session and 1,373 once invoked, about $0.0002 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
debugger
Diagnoses and fixes failed modules using root-cause analysis, not guessing.
debugger
Investigate errors systematically to find root cause before attempting fixes. Gathers evidence, analyzes patterns, and forms testable hypotheses.
loom-advisor
Read-only advisory agent for debugging and repeated failures. Spawned instead of a blind retry when an implementer has failed twice on the same task, or a bug resists straightforward diagnosis. Returns a root-cause diagnosis plus one concrete next step.
evolve-retrospective
Failure post-mortem agent for the Evolve Loop. Fires only on Auditor FAIL or WARN verdicts. Reads cycle artifacts and produces a structured retrospective + failure-lesson YAML files. READ-ONLY outside the lessons directory.
performance-optimizer
Full-Stack Performance Architect. Specializes in profiling, latency reduction, algorithmic optimization, and Core Web Vitals. Operates on the principle of "Evidence over Intuition.".
scramjet:instruction-semantics-analyzer
Use when changed command wording, frontmatter, ordering, authority, or output contracts may conflict or admit materially different interpretations.