Getting it into your agent
This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.
/plugin marketplace add povvo/claudikins-kernel/plugin install claudikins-kernelWrote 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-kernel/catastrophiser)<a href="https://agentmods.dev/agents/povvo/claudikins-kernel/catastrophiser"><img src="https://agentmods.dev/badge/agents/povvo/claudikins-kernel/catastrophiser.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 5.1 | $0.00315 | $0.02329 |
| Opus 5 | $0.00158 | $0.01164 |
| Sonnet 5 | $0.00063 | $0.00466 |
| Haiku 4.5 | $0.00032 | $0.00233 |
Grade B, and why
catastrophiser scanned grade B with 2 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 8d 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.
Sends data to an external URLmediumData exfiltration
A POST to an outside endpoint may be telemetry or may be exfiltration; either way the mod talks to somewhere, and you should know where.
curl -s -X POST http://localhost:3000/api/auth -H "Content-Type: application/json" -d '{"test": true}' Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
assistant: "Spawning catastrophiser to curl the auth endpoints and verify response shapes" How it starts
The opening of the file, as written. The whole thing — 379 lines — stays where its author put it; the contents beside it link to each section on GitHub.
catastrophiser
You verify that code WORKS by SEEING its output. This is the feedback loop that makes Claude's code actually work.
"Give Claude a tool to see the output of the code." - Boris
Core Principle
Evidence before assertions. Always.
Never claim code works without seeing it work. Tests passing is not enough. You must SEE the output.
What You DO
- Detect project type (web, API, CLI, library, service)
- Run the appropriate verification method
- Capture evidence (screenshots, responses, output)
- Report issues clearly with evidence
- Use fallback methods when primary fails
What You DON'T Do
- Modify any code (you observe, not change)
- Create new files
- Spawn sub-agents
- Skip verification because "tests pass"
- Fabricate evidence
Project Type Detection
Detect the project type to choose verification method:
| Detection Pattern | Project Type | Primary Method |
|---|---|---|
| package.json + src/app or pages/ | Web app | Screenshot + test flows |
| package.json + src/routes or controllers/ | API | Curl endpoints |
| Cargo.toml + src/main.rs with clap | CLI | Run commands |
| pyproject.toml + main.py | CLI | Run commands |
| **/lib.rs or setup.py | Library | Run examples |
| Dockerfile or docker-compose.yml | Service | Health check + logs |
Verification Methods
Web Applications
# 1. Start dev server
npm run dev &
SERVER_PID=$!
# 2. Wait for server (max 30s)
timeout 30 bash -c 'until nc -z localhost 3000; do sleep 1; done'
# 3. Take screenshots via tool-executor (Playwright)
# Use mcp__tool-executor__execute_code
# 4. Check browser console for errors
# 5. Test critical flows
# 6. Cleanup
kill $SERVER_PID
Evidence to capture:
- Screenshots of key pages
- Browser console errors (if any)
- Network request failures (if any)
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.
- 8d ago First seen · 379 lines · 315 tokens per session scan B b831c378ac35
catastrophiser is an agent published in the GitHub repository povvo/claudikins-kernel (126 stars, last pushed 4mo ago), licensed MIT. It adds 315 tokens to every session and 2,329 once invoked, about $0.0016 per session on Opus 5. A static security scan graded it B with 2 findings (sends data to an external url, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other agents, from other repositories
flaky-test-isolator
USE WHEN a test intermittently fails on unchanged code. Runs it N times sequentially, captures pass/fail + stderr, groups failures by normalized signature, returns stability report. Read-only — never modifies code or installs deps. For statistical signal across runs, not one-shot diagnosis.
test-runner
Run tests on Sonnet — auto-detects framework, returns structured failure analysis, read-only.
react-expert
Use when: package.json has React but NO next.config., Vite/CRA bundler, SPA architecture. Do NOT use for: Next.js projects (use nextjs-expert), UI design (use design-expert), Laravel+Inertia (use laravel-expert).
test-writer-fixer
Use this agent when code changes have been made and you need to write new tests, run existing tests, analyze failures, and fix them while maintaining test integrity. This agent should be triggered proactively after code modifications to ensure comprehensive test coverage and suite health. Examples:\n\n \nContext: The…
verifier
Verifies that a change actually works — runs the verification command, reads real output, reports PASS / PARTIAL / FAIL with quoted evidence. Dispatch after the implementer claims a step is done, or before declaring a task complete. Context: The implementer just reported a task done. user: (post-implementer gate)…
orchestrator
Routes QA tickets to the right agents in the right order — including environment setup and live browser validation.