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 steph-dove/klaussy-agents --skill rungit clone --depth 1 https://github.com/steph-dove/klaussy-agentsWrote 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/steph-dove/klaussy-agents/run)<a href="https://agentmods.dev/skills/steph-dove/klaussy-agents/run"><img src="https://agentmods.dev/badge/skills/steph-dove/klaussy-agents/run/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/steph-dove/klaussy-agents/run"><img src="https://agentmods.dev/badge/skills/steph-dove/klaussy-agents/run.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 | $0.00067 | $0.00998 |
| Opus 5 | $0.00034 | $0.00499 |
| Sonnet 5 | $0.00013 | $0.00200 |
| Haiku 4.5 | $0.00007 | $0.00100 |
Grade A, and why
{{REPO}}-run 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 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.
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.
This is a copy
97% identical to fastapi-run — 3 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 42 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Run this project's app and drive it far enough to observe the behavior the user cares about. Don't just start it and call it done — exercise the actual flow.
Steps
- Find the run command in CLAUDE.md. Read CLAUDE.md — its Commands section is the source of truth for how this project installs, builds, and runs. Look for entries labeled run / start / serve / dev, a CLI entrypoint, or a server command (this project may expose more than one, e.g. a CLI and a server — pick the one that matches what the user asked for; if it's ambiguous, ask).
- Read any
.claude/rules/*.mdwhosepaths:glob covers the code you're about to exercise — it may note required env vars, ports, or setup the command alone doesn't reveal. - Fall back to the stack only if CLAUDE.md names no run command (see the defaults below).
- Prepare the environment. Install/build first only if needed (a fresh checkout, or the run command errors on missing deps) — e.g. the editable install or
npm installfrom CLAUDE.md. If the app needs an env var, config file, or secret that isn't present, STOP and ask rather than inventing a value — a guessed secret produces a misleading failure. - Run it, matched to the app's shape:
- One-shot (CLI, script, build): invoke it directly. Start with a cheap sanity call (
--help/--version) to confirm it launches, then run a representative real command — the one that exercises the change or the behavior in question. - Long-running (web server, watcher, MCP/daemon): start it in the background, wait for its ready signal (a "listening on…" line, a health endpoint), then drive it from a second command — hit the endpoint, send a request, run the client. Tear it down when you're done; don't leave a stray process running.
- One-shot (CLI, script, build): invoke it directly. Start with a cheap sanity call (
- Observe and report. Capture the actual output — the CLI result, the HTTP response, the rendered page, the log line. State plainly what you saw and whether it matches the expected behavior. If it failed, show the real error; don't paper over it.
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 · 42 lines · 0 tokens per session scan A 44df01e39412
{{REPO}}-run is a skill published in the GitHub repository steph-dove/klaussy-agents (16 stars, last pushed 15d ago), licensed MIT. It adds 67 tokens to every session and 998 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. It is 97% identical to fastapi-run, differing in 3 lines, and is treated as a copy.
Other skills, from other repositories
tmux-real-user-testing
A real-user test workflow for Qwen Code's terminal interface, using tmux to drive the program and capture readable screen snapshots. tmux is a tool for running and observing terminal sessions.
e2e-testing
Guide for running end-to-end tests of the Qwen Code CLI, including headless mode, MCP server testing, and API traffic inspection. Use this skill whenever you need to verify CLI behavior with real model calls, reproduce user-reported bugs end-to-end, test MCP tool integrations, or inspect raw API request/response…
terminal-capture
Automates terminal UI screenshot testing for CLI commands. Applies when reviewing PRs that affect CLI output, testing slash commands (/about, /context, /auth, /export), generating visual documentation, or when 'terminal screenshot', 'CLI test', 'visual test', or 'terminal-capture' is mentioned.
agent-reproduce-align
Use after a Codex or Claude Code feature has been implemented in Qwen Code to run the selected reference agent and Qwen Code under the same scenario, capture HTTP and terminal traces, compare request bodies, tool/function schemas, outputs, and iterate until the reproduced behavior is close enough.
verify
Exercise the real app/API/CLI and collect observable evidence; tests alone do not count as end-to-end verification.
webapp-testing
Start/reuse a local app, wait for readiness, inspect rendered state/console/network, act from observed selectors, and verify with evidence.