Borrowing it
Nothing to install: this file belongs to nick-pape/grackle. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/nick-pape/grackle/main/.claude/skills/test-claude-runtime/SKILL.mdgit clone --depth 1 https://github.com/nick-pape/grackleWrote 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/nick-pape/grackle/test-claude-runtime)<a href="https://agentmods.dev/skills/nick-pape/grackle/test-claude-runtime"><img src="https://agentmods.dev/badge/skills/nick-pape/grackle/test-claude-runtime/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/nick-pape/grackle/test-claude-runtime"><img src="https://agentmods.dev/badge/skills/nick-pape/grackle/test-claude-runtime.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 | $0.00053 | $0.00734 |
| Opus 5.5 | $0.00021 | $0.00294 |
| Sonnet 5.5 | $0.00011 | $0.00147 |
| Haiku 4.5 | $0.00005 | $0.00073 |
Grade A, and why
test-claude-runtime 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 — 57 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Test the Claude Code runtime
How to spawn the native claude-code runtime against an isolated test server and observe its behavior. Assumes you've started a server with /launch-grackle (and have GRACKLE_URL + GRACKLE_API_KEY exported).
Allowed model names ✅
| Model | Works? | Notes |
|---|---|---|
sonnet |
✅ | Default persona (claude-code / "Software Engineer") uses this |
opus |
✅ | |
haiku |
✅ |
No model gating — native Claude Code works out of the box (subscription/OAuth). These are the values grackle runtimes advertises and they all spawn.
Spawn it
The default persona already uses claude-code:
grackle spawn local "<prompt>" # uses default persona (claude-code / sonnet)
Or make an explicit persona (e.g. to pick opus):
grackle persona create "Claude Opus Tester" --runtime claude-code --model opus --prompt "You are a test agent."
grackle spawn local "<prompt>" --persona claude-opus-tester
⚠️ Key gotcha: native Claude Code does NOT surface real tool failures
The Claude Agent SDK runs tools internally and (in streaming mode) does not emit real tool_result blocks with is_error. The adapter instead emits synthetic empty tool_result events that are always successful (flushPendingToolResults → content: "", is_error: false).
Verified live: prompting Claude Code to run a failing command (cat /nonexistent) produced tool_result events with content: {"is_ok":true,...} (empty) — the failure was not observable. This is the separate bug 1c (filed off #1355).
Implication: you cannot demonstrate a tool failure through native claude-code. The adapter's b.is_error read (packages/runtime-claude-code/src/claude-code.ts) is only exercised when the SDK does surface tool_result blocks (some non-streaming modes). To observe a real Claude tool failure, use the ACP variant (see /test-acp-runtime — now that #1366 is fixed) — its tool_call_update carries a real status: failed (validated live).
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 · 57 lines · 53 tokens per session scan A 75546334d3a9
test-claude-runtime is a skill published in the GitHub repository nick-pape/grackle (22 stars, last pushed 4mo ago), licensed MIT. It adds 53 tokens to every session and 734 once invoked, about $0.0002 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 2026-08-30.
Other skills, from other repositories
rpa-init
Run when the user invokes /rpa-init or asks to onboard or warm up context on a repository. The agent studies code, reads documentation and test code, sets up the dev environment as the project expects, runs tests, and writes a short project report. No extra user brief is required.
rpa-gen-rules
Use when the user invokes /rpa-gen-rules or asks to create, refresh, audit, or synchronize project instructions such as root AGENTS.md, Cursor .cursor/rules, or Claude Code .claude/rules, especially when existing rule trees have drifted.
rpa-feat
Run when the user invokes /rpa-feat together with a clear feature description (for example issue text). BDD workflow: plan, failing tests, implementation, green tests, full suite, docs and examples, linter at the end. Will not work correctly without the user supplying what to build.
rpa-bugfix
Run when the user invokes /rpa-bugfix together with a clear bug description (expected vs actual, reproduction). Reproduction test first, then fix, full test suite, short report. Will not work correctly without the bug details.
code-guidelines-go
Go 1.24–1.27 coding guidelines for the dimetron/pi-go AI agent runtime. Use this skill whenever writing, reviewing, or refactoring ANY Go code in pi-go. This covers idiomatic style, error handling, concurrency, project layout, testing (table-driven, fuzz, benchmarks, synctest), new stdlib usage, golangci-lint v2…
go-127
What changed in Go 1.27 (released August 2026) and how it changes the way Go is written in pi-go. Use this skill when writing or reviewing Go that could use a 1.27 feature, when bumping the go directive in go.mod, when a build or test behaves differently after a toolchain upgrade, or when code-guidelines-go points…