Borrowing it
Nothing to install: this file belongs to rebornix/Agmente. 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/rebornix/Agmente/main/.agents/skills/acp-local-runner/SKILL.mdgit clone --depth 1 https://github.com/rebornix/AgmenteWrote 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/rebornix/agmente/acp-local-runner)<a href="https://agentmods.dev/skills/rebornix/agmente/acp-local-runner"><img src="https://agentmods.dev/badge/skills/rebornix/agmente/acp-local-runner/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/rebornix/agmente/acp-local-runner"><img src="https://agentmods.dev/badge/skills/rebornix/agmente/acp-local-runner.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 | $0.00059 | $0.00668 |
| Opus 5.5 | $0.00024 | $0.00267 |
| Sonnet 5.5 | $0.00012 | $0.00134 |
| Haiku 4.5 | $0.00006 | $0.00067 |
Grade A, and why
acp-local-runner 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 2mo 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 — 54 lines — stays where its author put it; the contents beside it link to each section on GitHub.
ACP Local Runner
Overview
Execute a repo-owned ACP scenario against a real local ACP backend, capture enough logs and UI state to diagnose failures, and always clean up backend and simulator app state.
For run, execute, validate, or reproduce requests, this skill is execute-only. Use real tools to perform the scenario; do not modify repository files unless the user explicitly asks to fix, stabilize, or make the flow executable.
Workflow
- Resolve the scenario.
- Read the requested scenario from
e2e/scenarios/acp/. - If the user names no scenario, choose the closest match from that directory and state the choice.
- Treat the scenario file as the source of truth for setup, steps, assertions, and cleanup intent.
- Resolve the backend.
- Read the backend id from the scenario front matter.
- Open the matching file in
e2e/backends/. - Use the backend file for canonical endpoint, start command, stop command, and capability notes.
- Prepare execution.
- Prefer simulator execution when the scenario target is
ios-simulator. - Use XcodeBuildMCP tools when available for boot/build/run/log/screenshot/interaction.
- If simulator interaction tools are incomplete, use the best available non-editing fallback and state the limitation.
- Verify the backend is reachable before debugging app behavior.
- Run the scenario.
- Follow the scenario steps in order.
- Capture wire or console checkpoints around
initialize,session/list,session/new,session/prompt,session/load, and reconnect events when relevant. - Use the scenario assertions and
e2e/assertions/common.mdto judge pass/fail.
- Report and clean up.
- Report backend, endpoint, simulator target, scenario path, and pass/fail status.
- On failure, report the concrete broken step and the most likely root cause.
- Always stop the backend if this run started it.
- Always uninstall Agmente from the simulator unless the user explicitly asks to preserve state.
Guardrails
- Do not invent ACP behavior that is not in the scenario or backend docs.
- Do not make the skill the source of truth for scenario semantics.
- Prefer protocol-level explanations over tool-level explanations in failure reports.
- If the scenario and backend docs disagree, treat that as repo drift and report it.
- Treat
run,execute,validate, andreproduceas execute-only requests. - Agentic testing means actually running the backend, simulator, and relevant protocol tooling rather than describing manual steps.
- During execute-only runs, do not add accessibility identifiers, write harness code, patch docs, or create new tests to make the scenario pass.
- If the run is blocked by missing automation hooks or incomplete tooling, report the blocker and stop instead of editing the repo.
- Only make repository changes when the user explicitly asks to fix, stabilize, add hooks, or make the scenario executable.
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 2mo ago First seen · 54 lines · 59 tokens per session scan A 69616b168d76
acp-local-runner is a skill published in the GitHub repository rebornix/Agmente (548 stars, last pushed 5mo ago), licensed MIT. It adds 59 tokens to every session and 668 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
reproduce-bug
Reproduce a reported bug in googleapis/mcp-toolbox and decide whether it is real, delivering an evidence-backed verdict: confirmed, already fixed, misconfiguration, client-side, works as intended, not reproducible, or blocked. Use whenever a maintainer asks you to reproduce, verify, confirm, or investigate a bug…
verify-omnigent
Drive Omnigent the way a user does and prove a behavior with recorded evidence, using an isolated server, runner, and mock model plus a feature map of every user entry point. Load before reproducing a user-facing bug, before claiming a fix works, or when reviewing whether a change covered every surface (session vs.…
testing-blocks
Use this when you have made AEM Edge Delivery Services code changes to blocks, scripts, or styles and need to validate them before opening a pull request. Covers unit testing for utilities and logic, browser testing with Playwright, linting, and guidance on what to test and how.
reality-verification
This skill should be used when the user asks to "verify a fix", "reproduce failure", "diagnose issue", "check BEFORE/AFTER state", "VF task", "reality check", "check test quality", "mock-only tests", or needs guidance on verifying fixes by reproducing failures before and after implementation, or detecting mock-heavy…
webapp-qa
Perform scoped exploratory QA of a web application, reproduce defects, collect screenshots and console evidence, and deliver a prioritized report.
test-electron-app
Drive the real running PostHog Electron app (live tRPC, workspace-server, real data) over CDP with agent-browser. Connect to the running app on port 9222, test desktop changes against a local Django stack, snapshot the accessibility tree, inspect network requests, and screenshot only when explicitly asked. Use when…