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 dev-toolings/superpowers-symfony --skill runner-selectiongit clone --depth 1 https://github.com/dev-toolings/superpowers-symfonyWrote 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/dev-toolings/superpowers-symfony/runner-selection)<a href="https://agentmods.dev/skills/dev-toolings/superpowers-symfony/runner-selection"><img src="https://agentmods.dev/badge/skills/dev-toolings/superpowers-symfony/runner-selection/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/dev-toolings/superpowers-symfony/runner-selection"><img src="https://agentmods.dev/badge/skills/dev-toolings/superpowers-symfony/runner-selection.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00026 | $0.00430 |
| Opus 5.5 | $0.00010 | $0.00172 |
| Sonnet 5.5 | $0.00005 | $0.00086 |
| Haiku 4.5 | $0.00003 | $0.00043 |
Grade A, and why
runner-selection 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 22d 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.
What it actually says
Runner Selection (Symfony)
Use when
- Before the first PHP, console, composer or test command of a session.
- A command fails with a missing PHP, extension or database that the container provides.
- The project uses Docker Compose, Symfony Docker (FrankenPHP), DDEV or the host and the right prefix is unclear.
- The containers may be stopped and the commands must not silently run on the host.
Default workflow
- Run the library's runtime context CLI with
--format=markdown(or--format=envfor scripts). - Read the detected Docker type (
ddev,symfony-docker, a Compose file, ornone) and whether the containers are running. - Use the prefixed console, composer and test commands it prints, such as
docker compose exec php bin/console. - If the containers are stopped, start them with the guidance it prints (
ddev startordocker compose up -d), then run it again. - Reuse the same prefix for every command in the session.
Guardrails
- Never run the host
phporcomposerwhen the project expects containers. - Do not guess the Compose service name: take it from the detected commands.
- Without a Symfony application the CLI prints nothing: say so instead of inventing a runner.
- Do not start or stop containers the task does not need.
Progressive disclosure
- Use this file for execution posture and risk controls.
- Open references when deep implementation details are needed.
Output contract
- The detected environment (Docker type, running state, test framework).
- The prefixed console, composer and test commands for this session.
References
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.
- 22d ago Changed · +2 lines a8c8488395e5
- 1mo ago Changed · +2 lines · -3 tokens per session fcb2ae064153
- 1mo ago First seen · 39 lines · 29 tokens per session scan A ed525ed1f287
runner-selection is a skill published in the GitHub repository dev-toolings/superpowers-symfony (227 stars, last pushed 22d ago), licensed MIT. It adds 26 tokens to every session and 430 once invoked, about $0.0001 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
relay-deploy
Set up a complete deployment configuration — Dockerfile, deployment manifest, environment config, and rollback procedure. Use when asked about "deployment setup", "how do I deploy this", "deployment strategy", or "rollback plan".
pave-env
Set up local development environments — devcontainers, Docker Compose, one-command setup, dev/prod parity. Use when asked to "set up dev environment", "devcontainer", "docker compose for dev", "local development setup", or "one command to run".
relay-docker
Build production-ready Dockerfiles with multi-stage builds, security hardening, and docker-compose for local dev. Use when asked to "create Dockerfile", "optimize container", or "dockerize this".
env-provisioning
Provision a fast, reproducible dev environment for QA or standalone use — healthcheck-gated boot, reuse/teardown rules, host-mode fallback. Protocol for /orc:env, /orc:qa Phase 4, /orc:flow Phase 6, and the orc-env-provisioner agent.
ccc-devops
DevOps router: CI/CD, zero-downtime deploys, Docker, AWS, Terraform, monitoring, networking, runbooks. Use to set up, harden or plan infrastructure.
docker-best-practices
Docker expert — image optimization, security hardening, multi-stage builds, orchestration, production deployment.