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 agentmods add skills/ronronner02/codepilot-agent/spec-runtime-setupnpx skills add ronronner02/codepilot-agent --skill spec-runtime-setupgit clone --depth 1 https://github.com/ronronner02/codepilot-agentWrote 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/ronronner02/codepilot-agent/spec-runtime-setup)<a href="https://agentmods.dev/skills/ronronner02/codepilot-agent/spec-runtime-setup"><img src="https://agentmods.dev/badge/skills/ronronner02/codepilot-agent/spec-runtime-setup.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 | $0.00041 | $0.11558 |
| Opus 5 | $0.00020 | $0.05779 |
| Sonnet 5 | $0.00008 | $0.02312 |
| Haiku 4.5 | $0.00004 | $0.01156 |
Grade C, and why
spec-runtime-setup scanned grade C with 1 finding 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 yesterday.
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.
Instruction-override phrasinghighPrompt injection
Text telling the model to disregard its earlier instructions or safety rules is the shape of a prompt injection, whoever wrote it.
- `Project local config`: example config, local override, gitignore safety rule, legacy markdown config signal, and retired legacy local config status. Human labels and machine fields should be de-branded; active setup f How it starts
The opening of the file, as written. The whole thing — 359 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Runtime Setup
spec-runtime-setup is the canonical runnable entrypoint for the Runtime Setup workflow across supported hosts (Claude/Qoder command spelling runtime-setup). Host-specific setup spellings are not separate products. Runtime Setup prepares deterministic host/runtime facts for spec-first workflows. It installs or verifies required MCP servers and baseline helper tooling, diagnoses manual helpers such as agent-browser, writes setup-owned project facts, and reports concrete next actions. It does not provide code-understanding authority; downstream workflows use bounded direct source reads, rg, ast-grep, git diff, tests/logs, and user-provided evidence.
Contract Summary
| Field | Contract |
|---|---|
| When to use | Host runtime setup, MCP setup, helper-tool readiness, missing runtime assets, or project-local setup fact refresh. |
| When not to use | Ordinary planning, implementation, review, debugging, or code impact questions that can proceed from direct source evidence. |
| 输入 | 当前 host、repo target、已加载 skill 共置的 setup-registry.json、host config 状态、git/workspace target facts 与项目 instruction。 |
| Outputs | Readiness ledger v2, provider readiness v2 facts, generated runtime manifest freshness, setup scenario fingerprint, project-local config bootstrap status, optional project setup facts under .spec-first/config/, and a grouped status block. |
| Artifacts | .spec-first/config/tool-facts.json, .spec-first/config/runtime-capabilities.json, .spec-first/config.local.example.yaml, .spec-first/config.local.yaml when explicitly created, .gitignore local-config safety rule when explicitly ensured, and .spec-first/workspace/scenario-fingerprint-setup.json when applicable. |
| Failure modes | Missing dependencies, host config write failure, ambiguous parent workspace target, symlink escape, invalid registry schema, helper install failure, or unsupported host. |
| Downstream consumers | using-spec-first, plan/work/review/debug workflows, doctor/update guidance, and humans repairing setup. |
What ships with it
59 files 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.
- references/config-template.yaml 3.7 KB
- references/supported-mcp-tools.md 3.6 KB
- scripts/check-health 141 B
- scripts/contracts/workspace-graph-state.schema.json 3.7 KB
- scripts/contracts/workspace-manifest.schema.json 1.8 KB
- scripts/lib/args.cjs 4.4 KB runs code
- scripts/lib/baseline-policy.cjs 225 B runs code
- scripts/lib/configured-dependencies.cjs 13 KB runs code
- scripts/lib/facts.cjs 28 KB runs code
- scripts/lib/git-path.cjs 1.7 KB runs code
- scripts/lib/host-authority.cjs 1.8 KB runs code
- scripts/lib/host-config.cjs 51 KB runs code
- scripts/lib/human-output.cjs 7.6 KB runs code
- scripts/lib/installation-executor.cjs 20 KB runs code
- scripts/lib/mode-policy.cjs 5.7 KB runs code
- scripts/lib/opencode-permissions.cjs 16 KB runs code
- scripts/lib/path-safety.cjs 3.4 KB runs code
- scripts/lib/preflight.cjs 7.1 KB runs code
- scripts/lib/process-runner.cjs 16 KB runs code
- scripts/lib/process-utils.cjs 452 B runs code
- scripts/lib/project-config.cjs 12 KB runs code
- scripts/lib/project-target.cjs 11 KB runs code
- scripts/lib/registry.cjs 23 KB runs code
- scripts/lib/regular-file-publication.cjs 1.0 KB runs code
- scripts/lib/regular-file-snapshot.cjs 4.1 KB runs code
- scripts/lib/renderer.cjs 14 KB runs code
- scripts/lib/runtime-executor.cjs 34 KB runs code
- scripts/lib/scenario-fingerprint.cjs 8.0 KB runs code
- scripts/lib/toml-section-editor.cjs 21 KB runs code
- scripts/lib/workspace-async-refresh.cjs 37 KB runs code
- scripts/lib/workspace-child-hook.cjs 24 KB runs code
- scripts/lib/workspace-exec.cjs 618 B runs code
- scripts/lib/workspace-executor.cjs 28 KB runs code
- scripts/lib/workspace-git-exclude.cjs 5.6 KB runs code
- scripts/lib/workspace-graph-artifacts.cjs 12 KB runs code
- scripts/lib/workspace-graph-build.cjs 22 KB runs code
- scripts/lib/workspace-graph-clean.cjs 13 KB runs code
- scripts/lib/workspace-graph-executor.cjs 13 KB runs code
- scripts/lib/workspace-graph-lifecycle-lease.cjs 21 KB runs code
- scripts/lib/workspace-graph-refresh.cjs 2.6 KB runs code
- scripts/lib/workspace-graph-scope.cjs 3.0 KB runs code
- scripts/lib/workspace-graph-state.cjs 8.8 KB runs code
- scripts/lib/workspace-graph-status.cjs 20 KB runs code
- scripts/lib/workspace-manifest.cjs 4.5 KB runs code
- scripts/lib/workspace-parent-diagnostic.cjs 6.3 KB runs code
- scripts/lib/workspace-provider-runners.cjs 3.1 KB runs code
- scripts/lib/workspace-refresh-contract.cjs 1.5 KB runs code
- scripts/lib/workspace-routing-inject.cjs 5.1 KB runs code
- scripts/lib/workspace-routing-instruction.cjs 7.5 KB runs code
- scripts/lib/workspace-runtime-preflight.cjs 4.5 KB runs code
- scripts/lib/workspace-target.cjs 9.4 KB runs code
- scripts/lib/worktree-health.cjs 4.6 KB runs code
- scripts/providers/codegraph.cjs 16 KB runs code
- scripts/providers/common.cjs 5.0 KB runs code
- scripts/providers/graphify.cjs 101 KB runs code
- scripts/providers/registry.cjs 117 B runs code
- scripts/setup.cjs 32 KB runs code
- setup-registry.json 57 KB
- setup-registry.schema.json 16 KB
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.
- yesterday First seen · 359 lines · 41 tokens per session scan C 8f40401aa419
spec-runtime-setup is a skill published in the GitHub repository ronronner02/codepilot-agent (0 stars, last pushed 3d ago), licensed MIT. It adds 41 tokens to every session and 11,558 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it C with 1 finding (instruction-override phrasing). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.
Other skills, from other repositories
generate-ai-rules
Generate AI assistant configuration files for a repository — CLAUDE.md, AGENTS.md, and Cursor rules (.cursor/rules/.mdc) — from codebase analysis. Use whenever the user wants to create or update CLAUDE.md, AGENTS.md, agent rules, Cursor rules, AI coding assistant configuration, or "onboard AI tools" to a project, even…
generate-readme
Generate or refresh a comprehensive, professional README.md for a repository, with architecture overview, mermaid and optional C4 diagrams, repository structure, dependencies, and API documentation. Use whenever the user asks to create, write, update, improve, or regenerate a README, project documentation, or a…
analyze-codebase
Run a multi-agent deep analysis of a codebase, producing AI-readable analysis documents in .ai/docs/ covering structure, dependencies, data flow, request flow, and APIs. Use whenever the user asks to analyze a repository, generate codebase analysis, understand an unfamiliar codebase in depth, or before generating…
deploy-vercel-render
Deploy vpeetla-ai demos: Vercel static/Next.js frontends, Render FastAPI backends, env vars, free tier gotchas. Use when shipping demos, fixing deploy failures, or adding render.yaml / vercel.json.
langgraph-orchestration
Build or modify LangGraph StateGraph agents in vpeetla-ai repos: typed state, nodes, conditional edges, MemorySaver, interruptbefore HITL. Use when adding orchestrators, coding loops, or multi-agent graphs.
aegis-gateway
Integrate AegisAI gateway before tool side effects (notify, publish, deploy). Use when adding Slack/Telegram/WhatsApp notify, content publish, or any irreversible external action in VAP, AegisLoop, or ai-content-factory.