agentmods.dev

create-runfile

A guide for creating and repairing Kilroy run configuration files, which define how a workflow is executed.

In plain words
What is it for?
Use it to author run.yaml or run.json files, align providers with a DOT graph, choose production or test-shim mode, and fill the required configuration fields.
Why use it?
It prevents the run settings from disagreeing with the workflow graph's models, providers, or execution mode. It also makes runtime, testing, preflight, model, Git, and storage choices explicit.

Skill for Claude CodeCodex

218 4mo ago A scan 30 tokens original MIT
View the source file danshapiro/kilroy
Install

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.

agentmods
npx agentmods add skills/danshapiro/kilroy/create-runfile
Any agent
npx skills add danshapiro/kilroy --skill create-runfile
Clone the repo
git clone --depth 1 https://github.com/danshapiro/kilroy

Made for: Claude Code, Codex.

Per session 30 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,229 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00030 $0.01229
Opus 5 $0.00015 $0.00615
Sonnet 5 $0.00006 $0.00246
Haiku 4.5 $0.00003 $0.00123

Measured 3d ago against content hash f69609c56289, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

create-runfile 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 3d 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.

skills/create-runfile/SKILL.md · 107 lines

How it starts

The opening of the file, as written. The whole thing — 107 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Create Runfile

Scope

This skill owns run config authoring (run.yaml / run.json) for kilroy attractor run and resume.

In scope:

  • Building config structure (version: 1 schema).
  • Aligning provider backends with DOT model/provider usage.
  • Setting runtime, preflight, modeldb, git, and CXDB defaults.

Out of scope:

  • DOT graph authoring and routing design. Use create-dotfile for graph work.

Overview

Core principle:

  • Keep execution policy in run config, not in DOT topology.
  • Align run config with what the graph needs to execute now.
  • Favor explicit, deterministic defaults over implicit behavior.

Default run-config source:

  • skills/create-runfile/reference_run_template.yaml

Workflow

  1. Collect inputs.
  • Read the target DOT graph and detect provider usage (llm_provider attrs and model_stylesheet).
  • Capture user constraints for production/test mode and backend policy.
  1. Choose run mode explicitly.
  • Production mode: llm.cli_profile: real and no test-shim flags.
  • Test mode: llm.cli_profile: test_shim with shim-compatible provider config.
  1. Start from the template and fill required fields.
  • Required: version, repo.path, cxdb.binary_addr, cxdb.http_base_url, modeldb.openrouter_model_info_path.
  • Keep absolute paths for repo/modeldb/script entries.
  • Emit only fields supported by internal/attractor/engine/config.go.
  • Unknown keys are rejected at load time; do not emit unsupported keys.
  1. Align providers with DOT.
  • For every provider used by DOT, set llm.providers.<provider>.backend (api or cli).
  • Do not edit DOT to force backend execution strategy.

4.5 Resolve model names deterministically when catalogs are unavailable.

  • Model resolution order: user-specified model -> run snapshot/modeldb path -> internal/attractor/modeldb/pinned/openrouter_models.json -> internal/attractor/modeldb/manual_models.yaml -> skills/shared/model_fallbacks.yaml.
  • Use skills/shared/model_fallbacks.yaml only as backup; never let backup entries override explicit user model/provider choices.
  • Normalize known aliases through fallback mappings before emitting YAML (for example provider zai: glm-5.0 -> glm-5).

Read the full file on GitHub · 107 lines

Files

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.

Changes

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.

  1. 3d ago First seen · 107 lines · 30 tokens per session scan A f69609c56289

Subscribe to this mod's changes

create-runfile is a skill published in the GitHub repository danshapiro/kilroy (218 stars, last pushed 4mo ago), licensed MIT. It adds 30 tokens to every session and 1,229 once invoked, about $0.0002 per session on Opus 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.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

brainstorming

You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.

obra/superpowers · 37 tokens

auto-perf-optimize

Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.

microsoft/vscode · 62 tokens

chat-perf

Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.

microsoft/vscode · 51 tokens

chat-pet-sprite-creation

Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.

microsoft/vscode · 53 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens