skill-runner

skill-runner is a skill for Claude Code, Codex from MiaoDX/intuitive-flow. It costs 45 tokens per session (998 once invoked), scanned A, original, MIT.

A tool for running bounded development tasks through named skills in an isolated Codex or Claude session. It keeps logs and result files for tasks that need supervision or durable output.

In plain words
What is it for?
Use it to launch supervised worker tasks, assign owned paths and acceptance checks, monitor progress, and collect a final status.
Why use it?
It reduces the risk of losing progress or unclear results during long-running, artifact-sensitive work.

Skill for Claude CodeCodex

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/miaodx/intuitive-flow/skill-runner
Any agent
npx skills add MiaoDX/intuitive-flow --skill skill-runner
Clone the repo
git clone --depth 1 https://github.com/MiaoDX/intuitive-flow

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for skill-runner

README.md
[![agentmods](https://agentmods.dev/badge/skills/miaodx/intuitive-flow/skill-runner.svg)](https://agentmods.dev/skills/miaodx/intuitive-flow/skill-runner)
Your own site
<a href="https://agentmods.dev/skills/miaodx/intuitive-flow/skill-runner"><img src="https://agentmods.dev/badge/skills/miaodx/intuitive-flow/skill-runner.svg" alt="Measured on agentmods" height="20"></a>
Per session 45 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 998 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 $0.00045 $0.00998
Opus 5 $0.00023 $0.00499
Sonnet 5 $0.00009 $0.00200
Haiku 4.5 $0.00005 $0.00100

Measured 3d ago against content hash 79e0fcec7740, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

skill-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 3d ago.

The scan reads SKILL.md. This mod also ships 2 executable files (scripts/run_skill_runner.py, scripts/summarize_skill_runner_runs.py), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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/skill-runner/SKILL.md · 115 lines

How it starts

The opening of the file, as written. The whole thing — 115 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Skill Runner

Use skill-runner when an isolated worker needs durable logs, compact result artifacts, explicit path ownership, or supervision across a long task. Small read-only probes and tiny edits should stay on the host-approved lighter route.

Read references/codex-delegation.md before choosing a Codex worker surface. That file is the canonical policy for Paseo probing, native subagent disablement, and tmux fallback.

Launch Contract

Before launch, define:

  • objective and named skills;
  • owned paths and non-goals;
  • the smallest context package;
  • task-specific acceptance and verification;
  • stop conditions and final RESULT_STATUS contract;
  • review cadence for long-running work.

Use the runner's own help as the option source of truth:

uv run python skills/skill-runner/scripts/run_skill_runner.py --help

Codex prompt workers inherit the current Codex provider configuration and auth by default. This keeps ordinary supervised runs on the same working route as the parent session. Provider bakeoffs must pass --codex-config-mode isolated; that mode ignores user config and uses the explicit provider, base URL, env-key, and wire-API arguments supplied by the bakeoff runtime.

Launch from the target repo and pass the worker prompt after --. Use --dry-run first when validating a new agent, model, launch mode, or ownership split. Use --dangerous only with explicit authorization. Do not infer missing acceptance criteria or credentials just to make a worker start.

The script writes runs under ~/.cache/skill-runner/runs/ by default. Inspect compact artifacts before full logs:

  • result.md: normalized task result and blocker reason;
  • eval.md: scope, diff, proof, and ownership review;
  • skill-review.md: reusable skill feedback, advisory only;
  • run.json: selected agent, workspace, owned paths, and sandbox posture;
  • terminal.log: debugging evidence when compact artifacts disagree.

For batch review, use the summarizer's help rather than duplicating its options here:

Read the full file on GitHub · 115 lines

Files

What ships with it

3 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.

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 · 115 lines · 45 tokens per session scan A 79e0fcec7740

Subscribe to this mod's changes

skill-runner is a skill published in the GitHub repository MiaoDX/intuitive-flow (48 stars, last pushed 8d ago), licensed MIT. It adds 45 tokens to every session and 998 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.