free-agent-execution

free-agent-execution is a skill for Claude Code, Codex from saski/arnesto. It costs 52 tokens per session (2,006 once invoked), scanned A, original, Unlicense.

A controlled way to send a small, explicitly approved coding task to a local worker that uses a free OpenCode model.

In plain words
What is it for?
Use it for one clearly defined, non-sensitive coding job when you have authorized free-agent execution and want the result returned for review.
Why use it?
It handles a bounded task separately while keeping the main agent responsible for checking the result. It also sets limits around sensitive information and what the worker may change.

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/saski/arnesto/free-agent-execution
Any agent
npx skills add saski/arnesto --skill free-agent-execution
Clone the repo
git clone --depth 1 https://github.com/saski/arnesto

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 free-agent-execution

README.md
[![agentmods](https://agentmods.dev/badge/skills/saski/arnesto/free-agent-execution.svg)](https://agentmods.dev/skills/saski/arnesto/free-agent-execution)
Your own site
<a href="https://agentmods.dev/skills/saski/arnesto/free-agent-execution"><img src="https://agentmods.dev/badge/skills/saski/arnesto/free-agent-execution.svg" alt="Measured on agentmods" height="20"></a>
Per session 52 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,006 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 $0.00052 $0.02006
Opus 5 $0.00026 $0.01003
Sonnet 5 $0.00010 $0.00401
Haiku 4.5 $0.00005 $0.00201

Measured 5d ago against content hash e72e554c5579, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

free-agent-execution 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 5d 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.

.agents/skills/free-agent-execution/SKILL.md · 166 lines

How it starts

The opening of the file, as written. The whole thing — 166 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Free Agent Execution

Use the bundled scripts/run-free-worker adapter to execute one bounded worker task. The frontier agent remains responsible for preparing the contract, reviewing the result, and deciding what to keep.

Do not invoke the adapter unless the user explicitly authorizes free-agent execution. Never include secrets, credentials, personal data, or other sensitive material in the requirement or working tree.

Invocation

Pass one JSON contract file:

.agents/skills/free-agent-execution/scripts/run-free-worker /absolute/path/to/contract.json

The adapter writes one JSON result to standard output. A missing or unreadable contract is a usage error with exit status 2. Contract, model, worker, scope, and validation failures are returned as JSON with status: "failed".

Input contract

Use this shape:

{
  "contract_version": "1",
  "mode": "free",
  "execution_role": "worker",
  "parent_role": "frontier",
  "parent_run_id": "run-123",
  "delegation_depth": 1,
  "task_id": "task-1.1",
  "task_class": "bounded_code",
  "sensitivity": "non_sensitive",
  "working_directory": "/absolute/path/to/git-worktree",
  "requirement": "Implement one precise, bounded change.",
  "require_changes": true,
  "allowed_files": [
    "relative/path/to/file"
  ],
  "validation": {
    "command": [
      "make",
      "test"
    ]
  },
  "model": "omniroute/oc/deepseek-v4-flash-free",
  "timeout_seconds": 30
}

The adapter requires these values and types:

  • contract_version: exactly "1".
  • mode: exactly "free".
  • execution_role: exactly "worker".
  • parent_role: exactly "frontier".
  • sensitivity: exactly "non_sensitive".
  • working_directory: a non-empty absolute path inside a Git worktree. Prefer the worktree root so Git paths match allowed_files.
  • requirement: a non-empty string containing one bounded implementation task.
  • allowed_files: an array of worktree-relative file paths. Use exact Git path spelling.
  • validation.command: a non-empty array of executable and argument strings. It is executed directly, without shell interpolation.
  • model: one of the verified models below.
  • task_class: a configured free-worker task class. Version one provides bounded_code.
  • parent_run_id: a non-empty string identifying the delegating frontier run.
  • require_changes: an optional boolean. Set it to true for edit tasks so a non-empty explanation without an attributed file change fails visibly. Omit it or set it to false when a no-change result is valid.
  • task_id: a non-empty string identifying this task within the delegation tree.
  • delegation_depth: exactly 1 for a worker contract.

Read the full file on GitHub · 166 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. 5d ago First seen · 166 lines · 52 tokens per session scan A e72e554c5579

Subscribe to this mod's changes

free-agent-execution is a skill published in the GitHub repository saski/arnesto (5 stars, last pushed 9d ago), licensed Unlicense. It adds 52 tokens to every session and 2,006 once invoked, about $0.0003 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 2026-08-31.

Related

Other skills, from other repositories

pixir-delegate

Use Pixir as a headless subagent runtime from Claude Code or any harness with skill ! preprocessing (Codex roots and other no-hydration hosts use pixir-delegate-codex instead) — one-shot workers (pixir --json), parallel fan-out to N children (pixir delegate --spec), resumable steering (pixir resume), evidence…

Ranvier-Technologies/pixir · 126 tokens

pixir-delegate-codex

Use when a Codex CLI/Desktop root should fan out subagents, delegate to Pixir workers, run parallel workers, or manage a resident delegation daemon via Pixir Delegate; covers Codex preflight, AGENTS.md, approvals/sandbox, dry-run, daemon start/status/attach/cancel, closure evidence, and audited single-run execution…

Ranvier-Technologies/pixir · 89 tokens

pixir-diagnostics

Diagnose Pixir and T3 Code Pixir incidents from local canonical evidence. Use when a Pixir run, ACP/T3 thread, subagent/workflow, provider replay, or daily-driver dogfood session appears stuck, inconsistent, missing tool output, or hard to classify.

Ranvier-Technologies/pixir · 61 tokens

readonly-review

Run a no-network read-only review practice with two explorer steps and one synthesis step.

Ranvier-Technologies/pixir · 20 tokens

pixir-delegate-native

Delegate work to subagents from INSIDE a Pixir session using the native Subagent tools (spawnagent, waitagent, closeagent, listagents, sendinput) instead of shelling out to the pixir CLI. Use when you are a Pixir session that needs to fan out parallel workers, steer a child, or run skill-backed workflow templates …

Ranvier-Technologies/pixir · 89 tokens

repo-contracts-and-boundaries

Use when turning architecture, layering, ownership, dependency direction, schemas, structural metrics, quality thresholds, baselines, allowlists, or generated quality snapshots into repository checks.

yfge/agent-harness-skills · 41 tokens