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/saski/arnesto/free-agent-executionnpx skills add saski/arnesto --skill free-agent-executiongit clone --depth 1 https://github.com/saski/arnestoWrote 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/saski/arnesto/free-agent-execution)<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>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 | $0.00052 | $0.02006 |
| Opus 5 | $0.00026 | $0.01003 |
| Sonnet 5 | $0.00010 | $0.00401 |
| Haiku 4.5 | $0.00005 | $0.00201 |
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.
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 matchallowed_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 providesbounded_code.parent_run_id: a non-empty string identifying the delegating frontier run.require_changes: an optional boolean. Set it totruefor edit tasks so a non-empty explanation without an attributed file change fails visibly. Omit it or set it tofalsewhen a no-change result is valid.task_id: a non-empty string identifying this task within the delegation tree.delegation_depth: exactly1for a worker contract.
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.
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.
- 5d ago First seen · 166 lines · 52 tokens per session scan A e72e554c5579
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.
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…
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…
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.
readonly-review
Run a no-network read-only review practice with two explorer steps and one synthesis step.
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 …
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.