autonomy-boundary-checker

autonomy-boundary-checker is a skill for Claude Code, Codex from 45ck/skill-harness. It costs 31 tokens per session (245 once invoked), scanned A, original, MIT.

A review that sets the boundaries for what an agent may do on its own and what requires a person's approval. It considers file changes, tools, publishing, deployment, secrets, and other risky actions.

In plain words
What is it for?
Use it to classify workflows as safe to act, ask before action, proposal-only, or blocked, and to list autonomous, ask-first, and human-approval actions.
Why use it?
It reduces the chance that an agent will perform an irreversible action, access restricted data, or change permissions without a human decision. It also defines stop conditions and escalation paths.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it to classify workflows as safe to act, ask before action, proposal-only, or blocked, and to list autonomous, ask-first, and human-approval actions.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/45ck/skill-harness/autonomy-boundary-checker
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.

Any agent
npx skills add 45ck/skill-harness --skill autonomy-boundary-checker
Clone the repo
git clone --depth 1 https://github.com/45ck/skill-harness

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 autonomy-boundary-checker

README.md
[![agentmods](https://agentmods.dev/badge/skills/45ck/skill-harness/autonomy-boundary-checker/github.svg)](https://agentmods.dev/skills/45ck/skill-harness/autonomy-boundary-checker)
Your own site
<a href="https://agentmods.dev/skills/45ck/skill-harness/autonomy-boundary-checker"><img src="https://agentmods.dev/badge/skills/45ck/skill-harness/autonomy-boundary-checker/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for autonomy-boundary-checker

Your own site · 80×15
<a href="https://agentmods.dev/skills/45ck/skill-harness/autonomy-boundary-checker"><img src="https://agentmods.dev/badge/skills/45ck/skill-harness/autonomy-boundary-checker.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 31 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 245 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00031 $0.00245
Opus 5 $0.00015 $0.00122
Sonnet 5 $0.00006 $0.00049
Haiku 4.5 $0.00003 $0.00024

Measured 9d ago against content hash 2563ce02ab00, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

autonomy-boundary-checker 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 9d 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.

packs/agent-operating-skills/skills/autonomy-boundary-checker/SKILL.md · 40 lines

What it actually says

Autonomy Boundary Checker

Use this skill before allowing an agent to mutate files, run tools, publish, deploy, approve, or learn from its own output.

Checks

  • The intended autonomous actions are named.
  • Reversible actions are separated from irreversible actions.
  • External side effects are explicit.
  • Tool and data permissions match the task.
  • Human approval gates are named before risky actions.
  • The agent has a stop condition and escalation path.
  • Learning outputs are proposals until validated.

Human Approval Required

  • secret or credential handling
  • production data access
  • permission expansion
  • destructive filesystem, database, or infrastructure actions
  • network-visible publishing
  • autonomous merge, deployment, or account changes
  • security, privacy, legal, or compliance policy changes

Output

Verdict

Use safe-to-act, ask-before-action, proposal-only, or blocked.

Autonomous Actions

Ask-First Actions

Human-Approval Actions

Stop Conditions

Required Policy Changes

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. 9d ago First seen · 40 lines · 31 tokens per session scan A 2563ce02ab00

Subscribe to this mod's changes

autonomy-boundary-checker is a skill published in the GitHub repository 45ck/skill-harness (15 stars, last pushed 2mo ago), licensed MIT. It adds 31 tokens to every session and 245 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.