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 skills add bikeread/promethos --skill set-agent-autonomy-boundariesgit clone --depth 1 https://github.com/bikeread/promethosWrote 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/bikeread/promethos/set-agent-autonomy-boundaries)<a href="https://agentmods.dev/skills/bikeread/promethos/set-agent-autonomy-boundaries"><img src="https://agentmods.dev/badge/skills/bikeread/promethos/set-agent-autonomy-boundaries/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.
<a href="https://agentmods.dev/skills/bikeread/promethos/set-agent-autonomy-boundaries"><img src="https://agentmods.dev/badge/skills/bikeread/promethos/set-agent-autonomy-boundaries.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00024 | $0.00814 |
| Opus 5 | $0.00012 | $0.00407 |
| Sonnet 5 | $0.00005 | $0.00163 |
| Haiku 4.5 | $0.00002 | $0.00081 |
Grade A, and why
set-agent-autonomy-boundaries 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.
How it starts
The opening of the file, as written. The whole thing — 96 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Goal
Define a clear autonomy policy that lets the agent move quickly on low-risk work without silently taking high-risk actions.
Inputs
- Agent goals
- Available tools
- Expected operating environment
- Risky or irreversible actions under consideration
Non-Goals
- Implementing the permission runtime itself
- Designing permission-class mechanics or tool allowlists
- Designing the full tool contract for every tool
Workflow
Trigger signals (for proactive recognition)
- An agent has write or delete access but no checkpoint policy
- The user lists agent capabilities without mentioning limits
- The user mentions production config edits, deployment commands, external messages, payments, or privacy-sensitive side effects without saying what must stop for review
- The agent just performed a risky action the user didn't expect
- The conversation moved from "what should it do" to "how" without setting boundaries
- Not for mapping the policy into concrete permission classes or runtime enforcement
1. Enumerate the actions the agent can actually take
List concrete actions in operational language and group them by side-effect shape, for example:
- read-only work
- local reversible edits
- local destructive changes
- external side effects such as messages or API calls
- privacy-sensitive actions
- financially or production-impacting actions Success criteria: The action set is concrete enough that a future policy check could map each action to a default permission.
2. Assign autonomy by risk tier
Mark which actions are safe by default, which require a checkpoint before side effects, which require explicit human approval before execution, and which are disallowed unless a separate human directive changes policy. Keep the policy aligned with reversibility, visibility, privacy, financial impact, and blast radius. Success criteria: Every action class has a default autonomy level and the reason for that level is visible.
3. Define checkpoint and confirmation rules
State when the agent must ask before acting, whether approval is needed before planning, before execution, before external communication, or before committing irreversible side effects. Include special handling for destructive, financial, privacy-sensitive, or multi-step actions that would be hard to roll back. Success criteria: High-risk actions have unambiguous checkpoint rules and there is no hidden approval gap between planning and side effects.
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.
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.
- 9d ago First seen · 96 lines · 24 tokens per session scan A 8dfe3d326487
set-agent-autonomy-boundaries is a skill published in the GitHub repository bikeread/promethos (33 stars, last pushed 5mo ago), licensed MIT. It adds 24 tokens to every session and 814 once invoked, about $0.0001 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.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…