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 define-agent-requirementsgit 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/define-agent-requirements)<a href="https://agentmods.dev/skills/bikeread/promethos/define-agent-requirements"><img src="https://agentmods.dev/badge/skills/bikeread/promethos/define-agent-requirements/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/define-agent-requirements"><img src="https://agentmods.dev/badge/skills/bikeread/promethos/define-agent-requirements.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 | $0.00029 | $0.00765 |
| Opus 5 | $0.00015 | $0.00382 |
| Sonnet 5 | $0.00006 | $0.00153 |
| Haiku 4.5 | $0.00003 | $0.00076 |
Grade A, and why
define-agent-requirements 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 — 92 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Goal
Turn an agent idea into a clear working brief that can support architecture and implementation planning.
Inputs
- User request or agent concept
- Available environment and tools
- Constraints, risks, and success expectations
Non-Goals
- Choosing the final architecture
- Writing detailed implementation tasks
Workflow
Trigger signals
- User describes an agent idea without clear boundaries or success criteria
- User says "帮我搞个 bot", "想做个 agent", or "I want an assistant that..."
- User says "I'm not sure what the first version should do" or "what should v1 be"
- Features are listed without stating who the user is or what success looks like
- Someone skips straight to architecture, permissions, or implementation before the goal is pinned down
1. Identify the operator, beneficiary, and repeated job
State who is asking for the agent, who benefits from its work, and what job the agent is supposed to complete repeatedly. Success criteria: The agent's role is described as a concrete job, not a theme like "be helpful with coding."
2. Define the primary outcome and artifact
Decide what the agent should produce when it succeeds: a plan, code change, report, recommendation, triage result, or some other concrete artifact. Success criteria: The successful output is explicit enough that someone can tell whether the agent delivered the right thing.
3. Define the acceptance criteria
State how success will be judged in operational terms: what must be true, what quality bar must be met, and what evidence would prove the agent is doing the right job well enough. Success criteria: The brief contains explicit acceptance criteria that later architecture, planning, and verification work can inherit directly.
4. Bound the operating surface
List the agent's expected inputs, outputs, tool access, context sources, approval boundaries, and clearly out-of-scope behaviors. Success criteria: The agent's allowed working surface and forbidden actions are both visible.
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 · 92 lines · 29 tokens per session scan A c2c3d723534a
define-agent-requirements is a skill published in the GitHub repository bikeread/promethos (33 stars, last pushed 5mo ago), licensed MIT. It adds 29 tokens to every session and 765 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…
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…
chronicle
Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…