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 granoflow/granoflow-mcp-server --skill granoflow-delegated-authorizationgit clone --depth 1 https://github.com/granoflow/granoflow-mcp-serverWrote 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/granoflow/granoflow-mcp-server/granoflow-delegated-authorization)<a href="https://agentmods.dev/skills/granoflow/granoflow-mcp-server/granoflow-delegated-authorization"><img src="https://agentmods.dev/badge/skills/granoflow/granoflow-mcp-server/granoflow-delegated-authorization/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/granoflow/granoflow-mcp-server/granoflow-delegated-authorization"><img src="https://agentmods.dev/badge/skills/granoflow/granoflow-mcp-server/granoflow-delegated-authorization.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 | $0.00031 | $0.01472 |
| Opus 5 | $0.00015 | $0.00736 |
| Sonnet 5 | $0.00006 | $0.00294 |
| Haiku 4.5 | $0.00003 | $0.00147 |
Grade A, and why
granoflow-delegated-authorization 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 10d 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 — 139 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Granoflow Delegated Authorization
Use when a user wants one or more Granoflow tasks to continue while they are away or wants fewer repeated phase confirmations. The skill previews a machine-readable envelope containing separate phase grants, scope, expiry, allowed actions, forbidden actions, and invalidation rules; after explicit confirmation, hosts validate it at each gate and either continue or enter the existing visible waiting workflow.
Read granoflow-agent-workflow/unattended-interaction-contract.md first. A
direct user instruction for one bounded same-run completion uses that contract
without an envelope round trip. This skill owns the durable path when the grant
must survive an unattended interval, process restart, or later host turn.
Keyword
#delegated-authorization#unattended-task-work
When to use
- Use when the user says they will be away, asks the agent not to wait at every phase, or requests automatic continuation for bounded Granoflow tasks.
- Use when a host reaches an Analysis, Planning, Plan confirmation, or Execution gate and a delegated envelope may already exist.
- Do not use a task tag, preference, prior behavior, or inferred urgency as authorization.
- A user-origin
gf做 <bounded target>under the previously approvedgf-local-safe-v1profile is a direct conditional command, not an agent-authored delegated envelope. Use this skill only when that grant must remain durable across an unattended interval or later host turn.
Example requests
- 我离开一小时，这两个任务在 Grill 通过且不扩范围时自动继续。
- 减少确认：只允许改这两个仓库的列出文件和跑本地测试，发布和删除仍然问我。
Workflow
1. Classify the authorization request
Distinguish explicit conditional delegation from urgency, eligibility, or inferred consent.
Actions:
- Identify the exact task IDs, requested unattended interval, phase grants, local actions, repositories, and exclusions.
- Reject inferred authorization and route non-delegable actions to explicit waiting. Success criteria:
- Every proposed grant maps to an explicit user statement.
- No tag, preference, or absence signal is treated as permission. Checkpoints:
- Stop if task scope or forbidden external effects are ambiguous. Artifacts:
- authorization intent ledger
- delegable and non-delegable action split Rules:
- The skill invocation itself is never an authorization grant.
What ships with it
5 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.
- 10d ago First seen · 139 lines · 31 tokens per session scan A ef9819bed545
granoflow-delegated-authorization is a skill published in the GitHub repository granoflow/granoflow-mcp-server (0 stars, last pushed 1mo ago), licensed MIT. It adds 31 tokens to every session and 1,472 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 2026-08-31.
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…