granoflow-gfmcp-runner

granoflow-gfmcp-runner is a skill for Codex from granoflow/granoflow-mcp-server. It costs 29 tokens per session (1,352 once invoked), scanned A, original, MIT.

A local worker that checks Granoflow, a task-management system, for pending tasks marked with the GFMCP tag and sends eligible tasks to an authorized agent.

In plain words
What is it for?
Running a recurring background worker, selecting one eligible task at a time, and safely delegating it through Granoflow’s local API.
Why use it?
It lets suitable tasks continue automatically while checking authorization before sensitive steps. It also stops safely when permission is missing or uncertain.

Skill for Codex

Written for Codex: agents/openai.yaml present. Also seen: mentions Codex.

Good fit Running a recurring background worker, selecting one eligible task at a time, and safely delegating it through Granoflow’s local API.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/granoflow/granoflow-mcp-server/granoflow-gfmcp-runner
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 granoflow/granoflow-mcp-server --skill granoflow-gfmcp-runner
Clone the repo
git clone --depth 1 https://github.com/granoflow/granoflow-mcp-server

Made for: 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 granoflow-gfmcp-runner

README.md
[![agentmods](https://agentmods.dev/badge/skills/granoflow/granoflow-mcp-server/granoflow-gfmcp-runner/github.svg)](https://agentmods.dev/skills/granoflow/granoflow-mcp-server/granoflow-gfmcp-runner)
Your own site
<a href="https://agentmods.dev/skills/granoflow/granoflow-mcp-server/granoflow-gfmcp-runner"><img src="https://agentmods.dev/badge/skills/granoflow/granoflow-mcp-server/granoflow-gfmcp-runner/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 granoflow-gfmcp-runner

Your own site · 80×15
<a href="https://agentmods.dev/skills/granoflow/granoflow-mcp-server/granoflow-gfmcp-runner"><img src="https://agentmods.dev/badge/skills/granoflow/granoflow-mcp-server/granoflow-gfmcp-runner.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 29 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,352 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 $0.00029 $0.01352
Opus 5 $0.00015 $0.00676
Sonnet 5 $0.00006 $0.00270
Haiku 4.5 $0.00003 $0.00135

Measured 10d ago against content hash 9e161dc37bee, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

granoflow-gfmcp-runner 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.

The scan reads SKILL.md. This mod also ships 4 executable files (scripts/gfmcp_api.py, scripts/gfmcp_executor.py, scripts/gfmcp_runner.py, …), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

skills/granoflow-gfmcp-runner/SKILL.md · 114 lines

How it starts

The opening of the file, as written. The whole thing — 114 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Granoflow GFMCP Runner

Use this skill when installing, operating, or diagnosing the optional GFMCP automatic task worker. The worker polls Granoflow every five minutes, considers only pending tasks tagged GFMCP, and delegates one eligible task at a time to an authorized local agent.

Keyword

  • #gfmcp-runner
  • #gfmcp
  • #gfmcp-worker

Safety Contract

  • The tag is an eligibility signal, not blanket authorization.
  • Before any phase that needs authorization, re-read the delegated owner receipt and run granoflow-delegated-authorization's validator. Continue only on decision=allowed; decision=denied routes to the existing visible waiting workflow. The worker never constructs or confirms its own envelope.
  • Call POST /v1/ai-agent/gfmcp/prepare before polling. Granoflow owns the localized tag description template.
  • Call POST /v1/sync/gfmcp-safe-run before reading candidates. Granoflow decides whether cloud sync is allowed; guests continue locally and uncertain authorization fails closed.
  • Never print API tokens, task bodies, private failure details, or agent transcripts.
  • Safe local inspection and reversible workspace edits may proceed. Publishing, payment, login, external messages, destructive changes, secrets, or broadened scope require explicit user authorization.
  • Missing necessary information must be written into the task as a concise waiting/blocker note. Do not invent credentials or business choices.
  • A task is complete only after Granoflow API readback reports status=done. An agent process exit code is not completion evidence.
  • A task with Plan nodes must write and content/hash-readback Task Delivery before the final required node, then complete only through NodeService. A node-less compatibility task may use one finish call after its applicable Delivery gate.
  • Ordinary completion does not create deep Task Review or a new Card Checkpoint. It consumes the Delivery checkpoint already recorded by the task workflow.
  • An unattended worker may read linked cards and record phase candidates, but it cannot infer approval for card writes. Delegate every card search, draft, preview, confirmation, and write to granoflow-review-card-draft; record unapproved operations as deferred and never create hidden card drafts or cards.
  • An unattended worker never starts a daily review, drafts mood/efficiency notes, or writes a journal. If an interactive user separately requests one, delegate to granoflow_daily_review_skill.

Read the full file on GitHub · 114 lines

Files

What ships with it

6 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.

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. 10d ago First seen · 114 lines · 29 tokens per session scan A 9e161dc37bee

Subscribe to this mod's changes

granoflow-gfmcp-runner is a skill published in the GitHub repository granoflow/granoflow-mcp-server (0 stars, last pushed 1mo ago), licensed MIT. It adds 29 tokens to every session and 1,352 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 2026-08-31.

Related

Other skills, from other repositories

recipe-create-meet-space

Create a Google Meet meeting space and share the join link.

googleworkspace/cli · 18 tokens

workthreads

SpecStory Workthreads - a weekly work-thread rollup across a team's repos from SpecStory coding histories (any agent - Claude Code, Codex, Cursor, Gemini, and more). It groups the window's sessions into threads of work per project and labels each new / open / recently closed, so a lead sees what shipped, what is still…

specstoryai/getspecstory · 126 tokens

atmos-config

Atmos root configuration: atmos.yaml discovery, precedence, deep merging, basepath, imports, minimal bootstrap, and routing to narrower Atmos skills.

cloudposse/atmos · 31 tokens

story-readiness

Validate that a story file is implementation-ready. Checks for embedded GDD requirements, ADR references, engine notes, clear acceptance criteria, and no open design questions. Produces READY / NEEDS WORK / BLOCKED verdict with specific gaps. Use when user says 'is this story ready', 'can I start on this story', 'is…

Donchitos/Claude-Code-Game-Studios · 77 tokens

autotask-creator

Rules for automation CRUD from the group-chat commander. The commander does not call mutation tools and does not edit cloud/autotasks files directly. It emits one or more top-level ... containers in its final text; the bus parses and applies them after the turn.

Orkas-AI/Orkas · 5 tokens

projects

List all managed projects with status, branch, open PRs, and open issue counts — portfolio-level view.

me2resh/apexyard · 24 tokens