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-project-definitiongit 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-project-definition)<a href="https://agentmods.dev/skills/granoflow/granoflow-mcp-server/granoflow-project-definition"><img src="https://agentmods.dev/badge/skills/granoflow/granoflow-mcp-server/granoflow-project-definition/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-project-definition"><img src="https://agentmods.dev/badge/skills/granoflow/granoflow-mcp-server/granoflow-project-definition.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 | $0.00080 | $0.07115 |
| Opus 5 | $0.00040 | $0.03557 |
| Sonnet 5 | $0.00016 | $0.01423 |
| Haiku 4.5 | $0.00008 | $0.00711 |
Grade A, and why
granoflow-project-definition 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 — 583 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Granoflow Project Definition
Use this Skill when a user wants to start, define, refine, or initialize a software project in Granoflow—including Project Work, Design Baseline, and App Shell. It supports both technical users who edit one field at a time and users who provide only a vague outcome or mixed-format product documents.
Activation phrases (examples): Initialize this project,
Define this project, Start project definition, 初始化这个项目,
定义这个项目, 根据这些产品文档初始化项目并锁定设计基线.
Not this Skill: Initialize Granoflow / 初始化 Granoflow activates
granoflow-first-run-import (connection, capability packs, optional agent-data
import). Never route project definition through first-run import.
Granoflow App owns Project Work content, logical attachment identity, confirmation, readiness, hashes, design-baseline versions, and action admission. MCP is a thin protocol surface. The host Agent owns the conversation, recommendations, HTML authoring, packaging, and execution tools.
Keyword
#initialize-this-project#project-definition#design-baseline
When to use
- User asks to initialize or define this software project (not Granoflow itself).
- Need Project Work + Design Baseline (tokens + required layout-family App Shell) locked under contract fidelity before milestone/task automation.
Authority Of Initialization Outputs
The confirmed Project Work YAML plus the App-linked Design Baseline (including Design Tokens and every required layout-family App Shell) are the authoritative visual and information-architecture reference for every later milestone, task-level prototype, and code acceptance.
Later work must not invent a parallel visual authority. Changing navigation IA,
Shell mode, or locked tokens requires a new Design Baseline version and a fresh
visual confirmation. Subsequent prototypes Must declare derivedFrom the exact
baseline prototypeId / versionId / packageSha256 (document-level gate in
this release).
Acceptance bar combines contract fidelity with reference-viewport pixel-level high-fidelity:
What ships with it
34 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.
- agents/openai.yaml 738 B
- assets/device-shells/android-phone-portrait/device-shell.css 2.2 KB
- assets/device-shells/android-phone-portrait/frame.html 616 B
- assets/device-shells/device-shell-registry.json 3.8 KB
- assets/device-shells/ipad-pro-11-landscape/device-shell.css 1.9 KB
- assets/device-shells/ipad-pro-11-landscape/frame.html 544 B
- assets/device-shells/ipad-pro-11-portrait/device-shell.css 1.9 KB
- assets/device-shells/ipad-pro-11-portrait/frame.html 540 B
- assets/device-shells/iphone-17-pro-portrait/device-shell.css 2.3 KB
- assets/device-shells/iphone-17-pro-portrait/frame.html 716 B
- assets/device-shells/macos-tahoe-window/device-shell.css 2.6 KB
- assets/device-shells/macos-tahoe-window/frame.html 1.0 KB
- assets/device-shells/windows-11-window/device-shell.css 3.1 KB
- assets/device-shells/windows-11-window/frame.html 966 B
- references/design-spec-two-round-selection.md 7.6 KB
- references/device-shell-templates.md 8.8 KB
- references/hard-constraints.md 22 KB
- references/product-spec-flow-decomposition.md 8.5 KB
- references/project-artifact-workflows.md 57 KB
- references/project-definition-interaction.md 24 KB
- references/requirement-integrity-contract.md 4.0 KB
- references/shell-chrome-deck.json 2.4 KB
- references/shell-orientation-widget-contract.md 2.9 KB
- references/spec-seed-deck.json 4.7 KB
- scripts/build_option_contrast_gallery.py 12 KB runs code
- scripts/copy_device_shell_assets.py 7.0 KB runs code
- scripts/draw_visual_lots.py 11 KB runs code
- scripts/lint_design_spec_selection.py 13 KB runs code
- scripts/lint_device_shell.py 8.1 KB runs code
- scripts/lint_product_spec_coverage.py 40 KB runs code
- scripts/lint_shell_selection.py 8.0 KB runs code
- scripts/lint_task_ui_skill_pipeline.py 6.7 KB runs code
- scripts/lint_ui_component_effect_matrix.py 9.7 KB runs code
- scripts/package_prototype.py 7.8 KB runs code
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 · 583 lines · 80 tokens per session scan A 678eb21d695a
granoflow-project-definition is a skill published in the GitHub repository granoflow/granoflow-mcp-server (0 stars, last pushed 1mo ago), licensed MIT. It adds 80 tokens to every session and 7,115 once invoked, about $0.0004 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
recipe-create-meet-space
Create a Google Meet meeting space and share the join link.
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…
atmos-config
Atmos root configuration: atmos.yaml discovery, precedence, deep merging, basepath, imports, minimal bootstrap, and routing to narrower Atmos skills.
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…
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.
projects
List all managed projects with status, branch, open PRs, and open issue counts — portfolio-level view.