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 agentmods add skills/fmind/dot/project-licensenpx skills add fmind/dot --skill project-licensegit clone --depth 1 https://github.com/fmind/dotWrote 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/fmind/dot/project-license)<a href="https://agentmods.dev/skills/fmind/dot/project-license"><img src="https://agentmods.dev/badge/skills/fmind/dot/project-license.svg" alt="Measured on agentmods" 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 | $0.00048 | $0.00818 |
| Opus 5 | $0.00024 | $0.00409 |
| Sonnet 5 | $0.00010 | $0.00164 |
| Haiku 4.5 | $0.00005 | $0.00082 |
Grade A, and why
project-license 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 yesterday.
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 — 43 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Project License
Select, write, and declare the LICENSE a repository needs from its namespace, visibility, and content; github-repository owns the remaining repository settings.
Workflow
- Detect the namespace:
git remote -v, the manifest (pyproject.toml,go.mod,package.json), or the parent directory gives the owning organization or user. - Read the existing license first:
ls LICENSE*andgh repo view --json nameWithOwner,isPrivate,licenseInfo; an existing license stays unless the user asked to replace it. - Select the license:
- Public code under
fmind,fmind-ai, ormlops-courses: MIT, from MIT. - Written course material (lessons, exercises, prose): CC-BY-4.0 as
LICENSE.txt, from CC-BY-4.0;mlops-courses/mlops-coding-courseis the reference example. - Every private repository and every other namespace: proprietary, from PROPRIETARY; never an open-source license.
- Public code under
- Write the file at the repository root:
- Copyright holder from the namespace:
fmindandfmind-aiuseMédéric Hurier (Fmind);mlops-coursesusesMLOps Courses. When unsure, copy the holder from a sibling repository. - Resolve
<year>to the current calendar year (date +%Y).
- Copyright holder from the namespace:
- Declare it in the manifest:
- Python: PEP 639 SPDX
license = "MIT"orlicense = "LicenseRef-Proprietary"pluslicense-files = ["LICENSE"]inpyproject.toml. - Node:
"license": "MIT"or"UNLICENSED"inpackage.json; Go has no manifest field.
- Python: PEP 639 SPDX
Gotchas
- Namespace is not ownership:
mlops-coursesrepositories are public and MIT although the namespace is neitherfmindnorfmind-ai; a namespace-only rule would relicense them as proprietary. LICENSE.txt: a course repository may carryLICENSE.txt; writingLICENSEnext to it leaves two conflicting licenses.- Code and prose differ: one course organization holds both, MIT for code repositories and CC-BY-4.0 for the written course; check what the repository publishes.
- SPDX only: plain
"Proprietary"is not a valid SPDX expression and modern build tools reject it; useLicenseRef-Proprietary.
What ships with it
3 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.
- yesterday First seen · 43 lines · 48 tokens per session scan A 2616c9cfa7a1
project-license is a skill published in the GitHub repository fmind/dot (4 stars, last pushed yesterday), licensed MIT. It adds 48 tokens to every session and 818 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 2026-09-03.
Other skills, from other repositories
project-license
Select and generate the correct LICENSE — MIT for public fmind/fmind-ai repos, otherwise proprietary — and update project manifests. Use when adding or fixing a project's license.
go-stack
Build Go projects, libraries, CLIs, TUIs, web apps, or ADK agents with the standard package layout and pinned tooling.
python-stack
Build typed Python projects with uv, Ruff, ty, pytest, Litestar, and Typer. Use for packages, CLIs, web apps, tests, typing, or API verification.
chezmoi
Manage chezmoi dotfiles: source naming, Go templates, age-encrypted secrets, and the edit-source then apply/diff workflow.
hugo
Canonical Hugo static-site stack with the Hextra docs theme — Hugo Modules, mise tasks, dprint, lefthook, and GitHub Pages deploy. Use for documentation sites, project docs, and static websites.
k8s-local
Create and manage local Kubernetes clusters (k3d or kind) and deploy to them with kubectl, helm, helmfile, and skaffold. Use for local k8s cluster setup, dev loops, and debugging.