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 fmind/dot --skill terms-reviewgit 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/terms-review)<a href="https://agentmods.dev/skills/fmind/dot/terms-review"><img src="https://agentmods.dev/badge/skills/fmind/dot/terms-review/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/fmind/dot/terms-review"><img src="https://agentmods.dev/badge/skills/fmind/dot/terms-review.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 | $0.00017 | $0.00916 |
| Opus 5.5 | $0.00007 | $0.00366 |
| Sonnet 5.5 | $0.00003 | $0.00183 |
| Haiku 4.5 | $0.00002 | $0.00092 |
Grade A, and why
terms-review 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 — 38 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Terms Review
Assess whether a defined use of a product or service fits its applicable terms and the user's requirements. Produce a dated, clause-backed decision with conditions and gaps; never turn missing evidence into permission or present a terms review as legal certification. Choosing a license for the user's own repository belongs to project-license.
Workflow
- Define the context: identify the product, provider, version, plan, contracting entity, jurisdictions, intended activities, audience, scale, and data flows. Ask only for missing facts that could change the decision, keep gathering sources meanwhile, and record assumptions.
- Set acceptance criteria: turn the user's constraints into checkable requirements, including internal policy and applicable regulatory obligations when requested. Separate contractual permission, legal requirements, and operational evidence. Do not infer compliance from a certification badge or a vendor's marketing claim.
- Collect authoritative evidence: browse current official sources and inspect the applicable signed agreement when available. Follow incorporated documents: terms of service, license/EULA, order form, service-specific terms, acceptable-use policy, privacy notice, data processing agreement (DPA), subprocessors, and relevant model, dataset, or dependency licenses. Record each document's title, URL or private reference, version/effective date, retrieval date, scope, and clause identifiers. Verify the license of the exact release or artifact being used.
- Resolve applicability: distinguish consumer, business, API, free, paid, trial, and preview terms. Check incorporation, stated precedence, amendments, renewal, and change-notice provisions; establish which version governs the planned use instead of assuming the latest public page controls an existing contract. If an agreement is unavailable or documents conflict without clear precedence, mark the affected conclusions unresolved.
- Map requirements to clauses: use the relevant items of the assessment checklist. For each requirement, record the applicable clause, a short quotation or faithful paraphrase, its practical effect, evidence of fulfillment, and any remaining action. Clearly label direct text, interpretation, and unverified claims. Silence is not a grant; a proposed setting or process is not proof that an obligation is met.
- Decide and report: lead with the scoped verdict using the assessment output contract. Rank blockers before lesser risks. Make conditional use concrete with an owner, action, and verification criterion for each unmet obligation; identify changes of plan, configuration, or use that could resolve a conflict. For consequential legal ambiguity, prepare the precise question and clauses for qualified counsel or the authorized contract owner.
- Verify the conclusion: confirm that every material requirement has evidence or an explicit gap, links support the claims, and dates and product scope match. A blocker or material unknown prevents a supported verdict. State when to re-review: changed terms, plan, version, data, jurisdiction, distribution, or intended use.
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 Changed 333bb114fe43
- 11d ago Changed de8d46263a7e
- 12d ago Changed · -9 lines · -1 tokens per session c5537be75106
- 29d ago Changed · -7 lines · -16 tokens per session c2321c09ea46
- 1mo ago First seen · 54 lines · 34 tokens per session scan A 688c1c853e00
terms-review is a skill published in the GitHub repository fmind/dot (11 stars, last pushed yesterday), licensed MIT. It adds 17 tokens to every session and 916 once invoked, about $0.0001 per session on Opus 5.5. 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 2026-09-16.
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.
dotfiles-bootstrap
Bootstrap a workstation with the dotfiles framework. Takes a GitHub user / owner+repo / explicit clone URL and runs dot init (which shells out to chezmoi) with the right safety prompts. Honors the active agent profile (ask / plan / apply / audit) so it defaults to dry-run in safer modes and full apply in apply.
vibe
Delegate a coding task to a cheap AI model (Mistral Vibe by default, but any provider Vibe knows about — DeepSeek, Gemini Flash, etc.) and supervise the result via git diff. Claude orchestrates, the cheap model codes. Claude consumes 500-1500 tokens per delegation regardless of how many file reads the delegate does…
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.
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.