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 u17g/timothe-ai-plugins --skill growth-calendargit clone --depth 1 https://github.com/u17g/timothe-ai-pluginsWrote 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/u17g/timothe-ai-plugins/growth-calendar)<a href="https://agentmods.dev/skills/u17g/timothe-ai-plugins/growth-calendar"><img src="https://agentmods.dev/badge/skills/u17g/timothe-ai-plugins/growth-calendar/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/u17g/timothe-ai-plugins/growth-calendar"><img src="https://agentmods.dev/badge/skills/u17g/timothe-ai-plugins/growth-calendar.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 | $0.00050 | $0.03842 |
| Opus 5 | $0.00025 | $0.01921 |
| Sonnet 5 | $0.00010 | $0.00768 |
| Haiku 4.5 | $0.00005 | $0.00384 |
Grade A, and why
growth-calendar 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 11d 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 — 289 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Timothe's Growth Calendar
Product page: Growth Calendar
Growth Calendar keeps a workspace's SEO content schedule: planned articles with publish dates, reminder notes, and the articles already generated. Each planned article has a reservation that fires on its date and writes the article without anyone being present.
The MCP tools act on the user's own workspace. Everything is scoped to the workspace their connection is bound to, so there is no tenant to choose.
Linking the user to their calendar
These tools return data, not a screen. When you report on something the user might want to look at or edit by hand, give them the link:
- The calendar itself:
https://timothe.ai/tools/growth-calendar/app - One generated article:
https://timothe.ai/tools/growth-calendar/app?article=<trackId>/<date>
The article parameter is the track id and the publish date joined by a slash, which is exactly the
pair you passed to read_article. For the "guides" track on 14 August 2026 that is
?article=guides/2026-08-14. Both values are URL-safe by schema, so nothing needs encoding.
Read before you write
Start with list_tracks, then get_calendar for the month in question. A track is the
continuing publishing line a set of planned articles belongs to; its track id carries their
language and timezone, so you cannot write a correct create_note or plan_cluster call without
knowing which tracks exist. Guessing a track id creates a second, near-duplicate track.
get_cluster_context tells you what a track's current topic cluster is about and which dates
still expect an article. Read it before proposing new topics for an existing track, otherwise you
will suggest things the plan already covers.
list_articles takes no arguments and returns every planned article and every article already
written, across all tracks, with each one's title, the query it targets and its URL slug. This is
the overlap check to run before you plan anything new: it is how you notice that the workspace
already covers a query you were about to target a second time. It reports the 100 newest planned
articles and the 200 newest written ones, and says when a list stopped at that limit, which means
older articles exist that it did not show you.
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.
- 11d ago First seen · 289 lines · 50 tokens per session scan A bb74dffe6924
growth-calendar is a skill published in the GitHub repository u17g/timothe-ai-plugins (0 stars, last pushed 1mo ago), licensed MIT. It adds 50 tokens to every session and 3,842 once invoked, about $0.0003 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…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
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…