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/msolecki/founder-os/content-plannpx skills add msolecki/founder-os --skill content-plangit clone --depth 1 https://github.com/msolecki/founder-osWrote 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/msolecki/founder-os/content-plan)<a href="https://agentmods.dev/skills/msolecki/founder-os/content-plan"><img src="https://agentmods.dev/badge/skills/msolecki/founder-os/content-plan.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 | $0.00032 | $0.02443 |
| Opus 5 | $0.00016 | $0.01222 |
| Sonnet 5 | $0.00006 | $0.00489 |
| Haiku 4.5 | $0.00003 | $0.00244 |
Grade A, and why
content-plan 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 4d 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 — 190 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Content Plan
Publishing to nobody in particular is a hobby. It is a defensible hobby — but it should not be filed under business development, and the founder currently files it there.
The second thing this skill exists to stop: the plan that commits to three posts a week. That founder publishes for four weeks and then stops for a year, and the year of silence is caused by the plan, not by the founder's discipline.
When to use
Weekly. Fired by the local scheduler on Wednesdays after setup-cadences;
otherwise run content-plan by hand. Also when
the founder has gone quiet for a month, or has a plan and nothing to say — which
means the plan was built from topics rather than from questions.
Weekly does not mean re-planning weekly. The plan is a rolling four-week horizon and most Wednesdays touch one week of it: fill the week that just came into view, mark what shipped, cut what died. A skill that rewrites the whole plan every Wednesday has never let a plan survive contact with a week, and the founder learns the plan is provisional — at which point it stops being a commitment and becomes a suggestion they are already behind on.
Inputs
Read first, in order — house rule 1:
content.md— the## Shippedlist. What actually went out, not what was scheduled. The trailing four weeks of it set the cadence and nothing else does.offer.md— the ICP, the trigger, the offer. Every piece serves this or it is out.pipeline.md— what prospects actually asked on calls. These are the posts.content.md## Audience— the verbatim quotes fromaudience-research
Beliefs
- The founder is not the audience, and the piece they most want to write is the one nobody asked for. Wanting to write it is a fact about the founder's week, not a signal from the market.
- Nobody is waiting. No reader has ever noticed a missed week — the disappointed audience the founder pictures does not exist, and the cadence is a constraint on the founder rather than a promise to anybody.
- A piece a stranger nods at is worth less than one six people argue with and one person books a call about. Agreement is what writing gets when it has not claimed anything, and the founder will read it as the piece having gone well.
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.
- 4d ago First seen · 190 lines · 32 tokens per session scan A 90d755f2000a
content-plan is a skill published in the GitHub repository msolecki/founder-os (4 stars, last pushed yesterday), licensed MIT. It adds 32 tokens to every session and 2,443 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 2026-08-31.
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…
chronicle
Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…
imagegen
Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…
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…