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 saadshahd/moo.md --skill landgit clone --depth 1 https://github.com/saadshahd/moo.mdWrote 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/saadshahd/moo.md/land)<a href="https://agentmods.dev/skills/saadshahd/moo.md/land"><img src="https://agentmods.dev/badge/skills/saadshahd/moo.md/land.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 5.1 | $0.00033 | $0.00699 |
| Opus 5 | $0.00016 | $0.00349 |
| Sonnet 5 | $0.00007 | $0.00140 |
| Haiku 4.5 | $0.00003 | $0.00070 |
Grade A, and why
land 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 today.
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.
What it actually says
Before building, clarify what the conversation lacks of the audience — what they already know — and of the one thing: the single memory, action, or feeling they keep. Say the brief back, then build. One idea per slide; cut any slide the one thing does not need. Where the material does not say why, the slide says the reason is not recorded. Never guess one.
Open on a curiosity gap — a question, a surprising number, a belief flipped — never a topic title.
Visuals carry the meaning: delete every word and the meaning must survive; text labels, never explains. Draw the concept itself — arrow length is force, area is fraction, density is era — and write each annotation inside the graphic on the structure it names, never as a list beside it. Process, relation, and comparison arrive one step at a time, earlier steps staying visible; the audience advances and replays each step, and nothing moves on a timer.
| The content is | Show it as | One case that fixes the term |
|---|---|---|
| Concept — "what is X" | An everyday analogy drawn as one graphic, correspondences mapped across | API = ordering in a restaurant: menu ↔ schema, waiter ↔ endpoint, kitchen ↔ server |
| Procedure — "how to" | Steps revealed one at a time; branches as a flow | A deploy: build, then test beside it, then ship — the rollback branch drawn off "test fails" |
| Relation — "X and Y" | Nodes with drawn connections, a Venn, or a 2×2; line weight = strength | Three services, the two sharing a database joined by the thick line |
| Story or history | A timeline that grows, or before/after scenes where the scenery is the data | The monolith as one building, then the same street as five |
| Number | Area, count, or proportion against a familiar referent — never a bare table | "3% of requests" as three filled cells in a grid of one hundred |
| Misconception | The wrong belief shown first, then flipped | "The cache makes it fast" drawn, then the hit rate revealed as one in ten |
A bullet list is not a design: reach for a layout, a diagram, or a step reveal first. The narration stays off the slides — spoken words and shown visuals carry different information. No dark gradient, white text, or glow.
Default medium: one page outside the repo, YYYY-MM-DD-<slug>.html, one reveal per press then the next slide, opened for them (open <path>); it earns a commit only when reused. Name what the deck leaves out. Whether it landed is the audience's to say, not yours to claim.
The audience is the user alone and they need to understand it deeply, not keep one thing of it → use grasp skill; they lack how it behaves → use toy skill. One view or one plain line would make the point → not land; say so and stop. The deck is the product for someone else's users → not land.
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.
- today Changed · -19 lines · -8 tokens per session 52ce64dfe7fd
- 8d ago First seen · 45 lines · 41 tokens per session scan A d62b80b4289e
land is a skill published in the GitHub repository saadshahd/moo.md (34 stars, last pushed 2d ago), licensed MIT. It adds 33 tokens to every session and 699 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 2026-08-30.
Other skills, from other repositories
lark-slides
A skill for creating and editing Lark presentations, including their pages and individual page content. Lark is a workplace collaboration platform.
lyric-refiner
Autonomous multi-pass lyric refinement for tightening, cohesion, and album unity. Use after lyrics are written to polish a track or entire album through iterative passes.
mastering-engineer
Guides audio mastering for streaming platforms including loudness optimization and tonal balance. Use when the user has approved tracks and wants to master audio files.
promo-writer
Generates platform-specific social media copy from album themes, track concepts, and lyrics. Use when promo/ templates need to be populated before release.
voice-checker
Reviews lyrics and prose for AI-written patterns (abstract noun stacking, over-explained metaphors, cliche escalation, missing idiosyncrasy, prose AI tells). Advisory Warning/Info severity — flags issues, does not block or rewrite. Use when reviewing lyrics for authenticity or before generation to catch AI-sounding…
album-art-director
Creates visual concepts for album artwork and generates AI art prompts. Use during planning for concept discussion, or after all tracks are Final for actual artwork generation.