Borrowing it
Nothing to install: this file belongs to miikkij/aimeat-protocol. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/miikkij/aimeat-protocol/main/.claude/skills/aimeat-writing/SKILL.mdgit clone --depth 1 https://github.com/miikkij/aimeat-protocolWrote 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/miikkij/aimeat-protocol/aimeat-writing)<a href="https://agentmods.dev/skills/miikkij/aimeat-protocol/aimeat-writing"><img src="https://agentmods.dev/badge/skills/miikkij/aimeat-protocol/aimeat-writing/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/miikkij/aimeat-protocol/aimeat-writing"><img src="https://agentmods.dev/badge/skills/miikkij/aimeat-protocol/aimeat-writing.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00000 | $0.05081 |
| Opus 5 | $0.00000 | $0.02540 |
| Sonnet 5 | $0.00000 | $0.01016 |
| Haiku 4.5 | $0.00000 | $0.00508 |
Grade A, and why
aimeat-writing 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 — 275 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Writing
Two jobs. Remove the tells that make a text read as machine-written, and write each language as that language rather than as translated English.
The tells
They are not a style preference. Every one of them is generic, adds length without adding clarity, and signals that nobody decided anything. A reader who spots two stops trusting the third.
Words to strike on sight: delve · crucial · pivotal · tapestry · foundational · robust · seamless · landscape · realm · leverage (as a verb) · underscore · testament to · navigate (when nothing is being steered).
Openers and fillers: "Here's the thing" · "Hope this helps" · "After careful consideration" · "I wanted to provide a quick update" · "It's worth noting that" · "Most people…" as a lead-in to a claim nobody measured.
Three patterns matter more than the word list, because they survive a find-and-replace:
- Negative parallelism. "It's not X, it's Y." "Not a bug, a feature." It fakes insight by pushing away a claim nobody made. Say Y. If X genuinely needs rejecting, reject it in its own sentence with a reason.
- The grand pronouncement. A short final line that reframes what was just said as something larger: "This isn't a budget. It's a statement of intent." Cut it. The paragraph already said the thing; the flourish only announces that the writer wanted an ending.
- Adverb abuse. "quietly runs", "simply add", "essentially the same", "actually works", "seamlessly integrates". The adverb is doing the work the verb should do, or hiding that no measurement was made. Strike it or replace the verb.
Two more this project keeps producing: em-dashes (use a comma, a colon or two sentences) and decorative emoji (only ✓ ✗ → ↩ carry meaning; the rest are noise, and in an app UI they read as AI slop; the same rule applies there).
Speak human. A term from the system's own vocabulary carries its meaning in the same sentence, or it does not appear. "agentAutonomy is L3 and meta.decisions is alwaysGate" tells the reader nothing; "the agent may write on its own, but decisions and gaps wait for your approval" says the same thing and can be acted on. This applies hardest when reporting to the developer: an identifier, a config key or a status enum is evidence, and the sentence still has to work without it. The same goes for a number: say what it means, not only what it is.
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 First seen · 275 lines · 0 tokens per session scan A 9ce67a1cd28b
aimeat-writing is a skill published in the GitHub repository miikkij/aimeat-protocol (7 stars, last pushed today), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 5,081 tokens. 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
coordinate-agent-work
Coordinate independent coding or research agents across host sessions and linked Git worktrees through AgentTool Collab's local journal. Use when starting or resuming credential-bound coordination, publishing optional self-declared presence, splitting parallel work, preventing overlapping edits, polling or…
capability-conductor
A guide for finding and combining existing agent skills for one task while keeping track of where each skill came from and what limits it has.
nen-math-card
Frame a mathematical challenge as a bounded proof, model, or measurement inquiry and decide whether it can construct, repair, choose, or clarify anything. Use when a user asks whether a math problem is useful, wants to turn a competition or puzzle into reusable understanding, needs to separate formal proof from world…
nen-common-ground
Model several explicitly stated decision boundaries as convex feasible regions and return either shared room, a small conflict witness, or an honest refusal of the model. Use when the user invokes Helly, common-ground geometry, 共域, local-to-global agreement, constraint reconciliation, or a KINGDOM challenge about…
scriptwriter-room
Focused on writers' room operations — creating rooms with a seed prompt, contributing signed scenes/dialogue/stage-directions/twists/chaos-cards/notes, subscribing to the SSE live stream, polling for new contributions. Use when the user wants to actually draft something with peers, draw a chaos card to seed a scene…
scriptwriter-rrr
Focused on the REAL RECOGNISE REAL cascade flow specifically — opening cascades with a peer, escalating depth, verifying chains, surfacing wall refusals with their meaning. Use when the user explicitly references RRR depth, cascade verification, alternation walls, or the "I know you know I know" mutual-recognition…