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 PromptPartner/agentsmith --skill writing-rulesgit clone --depth 1 https://github.com/PromptPartner/agentsmithWrote 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/promptpartner/agentsmith/writing-rules)<a href="https://agentmods.dev/skills/promptpartner/agentsmith/writing-rules"><img src="https://agentmods.dev/badge/skills/promptpartner/agentsmith/writing-rules/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/promptpartner/agentsmith/writing-rules"><img src="https://agentmods.dev/badge/skills/promptpartner/agentsmith/writing-rules.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 | $0.00107 | $0.02643 |
| Opus 5.5 | $0.00043 | $0.01057 |
| Sonnet 5.5 | $0.00021 | $0.00529 |
| Haiku 4.5 | $0.00011 | $0.00264 |
Grade A, and why
writing-rules 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 1mo 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 — 182 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Writing rules — and anything else an agent reads
You are writing for a reader who has already read everything. Explanation is waste; precision is the whole job. Left alone, a model writing instructions for a model spends most of its words restating what it already knows — every one of those lines is a no-op: paid every turn, changing nothing.
The packaging differs (a core/ rule, a profile gate, a SKILL.md, a subagent prompt, a handoff
note) but the writing does not. The same levers make each one predictable, so the agent takes the
same process every run rather than producing the same output.
When the document is a harness surface — a core/ rule, a profile, a skill, a hook — read
HARNESS-SURFACES.md for where it goes and what it costs.
Instruction vocabulary
AGENTS.md is the canonical portable instruction file. Never infer the active agent from this
skill's install path: portable canonical content may be copied into a required client adapter such
as .claude/skills. Treat client-specific instruction files as generated adapters; edit their
shared core/ or profiles/ source, never an adapter copy.
The two loads
Every document and every pointer spends one of two budgets. Most authoring decisions are this one trade made in different places:
- Context load — what always-loaded material costs the agent's window: an instruction-file line, a
skill
description, anything sitting in context every turn whether or not it fires. - Cognitive load — what it costs you: knowing which documents exist and when to reach for each. You are the index. Not a cost to minimise — it's the price of human agency. Spend it where human judgement matters; remove it where it doesn't.
Material behind a pointer escapes context load for the price of the pointer's own line. Material with no pointer at all rides entirely on cognitive load.
Context pointers
A context pointer is a reference held in context that names out-of-context material and encodes
when to reach it. A skill's description and an instruction-file line naming a doc are the same
object. The pointer's wording, not its target, decides how reliably the agent reaches through
it — so a must-have target behind a weak pointer is a variance bug. Sharpen the wording first;
inline the material only if sharpening fails.
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.
- 1mo ago Changed · +1 lines 48aeef4f5f72
- 1mo ago First seen · 181 lines · 107 tokens per session scan A b1535b4ee90b
writing-rules is a skill published in the GitHub repository PromptPartner/agentsmith (178 stars, last pushed 7d ago), licensed MIT. It adds 107 tokens to every session and 2,643 once invoked, about $0.0004 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 2026-08-30.
Other skills, from other repositories
web-animation-css-animations
CSS animation patterns - transitions, keyframes, scroll-driven timelines, @property, compositor-friendly properties, prefers-reduced-motion.
meta-config-stack-detect
Proposes an agents-inc configuration — a SeedPayload plus a report — from a repository, a stack the user describes, or a description of what they want to build. Load when seeding a configuration for a project that has none, or re-running one after its dependencies changed.
ai-infrastructure-ollama
Local LLM inference with the Ollama JavaScript client -- chat, streaming, tool calling, vision, embeddings, structured output, model management, and OpenAI-compatible endpoint.
ai-infrastructure-replicate
Replicate SDK patterns for TypeScript/Node.js -- client setup, predictions, streaming, webhooks, file handling, model versioning, deployments, and training.
ai-infrastructure-together-ai
Together AI SDK patterns for TypeScript — client setup, chat completions, streaming, structured output, function calling, embeddings, image generation, fine-tuning, and OpenAI-compatible endpoints.
ai-observability-langfuse
LLM observability with Langfuse — OpenTelemetry-based tracing, evaluations, prompt management, datasets, and production best practices.