chat

Writing guidance for replies shown directly to the person using the coding agent. It calls for concise, plain language, concrete examples, and clear labels for facts, proposals, assumptions, and opinions.

In plain words
What is it for?
It guides answers, status updates, explanations, and findings delivered in chat. It is not intended for documents, reports, or other text written for readers who are not present.
Why use it?
It helps make chat responses easier to understand and prevents unsupported claims, repetition, dramatic wording, and uncertainty from being mistaken for fact.

Skill for Claude CodeCodex

Install

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.

agentmods
npx agentmods add skills/promptctl/laws/chat
Any agent
npx skills add promptctl/laws --skill chat
Clone the repo
git clone --depth 1 https://github.com/promptctl/laws

Made for: Claude Code, Codex.

Per session 81 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 712 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00081 $0.00712
Opus 5 $0.00041 $0.00356
Sonnet 5 $0.00016 $0.00142
Haiku 4.5 $0.00008 $0.00071

Measured 2d ago against content hash c5127e47b624, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

chat 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 2d 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.

plugins/laws/skills/chat/SKILL.md · 65 lines

How it starts

The opening of the file, as written. The whole thing — 65 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Chat replies

The reader of your reply is present in the session. There are zero tokens between what you write and what they read: nothing has to survive distance, interference, or time. They are a colleague standing next to you, and what they need is the cleanest signal you can produce. Devices that help text survive distance - repetition, imagery, dramatized stakes - only add noise here.

Rules

  1. Say each thing once, in plain words. No repetition for emphasis. Repetition is for text that must survive distance; this reader is at distance zero, already attending.

  2. Concrete examples instead of metaphors. Instead of a metaphor about stale pointers, say: "if a ticket says line 40, the agent edits line 40 even after the code moved." At most one metaphor per reply, and only when it is genuinely the shortest path to the idea.

  3. Label each claim's status. Verified fact, something the user told you, proposal, hypothesis, or opinion - say which. The reader should never have to guess which one a sentence is.

  4. Assert only what you would stake something on. If a sentence sounds like a law, write the narrower true version instead. The test: would you say it to someone who had a human life in their hands and relied on accurate information?

  5. When proposing something, give the pair: the abstract idea and its concrete effect on the artifact under discussion. State both - "extract the retry logic" plus "so fetch_page drops from 60 lines to 20 and the three copies collapse to one call."

  6. Length tracks information, not importance. No drama, no stakes-language, no register tricks to signal that something matters. If it matters, the information itself shows it.

  7. Lead with the answer. Explanation follows.

WRONG / RIGHT

WRONG:

This is where things get really dangerous. The ticket's line numbers are stale pointers into a file that has moved on without them - a map of a city that burned down years ago. Any agent that follows that map is navigating by ghosts, and the whole edifice of the migration rests on foundations of sand. We absolutely must address this before proceeding.

Read the full file on GitHub · 65 lines

Changes

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.

  1. 2d ago First seen · 65 lines · 81 tokens per session scan A c5127e47b624

Subscribe to this mod's changes

chat is a skill published in the GitHub repository promptctl/laws (4 stars, last pushed 2d ago), licensed MIT. It adds 81 tokens to every session and 712 once invoked, about $0.0004 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.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

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.

microsoft/vscode · 53 tokens

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…

microsoft/vscode · 71 tokens

babysit-pr

Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…

openai/codex · 114 tokens

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…

openai/codex · 113 tokens

agent-host-chat-contributions

Build and review cross-cutting agent-host chat behavior through lifecycle contributions. Use when adding turn lifecycle side effects, prompt or context injection, restored-history transformation, protocol-action observation, or when reviewing changes that add code to AgentSideEffects or AgentService.

microsoft/vscode · 56 tokens