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 instructions/thematters/matters-web/agents-mdgit clone --depth 1 https://github.com/thematters/matters-webWrote 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/instructions/thematters/matters-web/agents-md)<a href="https://agentmods.dev/instructions/thematters/matters-web/agents-md"><img src="https://agentmods.dev/badge/instructions/thematters/matters-web/agents-md.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 | $0.00888 | $0.00888 |
| Opus 5 | $0.00444 | $0.00444 |
| Sonnet 5 | $0.00178 | $0.00178 |
| Haiku 4.5 | $0.00089 | $0.00089 |
Grade A, and why
matters-web AGENTS.md 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 — 83 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Basic
a. Never speculate. Investigate and confirm the facts before writing any code. b. Related Matters repositories for reference are at https://github.com/orgs/thematters/repositories c. If a requirement is ambiguous, or the existing architecture cannot solve the problem elegantly, ask the developer first instead of modifying core low-level modules on your own.
Development
a. TypeScript is the primary language; write components as function components with arrow functions. b. Do not write an if-else on a single line. c. Write comments in English and only on the important parts. Keep them short and clear; avoid over-commenting. d. After every change, run lint and format, including tsc type check, next lint and stylelint. e. After every change, add or update the matching vitest unit test or playwright e2e test and make sure they pass. f. Install non-essential packages as devDependencies to keep them out of runtime; lint, prettier, test tools such as vitest and playwright, storybook and other design or build tooling must not appear in dependencies.
Imports
a. Use the path aliases ~/ for src and @/ for the project root; a parent reference such as ../ is fine, but avoid deep relative paths. b. Import and export order is sorted automatically by simple-import-sort; do not reorder by hand.
GraphQL and codegen
a. Types are generated into src/gql/graphql.ts; do not edit it by hand, it is ignored by eslint. b. Before making changes, sync to the latest schema as much as possible first. c. After changing a query or mutation, run gen:type to regenerate the types. d. Write operations with gql and split them with fragments where it helps.
i18n
a. Use react-intl FormattedMessage or intl.formatMessage for all copy; do not hardcode strings. b. Every message needs a defaultMessage and an auto-generated id; the formatjs eslint rules enforce this. c. After changing copy, run i18n to re-extract, generate and compile.
Styling
a. Style with CSS Modules, one styles.module.css per component, referencing classes through the styles object; avoid inline styles. b. Follow the stylelint rules; order properties by recess-order. c. Reuse the design system's existing CSS as much as possible; do not duplicate the same styles in styles.module.css.
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 · 83 lines · 888 tokens per session scan A 2faa8a41c601
matters-web AGENTS.md is an instructions file published in the GitHub repository thematters/matters-web (86 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 888 tokens to every session, about $0.0044 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 instructions, from other repositories
windmill AGENTS.md
AGENTS.md instructions for windmill-labs/windmill, covering windmill, workflow, documentation, dev environment and per-worktree ports and database.
kubara AGENTS.md
AGENTS.md instructions for kubara-io/kubara, covering ai agent context, scope, product intent (stable), truth hierarchy and reference map.
sdks AGENTS.md
AGENTS.md instructions for morpho-org/sdks, covering engineering rules, 1. architecture, layering: one direction, no exceptions, modularity: one reason to exist and testability: pure cores, i/o at the edge.
skills docs.instructions.md
Instructions for apollographql/skills, covering preamble, primary directive, voice, language and framing.
agentarea AGENTS.md
AGENTS.md instructions for agentarea/agentarea, covering agents.md, where to look, structure, commands and backend (from agentarea-platform/).
windmill CLAUDE.md
Claude Code instructions for windmill-labs/windmill, a project described as: Open-source developer platform to power your entire infra and turn scripts into webhooks, workflows and UIs. Fastest workflow engine (13x vs Airflow). Open-source alternative to Retool and Temporal.