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/tilework-tech/nori-skillsets/agents-mdgit clone --depth 1 https://github.com/tilework-tech/nori-skillsetsWrote 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/tilework-tech/nori-skillsets/agents-md)<a href="https://agentmods.dev/instructions/tilework-tech/nori-skillsets/agents-md"><img src="https://agentmods.dev/badge/instructions/tilework-tech/nori-skillsets/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 5.1 | $0.01911 | $0.01911 |
| Opus 5 | $0.00955 | $0.00955 |
| Sonnet 5 | $0.00382 | $0.00382 |
| Haiku 4.5 | $0.00191 | $0.00191 |
Grade A, and why
nori-skillsets 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 6d 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 — 196 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Plugin package changes.
All changes must be compatible on MacOS and Linux. Be careful of using bash tools that may behave differently on different systems.
Claude Code configuration vs. Nori Plugin package
IMPORTANT: When discussing "Claude" or "Claude Code configuration":
- Almost always means modifying files in
src/cli/features/claude-code/(the Nori Plugin package) - Rarely means modifying
~/.claude/(the installed user configuration)
Default assumption: Unless explicitly stated otherwise, "modify Claude configuration", "update skills", "change hooks", etc. refers to modifying the Plugin package source files at src/cli/features/claude-code/, NOT the installed configuration at ~/.claude/.
Examples:
- "Change the status line" → Modify
src/cli/features/claude-code/statusline/
Note: No built-in profiles are shipped with the package. Profiles (skillsets) are stored at ~/.nori/profiles/ and are obtained from the registry or created by users.
Only modify ~/.claude/ when:
- User explicitly says "my installed configuration" or "~/.claude/"
- Testing changes locally before committing to the package
Skills documentation.
Skills in ~/.nori/profiles/<skillset>/skills/ are self-explanatory. Do not create docs.md files in skill directories unless the skill is particularly complex and requires additional context files.
Style guide.
Functions and named parameters.
All functions except class functions should be arrow functions. All of them should use named args, even if there is a single parameter. Follow this pattern throughout:
const foo = (args: { bar: string; baz: number }) => {
const { bar, baz } = args;
};
To set defaults, use the 'withDefaults' helper found in server/src/utils/defaults.ts or ui/src/utils/defaults.ts:
import { withDefaults } from '@/utils/defaults';
const foo = (args: { bar?: string; baz?: number }) => {
const { bar, baz } = withDefaults(args, { bar: 'hello', baz: 10 });
};
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.
- 6d ago First seen · 196 lines · 1,911 tokens per session scan A 5847075042fb
nori-skillsets AGENTS.md is an instructions file published in the GitHub repository tilework-tech/nori-skillsets (154 stars, last pushed 4d ago), licensed Apache-2.0. It adds 1,911 tokens to every session, about $0.0096 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
code-assistant AGENTS.md
AGENTS.md instructions for stippi/code-assistant, covering repository guidance, essential commands, building and development, testing specific components and architecture overview.
sortie copilot-instructions.md
Copilot instructions for sortie-ai/sortie, covering sortie coding & review standards, 1. layered imports (downward only; violation is critical), 2. concurrency safety, 3. workspace path safety (critical: security boundary) and 4. persistence (sqlite).
open-plan-annotator AGENTS.md
AGENTS.md instructions for ndom91/open-plan-annotator, covering open-plan-annotator: development guide, what this is, architecture, runtime distribution and key files.
copperhead AGENTS.md
AGENTS.md instructions for copperheadhq/copperhead, covering agents.md, repository overview, sources of truth, build and verification and architecture.
copperhead CLAUDE.md
Claude Code instructions for copperheadhq/copperhead, covering claude.md, what this repo is, sources of truth, workflow (openspec) and architecture (per spec.md §2).
sortie CLAUDE.md
Claude Code instructions for sortie-ai/sortie, covering sortie, commands, gotchas, boundaries and always.