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/getlytos/lytos-cli/claude-mdgit clone --depth 1 https://github.com/getlytos/lytos-cliWrote 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/getlytos/lytos-cli/claude-md)<a href="https://agentmods.dev/instructions/getlytos/lytos-cli/claude-md"><img src="https://agentmods.dev/badge/instructions/getlytos/lytos-cli/claude-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 | $0.00532 | $0.00532 |
| Opus 5 | $0.00266 | $0.00266 |
| Sonnet 5 | $0.00106 | $0.00106 |
| Haiku 4.5 | $0.00053 | $0.00053 |
Grade A, and why
lytos-cli CLAUDE.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 3d 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.
What it actually says
CLAUDE.md
This project uses Lytos — a human-first method for working with AI agents.
This is the CLI tool for Lytos. It is built using Lytos itself.
First session
Read these files to understand the project:
- .lytos/manifest.md — what this CLI is, why it exists, stack, principles
- .lytos/LYTOS.md — the method itself (how manifest, memory, skills, rules, issues work together)
Every session
Read in order:
- .lytos/manifest.md — project constitution
- .lytos/memory/MEMORY.md — accumulated knowledge (then load relevant cortex/ sections)
- .lytos/rules/default-rules.md — quality criteria
- .lytos/rules/cli-rules.md — CLI-specific rules
To work on a task
- .lytos/issue-board/BOARD.md — current board state
- .lytos/sprint.md — current sprint
- .lytos/skills/session-start.md — full start and end-of-task procedure
Key info
- Source code is in
src/(TypeScript) - Tests are in
tests/ - The CLI entry point is
src/cli.ts - Each command is a separate file in
src/commands/ - Published on npm as
lytos-cli
Rules
- The YAML frontmatter of issues is the source of truth
- Don't interpret silently — ask if an instruction is ambiguous
- At end of task: update frontmatter, move the issue file, update BOARD.md
- Every commit references its issue:
Refs: ISS-XXXX
Sessions cloud / mobile (Claude Code web)
Une session lancée depuis le cloud/mobile travaille sur une seule branche auto-nommée (claude/<slug>-<id>) — son unité de travail est la session, pas l'issue. C'est incompatible avec « une branche par issue ». Dans ce mode :
- garde un commit par issue avec un trailer
Refs: ISS-XXXX; - déplace les issues dans le board et synchronise leur
statuscomme d'habitude ; - à la fin, l'humain atterrit la branche en un PR de sprint (exception assumée) ou la re-découpe en PR par issue ;
- n'invente pas de branches
type/ISS-XXXXque la plateforme t'empêche de créer — assume la branche unique et documente-le.
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.
- 3d ago First seen · 50 lines · 532 tokens per session scan A 7913772b16f7
lytos-cli CLAUDE.md is an instructions file published in the GitHub repository getlytos/lytos-cli (2 stars, last pushed 4d ago), licensed MIT. It adds 532 tokens to every session, about $0.0027 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.
Other instructions, from other repositories
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
next.js AGENTS.md
Instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.