What is synlin CLAUDE.md?

Repository instructions for synlin, a command-line tool that manages reusable Claude Code configuration such as skills, agents, commands, rules, and templates. They describe its code layout, library location, and safe file-writing rules.

Use them when changing synlin's catalog, installer, manifest, file-resolution, or command-handling code, and when checking how changes should be verified.

They explain which files belong to the tool and which belong to the user's separate configuration library. This helps prevent accidental changes to user data while developing or testing the command-line tool.

How tylld/synlin configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to tylld/synlin. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/tylld/synlin/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/tylld/synlin

Made for: Claude Code.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/tylld/synlin/claude-md/github.svg)](https://agentmods.dev/instructions/tylld/synlin/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/tylld/synlin/claude-md"><img src="https://agentmods.dev/badge/instructions/tylld/synlin/claude-md/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.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/tylld/synlin/claude-md"><img src="https://agentmods.dev/badge/instructions/tylld/synlin/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 628 This file is loaded in full into every session.

When invoked 628 The same file — it is already loaded in full.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

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.

Model	Per session	Once invoked
Fable 5.1	$0.00628	$0.00628
Opus 5.5	$0.00251	$0.00251
Sonnet 5.5	$0.00126	$0.00126
Haiku 4.5	$0.00063	$0.00063

Measured 2mo ago against content hash 02f28a5157e7, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

synlin 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 2mo 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.

CLAUDE.md · 49 lines

How it starts

The opening of the file, as written. The whole thing — 49 lines — stays where its author put it; the contents beside it link to each section on GitHub.

synlin — Claude Code Instructions

CLI that manages a personal library of Claude Code config items (skills, agents, commands, rules, templates) and installs them into projects' .claude/ dirs.

Layout

src/lib/ — pure core: catalog scan, manifest, tree hashing, installer, name resolution, tool adapters. All side-effect-light and unit-tested.
src/commands/ — thin command handlers over src/lib/; interactive prompts (@clack/prompts) stay at this layer only.
The library is NOT in this repo. It is the user's own directory, resolved via SYNLIN_LIBRARY → libraryRoot in ~/.config/synlin/config.json → ~/.synlin/library (see resolveLibraryRoot). synlin library init bootstraps a new one. Andrei's personal library lives in the separate private repo ~/Documents/ai-playground/synlin-library.
scripts/seed.ts — one-time initial import into the resolved library; do not re-run casually (it refuses unless the library is empty or --force is passed).

Rules

Never modify library content as a side effect of CLI code changes — the library is user data, wherever it lives.
Every file write/delete in a target project must stay inside the project's write envelope: the tool config dirs (.claude/, .codex/, .cursor/, .opencode/), adapter-declared shared files at the project root (currently AGENTS.md), and <projectRoot>/.synlin.json. Owned-tree writes for tool T must additionally stay inside T's own config dir (see assertWritable / assertInside in src/lib/paths.ts); keep that guarantee when touching the installer or adapters.
The manifest format (<projectRoot>/.synlin.json, version 2) is a compatibility contract — bump MANIFEST_VERSION and add migration on breaking changes. Version 1 (.claude/.synlin.json) is migrated in memory on read and persisted (legacy file deleted) on the next write.
Tool adapters (src/lib/tools/) must render deterministically: pure functions of library item content — no clocks, env, or fs beyond the item.
Tests run against tmp-dir fixtures (tests/helpers/tmp.ts); command handlers accept an injectable Runtime (cwd, env, interactive) — never depend on process.cwd() inside src/lib/.

Read the full file on GitHub · 49 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.

2mo ago First seen · 49 lines · 628 tokens per session scan A 02f28a5157e7

Subscribe to this mod's changes

synlin CLAUDE.md is an instructions file published in the GitHub repository tylld/synlin (2 stars, last pushed 5mo ago), licensed MIT. It adds 628 tokens to every session, about $0.0025 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 2026-08-31.

Building agents

synlin CLAUDE.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
synlin CLAUDE.mdtylld/synlin	Instructions file	2	5mo ago	MIT	A	628	Claude Code
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	9,719	GitHub Copilot
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	5,516	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	yesterday	MIT	A	7,461	Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	today	MIT	A	4,680	Codex, OpenCode
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	3,093	GitHub Copilot
vscode model-prompts.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	2,022	GitHub Copilot

synlin: Instructions file for Claude Code