[object Object]

[object Object] is a skill for Claude Code, Codex from team-reflect/reflect-open. It costs 51 tokens per session (777 once invoked), scanned A, original, MIT.

A command-line tool for reading and searching notes in a Reflect graph, which is a local collection of markdown notes. It can resolve note titles and dates while keeping access directed at the selected graph.

In plain words
What is it for?
Use it to search, read, and open notes, daily entries, or journal material in Reflect, and to inspect note history when requested.
Why use it?
It avoids manually scanning note files and provides a defined way to find current notes. Git history can be used separately when someone needs past versions, differences, or recovery.

Skill for Claude CodeCodex

About the project

Reflect is an open-source note-taking app that stores notes as Markdown files in a user-chosen folder, with daily notes, wiki links, backlinks, local search, and optional AI features. People use it to write, connect, search, synchronize, and query personal notes on Mac and iPhone. Catalogue add-ons support agent workflows such as interacting with notes through its CLI and related automation.

team-reflect/reflect-open · 1,454 stars · on GitHub

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/team-reflect/reflect-open/graph
Any agent
npx skills add team-reflect/reflect-open --skill graph
Clone the repo
git clone --depth 1 https://github.com/team-reflect/reflect-open

Made for: Claude Code, Codex.

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.

agentmods badge for [object Object]

README.md
[![agentmods](https://agentmods.dev/badge/skills/team-reflect/reflect-open/graph.svg)](https://agentmods.dev/skills/team-reflect/reflect-open/graph)
Your own site
<a href="https://agentmods.dev/skills/team-reflect/reflect-open/graph"><img src="https://agentmods.dev/badge/skills/team-reflect/reflect-open/graph.svg" alt="Measured on agentmods" height="20"></a>
Per session 51 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 777 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 $0.00051 $0.00777
Opus 5 $0.00026 $0.00388
Sonnet 5 $0.00010 $0.00155
Haiku 4.5 $0.00005 $0.00078

Measured today against content hash 44ee40f98b46, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

[object Object] 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 today.

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.

apps/desktop/src-tauri/skills/graph-skill.md · 82 lines

How it starts

The opening of the file, as written. The whole thing — 82 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Reflect graph: {{GRAPH_NAME}}

Reflect is a local-first, markdown-backed note-taking app. This skill targets one graph (a folder of notes):

{{GRAPH_ROOT}}

Read it through the reflect CLI rather than scanning the files — the CLI resolves titles, aliases, and daily dates, searches the graph's ranked index, and enforces the privacy contract.

The CLI

Use reflect from PATH when available; the app also bundles the binary at:

{{CLI_PATH}}

Always target the graph explicitly so calls stay deterministic:

reflect --graph "{{GRAPH_ROOT}}" <command>

or export REFLECT_GRAPH="{{GRAPH_ROOT}}" for a sequence of calls.

Git history

On desktop, every graph is also a Git repository at its root. Reflect initializes or adopts that repo when the graph opens; even graphs with no backup remote keep local history through a commit-only sync loop. There may be no origin, but .git history is available.

Use the CLI for current note lookup, privacy filtering, and path resolution. Use Git only when the user asks for history, diffs, recovery, or past states:

git -C "{{GRAPH_ROOT}}" log --oneline -- <graph-relative-path>
git -C "{{GRAPH_ROOT}}" diff <rev> -- <graph-relative-path>
git -C "{{GRAPH_ROOT}}" show <rev>:<graph-relative-path>

Do not use Git history to bypass privacy. If a note is private, avoid reading or exposing its current or historical content unless the user explicitly asks.

Commands

reflect today              # print today's daily note
reflect today --path       # its absolute path (works before the file exists)
reflect search <query>     # ranked full-text search over the graph
reflect show <note>        # print a note by date, path, title, or alias
reflect path <note>        # resolve a note to its absolute path
reflect open <note>        # open the note in the Reflect app
  • Add --json to any command for stable machine-readable output — the field names and exit codes are the supported automation contract.
  • <note> resolves in order: YYYY-MM-DD date, graph-relative path, title, then alias (case-insensitive).
  • stdout carries only data; warnings and errors go to stderr.

Read the full file on GitHub · 82 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. today First seen · 82 lines · 51 tokens per session scan A 44ee40f98b46

Subscribe to this mod's changes

[object Object] is a skill published in the GitHub repository team-reflect/reflect-open (1,454 stars, last pushed today), licensed MIT. It adds 51 tokens to every session and 777 once invoked, about $0.0003 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 2026-09-05.