Updated 4d ago
by o11y-dev
reflect
Reflect helps engineering teams see whether AI coding agents are actually improving delivery or just burning tokens, failing tools, and creating hidden debt
20 GitHub stars (20)
+1 in 3 days
| Period | New stars |
|---|---|
| Oct 14 | +1 |
| Oct 15 | 0 |
| Oct 16 | 0 |
- 3 skills (3 skills found in its SKILL.md files)
- 2 forks (2 forks)
- 4d ago last update (Last updated 4d ago)
Install
Skills CLI
npx skills add o11y-dev/reflect
Asks which skills and agents to install. Just one: npx skills add o11y-dev/reflect --skill reflect-skills — add -g for every project.
Claude Code
git clone https://github.com/o11y-dev/reflectcp -r "reflect/src/reflect/data/skills/reflect-skills" ~/.claude/skills/
Copies the reflect-skills skill into ~/.claude/skills/ for every project (use .claude/skills/ for one project). Repeat for the other skills listed below.
Plugin
/plugin marketplace add o11y-dev/reflect
Run inside Claude Code if the repository ships a plugin marketplace, then pick plugins from /plugin.
Skills can run code on your machine — read the SKILL.md first.
What it does
In the author's own words, from each skill's SKILL.md.
-
reflect-skills
Use when the user wants to inventory, inspect, discover, version, apply, or roll back reusable skills derived from AI coding sessions.
src/reflect/data/skills/reflect-skills/SKILL.md on GitHub (opens in a new tab) -
reflect-usage
Inspect and explain exact local AI coding-agent usage for the current session, a selected session, or all captured sessions. Use for questions such as "where did my tokens go?", "why were so many tokens used?", "was the usage efficient or worth it?", or any token, cache, cost, model, tool, MCP, subagent, duration, failure, or usage-statistics analysis across Codex, Claude, Cursor, Copilot, Gemini…
src/reflect/data/skills/reflect-usage/SKILL.md on GitHub (opens in a new tab) -
reflect
Use when the user wants task-specific guidance from prior AI coding sessions, actionable workflow improvements, workflow or skill impact, an evidence-backed case study, a Reflect dashboard, telemetry analysis, tool/model/MCP/subagent investigation, provider usage explanations, or local-first versus gateway architecture advice. Start every non-trivial repository task with approved local guidance,…
src/reflect/data/skills/reflect/SKILL.md on GitHub (opens in a new tab)
No skill matches that filter.
Review before you install
A skill is a set of instructions and scripts your agent will follow, and it can run code on your machine. Read the SKILL.md and any scripts first — this listing is not a security review.