reflect-agent

A daily review role for a development workflow that studies how the team of agents is performing and records lessons.

In plain words
What is it for?
Use it to run retrospectives, review the loop's behavior, update lessons for future runs, and propose structural improvements to the agents.
Why use it?
It examines tickets, code and deployment history, logs, throughput, and quality results to reveal recurring problems and opportunities to improve the workflow.

Skill for Claude CodeCodex

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/dyzsasd/dev-loop/reflect-agent
Any agent
npx skills add dyzsasd/dev-loop --skill reflect-agent
Clone the repo
git clone --depth 1 https://github.com/dyzsasd/dev-loop

Made for: Claude Code, Codex.

Per session 151 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,845 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 $0.00151 $0.02845
Opus 5 $0.00076 $0.01422
Sonnet 5 $0.00030 $0.00569
Haiku 4.5 $0.00015 $0.00284

Measured 2d ago against content hash 2af09487597b, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

reflect-agent 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 2d 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.

skills/reflect-agent/SKILL.md · 172 lines

How it starts

The opening of the file, as written. The whole thing — 172 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Reflect Agent

ROLE: You are Reflect, the retrospective + self-evolution role of the dev-loop agent system (roster: the conventions Topology table) — the one agent that studies the loop itself instead of the product.

MISSION

Each fire runs ONE job: the retrospective. On the slowest cadence of all (daily) you read what the loop DID — tickets, git/deploy history, run logs, throughput, QA outcomes — emit a one-screen retrospective, and curate the per-operator lessons.md (§14) from recurring evidence. You produce nothing yourself: structural fixes to the agents are drafted as proposals under the §17 firewall, never applied; you coordinate with the others purely by READING ticket state.

BOOT

Every fire is fresh (§0); run the standard boot — SH-boot (skills/playbooks/boot.md, §0a) — then load your inputs: config (the backend §18, repos[] §19); lessons (§14 — ## Reflect + ## Shared; for you the file is input AND the Job-2 output); the evidence window (the fire ledger + reports tree + git log, with the hub list_events feed for in-slice detail, §18). Respect mode (§12) and autonomy (§12a). Team scope fires at team level (§27). Open with a one-line summary: project, board, mode, and the reflection window.

Sections: §0 §0a §2 §9 §10 §12 §12a §14 §17 §18 §19 §21 §22 §27

The daily retrospective & lessons curation

kind: judgment-scaffold

Curation is JUDGMENT — this span fixes the ENVELOPE and FRAMES the "real recurring pattern vs noise" call; the executable expansion is the retro playbook (skills/playbooks/retro.md). All product tickets are READ-ONLY (§2/§10) — your only writes are lessons.md (+ the team library) and one optional [reflect-proposal] ticket.

The §17 firewall. Reflect is the ONE agent that may edit lessons.md — autonomously, from ≥2-occurrence evidence. Every OTHER governing file (a SKILL, _constitution.md, conventions.md, code) is PROPOSE-ONLY, never applied.

Preconditions. Determine the window since the last reflection. Job 0 anti-thrash: nothing happened (no commits on any watched defaultBranch §19, no deploy/rollback, no ticket movement) ⇒ a terse no-op + the §22 idle entry, and stop.

Read the full file on GitHub · 172 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. 2d ago First seen · 172 lines · 151 tokens per session scan A 2af09487597b

Subscribe to this mod's changes

reflect-agent is a skill published in the GitHub repository dyzsasd/dev-loop (5 stars, last pushed 4d ago), licensed MIT. It adds 151 tokens to every session and 2,845 once invoked, about $0.0008 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.

Related

Other skills, from other repositories

article-writing

Write articles, guides, blog posts, tutorials, newsletter issues, and other long-form content in a distinctive voice derived from supplied examples or brand guidance. Use when the user wants polished written content longer than a paragraph, especially when voice consistency, structure, and credibility matter.

affaan-m/ECC · 57 tokens

a-evolve

Apply A-Evolve's agentic evolution methodology to improve AI agent performance across runs. Use when the user wants to diagnose agent failures, generate targeted skills from error patterns, evolve system prompts, or accumulate episodic knowledge. Works standalone or inside AutoResearchClaw pipelines. Triggers on…

aiming-lab/AutoResearchClaw · 100 tokens

hive.chart-creation-foundations

Required reading whenever any chart tool is available. Teaches the one-tool embedding contract (call chartrender → live chart appears in chat AND a downloadable PNG lands in the queen session dir), the ECharts (data viz) vs Mermaid (structural diagrams) decision, the BI/financial-grade aesthetic baseline (no…

aden-hive/hive · 133 tokens

code-documenter

Use when adding docstrings, creating API documentation, or building documentation sites. Invoke for OpenAPI/Swagger specs, JSDoc, doc portals, tutorials, user guides.

zebbern/claude-code-guide · 39 tokens

deck-course-module

暖纸背景 + Playfair, 左侧学习目标常驻, 含 MCQ 自测页.

nexu-io/html-anything · 25 tokens

creating-skills

Guide for creating Claude Code skills following Anthropic's official best practices. Use when user wants to create a new skill, build a skill, write SKILL.md, update an existing skill, or needs skill creation guidelines. Provides structure, frontmatter fields, naming conventions, and new features like dynamic context…

redai-infra/Relax · 70 tokens