reflection

reflection is a skill for Claude Code, Codex from hajekim/agentic-design-patterns-extension. It costs 379 tokens per session (3,115 once invoked), scanned A, a copy of reflection, MIT.

A self-review method for agents that follows a generate, critique, and refine cycle. The agent examines its first answer for mistakes or gaps and then improves it.

In plain words
What is it for?
It is for revising code, writing, plans, and other outputs when a quality check or iterative improvement is useful.
Why use it?
It reduces errors and weak reasoning that can remain in an unreviewed first draft.

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/hajekim/agentic-design-patterns-extension/reflection
Any agent
npx skills add hajekim/agentic-design-patterns-extension --skill reflection
Clone the repo
git clone --depth 1 https://github.com/hajekim/agentic-design-patterns-extension

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 reflection

README.md
[![agentmods](https://agentmods.dev/badge/skills/hajekim/agentic-design-patterns-extension/reflection.svg)](https://agentmods.dev/skills/hajekim/agentic-design-patterns-extension/reflection)
Your own site
<a href="https://agentmods.dev/skills/hajekim/agentic-design-patterns-extension/reflection"><img src="https://agentmods.dev/badge/skills/hajekim/agentic-design-patterns-extension/reflection.svg" alt="Measured on agentmods" height="20"></a>
Per session 379 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,115 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin 100% copy Near-identical to another mod 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 $0.00379 $0.03115
Opus 5 $0.00189 $0.01558
Sonnet 5 $0.00076 $0.00623
Haiku 4.5 $0.00038 $0.00312

Measured 4d ago against content hash d9b893f2bed7, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

reflection 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 4d 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.

Origin

This is a copy

100% identical to reflection — 3 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

skills/reflection/SKILL.md · 340 lines

How it starts

The opening of the file, as written. The whole thing — 340 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Reflection Pattern

Overview

The Reflection Pattern enables an agent to critically evaluate its own outputs and iteratively improve them through self-assessment loops. Rather than accepting the first response as final, the agent acts as its own critic — identifying flaws, gaps, and inaccuracies — then generates a refined output based on that critique.

Core Principle: Generate → Critique → Refine — treat the first output as a draft, not a final answer.

When This Skill Applies

Activate this pattern when:

  • Output quality must meet a high standard before delivery
  • The task involves complex reasoning where first attempts are often suboptimal
  • You need an agent to self-correct factual errors or logical inconsistencies
  • A separate "critic" role would improve the overall quality of the response
  • Tasks require iterative refinement (code writing, essay drafting, plan generation)
  • The cost of external human review is high and automated quality checks are preferable

Rule of thumb: If the task is complex enough that a human expert would draft, review, and revise — apply the Reflection pattern.

DEFINE → PLAN → ACTION Workflow

DEFINE

Identify the reflection requirements:

  1. What is the quality bar for the final output?
  2. What specific dimensions should be critiqued (accuracy, completeness, clarity, safety)?
  3. How many refinement iterations are appropriate before accepting output?
  4. What constitutes a "good enough" output to exit the loop?

PLAN

Design the reflection architecture:

  1. Define the Generator: initial response producer with a focused prompt
  2. Define the Critic: evaluator that identifies specific weaknesses with explanations
  3. Define the Refiner: takes original + critique and produces improved output
  4. Set convergence criteria: max iterations, quality threshold, or "no more critique" signal
  5. Plan logging of each iteration for debugging and audit

ACTION

Implement the reflection loop:

  1. Generate initial output with the Generator prompt
  2. Apply the Critic prompt to evaluate the output on defined dimensions
  3. If critique finds issues, pass original + critique to the Refiner
  4. Repeat until convergence criteria met
  5. Return final refined output

Read the full file on GitHub · 340 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. 4d ago First seen · 340 lines · 379 tokens per session scan A d9b893f2bed7

Subscribe to this mod's changes

reflection is a skill published in the GitHub repository hajekim/agentic-design-patterns-extension (1 stars, last pushed 5mo ago), licensed MIT. It adds 379 tokens to every session and 3,115 once invoked, about $0.0019 per session on Opus 5. A static security scan graded it A with 0 findings. It is 100% identical to reflection, differing in 3 lines, and is treated as a copy.