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.
npx agentmods add skills/hajekim/agentic-design-patterns-skills/reflectionnpx skills add hajekim/agentic-design-patterns-skills --skill reflectiongit clone --depth 1 https://github.com/hajekim/agentic-design-patterns-skillsWrote 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.
[](https://agentmods.dev/skills/hajekim/agentic-design-patterns-skills/reflection)<a href="https://agentmods.dev/skills/hajekim/agentic-design-patterns-skills/reflection"><img src="https://agentmods.dev/badge/skills/hajekim/agentic-design-patterns-skills/reflection.svg" alt="Measured on agentmods" height="20"></a>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 | $0.00379 | $0.03114 |
| Opus 5 | $0.00189 | $0.01557 |
| Sonnet 5 | $0.00076 | $0.00623 |
| Haiku 4.5 | $0.00038 | $0.00311 |
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 5d 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.
Copies of this mod
1 near-identical copy found in the catalogue:
- reflection — 100% identical, 3 lines differ
How it starts
The opening of the file, as written. The whole thing — 339 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:
- What is the quality bar for the final output?
- What specific dimensions should be critiqued (accuracy, completeness, clarity, safety)?
- How many refinement iterations are appropriate before accepting output?
- What constitutes a "good enough" output to exit the loop?
PLAN
Design the reflection architecture:
- Define the Generator: initial response producer with a focused prompt
- Define the Critic: evaluator that identifies specific weaknesses with explanations
- Define the Refiner: takes original + critique and produces improved output
- Set convergence criteria: max iterations, quality threshold, or "no more critique" signal
- Plan logging of each iteration for debugging and audit
ACTION
Implement the reflection loop:
- Generate initial output with the Generator prompt
- Apply the Critic prompt to evaluate the output on defined dimensions
- If critique finds issues, pass original + critique to the Refiner
- Repeat until convergence criteria met
- Return final refined output
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.
- 5d ago First seen · 339 lines · 379 tokens per session scan A d2a86fbdbf14
reflection is a skill published in the GitHub repository hajekim/agentic-design-patterns-skills (4 stars, last pushed 5mo ago), licensed MIT. It adds 379 tokens to every session and 3,114 once invoked, about $0.0019 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.
Other skills, from other repositories
impact-audit
Blast radius of a change you have not made yet -- traces a symbol across federated repositories, splits impact per repo, and reports what must ship together.
onboard-repo
Index an unfamiliar codebase into the knowledge graph, then produce a first orientation map -- entry points, most-depended-upon modules, hotspots, test topology.
review-pr
Review a PR or branch diff using the knowledge graph for full structural context. Outputs a structured review with blast-radius analysis.
build-graph
Build or update the code review knowledge graph. Run this first to initialize, or let hooks keep it updated automatically.
prompt-optimizer
Analyze raw prompts, identify intent and gaps, match ECC components (skills/commands/agents/hooks), and output a ready-to-paste optimized prompt. Advisory role only — never executes the task itself. TRIGGER when: user says "optimize prompt", "improve my prompt", "how to write a prompt for", "help me prompt", "rewrite…
openclaw-persona-forge
为 OpenClaw AI Agent 锻造完整的龙虾灵魂方案。根据用户偏好或随机抽卡， 输出身份定位、灵魂描述(SOUL.md)、角色化底线规则、名字和头像生图提示词。 如当前环境提供已审核的生图 skill，可自动生成统一风格头像图片。 当用户需要创建、设计或定制 OpenClaw 龙虾灵魂时使用。 不适用于：微调已有 SOUL.md、非 OpenClaw 平台的角色设计、纯工具型无性格 Agent。 触发词：龙虾灵魂、虾魂、OpenClaw 灵魂、养虾灵魂、龙虾角色、龙虾定位、 龙虾剧本杀角色、龙虾游戏角色、龙虾 NPC、龙虾性格、龙虾背景故事、 lobster soul、lobster…