reflect

reflect is a skill for Claude Code from pitimon/8-habit-ai-dev. It costs 63 tokens per session (2,127 once invoked), scanned A, original, MIT.

A brief review held after a task or workflow, using six questions to capture lessons, surprises, improvements, and reusable patterns.

In plain words
What is it for?
Use it after finishing a task or workflow to identify what worked, what changed your understanding, and what action should improve future work.
Why use it?
It turns completed work into practical learning instead of allowing the same problems to recur without being recorded.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: reads .claude/ paths.

Runs only inside its plugin — its command needs a path that Claude Code sets for a plugin’s own hooks and for nothing else. Install the plugin, not this.

Part of the 8-habit-ai-dev plugin — 24 skills, 2 agents, 1 hook shipped together

Install

Getting it into your agent

This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.

Claude Code
/plugin marketplace add pitimon/8-habit-ai-dev
Claude Code
/plugin install 8-habit-ai-dev

Made for: Claude Code.

Or install 8-habit-ai-dev, the plugin that ships this one along with the rest of its 24 skills, 2 agents, 1 hook.

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 reflect

README.md
[![agentmods](https://agentmods.dev/badge/skills/pitimon/8-habit-ai-dev/reflect.svg)](https://agentmods.dev/skills/pitimon/8-habit-ai-dev/reflect)
Your own site
<a href="https://agentmods.dev/skills/pitimon/8-habit-ai-dev/reflect"><img src="https://agentmods.dev/badge/skills/pitimon/8-habit-ai-dev/reflect.svg" alt="Measured on agentmods" height="20"></a>
Per session 63 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,127 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 5.1 $0.00063 $0.02127
Opus 5 $0.00032 $0.01064
Sonnet 5 $0.00013 $0.00425
Haiku 4.5 $0.00006 $0.00213

Measured 5d ago against content hash 3b5d6baad6ed, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

reflect 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.

plugin/skills/reflect/SKILL.md · 144 lines

How it starts

The opening of the file, as written. The whole thing — 144 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Reflect (ทบทวน)

Habit: H7 — Sharpen the Saw | Anti-pattern: All output, no capability improvement — repeating the same mistakes

Why This Exists

DORA research shows per-task micro-retros (3-5 questions, 5 minutes) are more effective than monthly hour-long retrospectives. The key differentiator: teams that assign action items with owners improve; teams that just "discuss" don't. Q6 below extends the DORA pattern with a skill-effectiveness signal specific to this plugin (H7 applied to the plugin itself, per Issue #92).

Process

Ask these 6 questions. Keep answers brief — this should take no more than 5 minutes.

1. What went well?

Reinforce good practices. What should we keep doing?

2. What surprised me?

Surface hidden complexity. What did we not expect? Sub-prompt: did a prior diagnosis or shipped fix prove wrong this session — what evidence reversed it? A root cause that was confident-but-wrong is a high-value surprise to capture; this signal feeds SKILL-EFFECTIVENESS.md. See independent-source-verification.md.

3. What would I do differently?

Improve next iteration. If starting over, what would change?

4. What reusable pattern did I discover?

Extract for the team. Is there a script, template, or approach worth sharing?

Sub-prompt: did the AI workflow itself reveal a reusable cost/health pattern — repeated loops, retries without new evidence, context compaction that needed verification, missing audit trail, or next-session recovery gaps?

5. Action item

One specific, assigned action with a deadline. Not "we should improve testing" but "create a test template for API endpoints by Friday." If AI-work cost was unhealthy, make the action concrete: add a handoff note, add a validator, shorten a prompt, or preserve a recovery artifact. Do not add runtime budget enforcement in this plugin.

6. Skill effectiveness signal

Capture three fields:

  • most_useful: Which 8-habit skill was most useful this session?
  • least_or_confusing: Which skill was least useful or confusing?
  • missed_skill: Which skill should have been invoked but was missed until later?

Read the full file on GitHub · 144 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. 5d ago First seen · 144 lines · 63 tokens per session scan A 3b5d6baad6ed

Subscribe to this mod's changes

reflect is a skill published in the GitHub repository pitimon/8-habit-ai-dev (3 stars, last pushed 1mo ago), licensed MIT. It adds 63 tokens to every session and 2,127 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 2026-08-31.