reflect

reflect is a skill for Claude Code, Codex from epicsagas/plugins. It costs 67 tokens per session (541 once invoked), scanned A, original, Apache-2.0.

A session self-assessment workflow for reviewing how well an AI coding session was used. It scores goal clarity, prompt quality, iteration efficiency, tool use, and alignment with the intended result.

In plain words
What is it for?
Use it at the end of a session to produce a scorecard, identify the most useful improvement, and record that lesson in project memory.
Why use it?
It turns a vague review of an AI session into specific evidence about what worked and what could improve.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it at the end of a session to produce a scorecard, identify the most useful improvement, and record that lesson in project memory.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/epicsagas/plugins/reflect
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.

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

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 reflect

README.md
[![agentmods](https://agentmods.dev/badge/skills/epicsagas/plugins/reflect/github.svg)](https://agentmods.dev/skills/epicsagas/plugins/reflect)
Your own site
<a href="https://agentmods.dev/skills/epicsagas/plugins/reflect"><img src="https://agentmods.dev/badge/skills/epicsagas/plugins/reflect/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for reflect

Your own site · 80×15
<a href="https://agentmods.dev/skills/epicsagas/plugins/reflect"><img src="https://agentmods.dev/badge/skills/epicsagas/plugins/reflect.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 67 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 541 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 $0.00067 $0.00541
Opus 5 $0.00034 $0.00270
Sonnet 5 $0.00013 $0.00108
Haiku 4.5 $0.00007 $0.00054

Measured 4d ago against content hash 82fef61c8473, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, 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 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.

.hermes/epic/skills/reflect.SKILL.md · 67 lines

What it actually says

Self-assessment of AI session quality across 5 dimensions. Uses harness session data and memory to produce an honest scorecard.

Usage

/reflect

The 5 dimensions

Dimension Weight Measures
Goal clarity 20% Were requirements specific enough? Did the user provide clear acceptance criteria?
Prompt quality 20% Were instructions precise? Did the user catch misunderstandings early?
Iteration efficiency 20% How many correction cycles? Were they due to unclear specs or exploration?
Tool utilization 20% Did the user leverage available tools (memory, search, code analysis)?
Outcome alignment 20% Does the final result match what was actually needed?

Process

  1. Collect dataharness_reflect_context to get session stats and evolution history
  2. Recall contextharness_mem_recall with hint about the current session
  3. Score each dimension — 1-5 scale with specific evidence
  4. Calculate overall — weighted average
  5. Identify top improvement — single most impactful thing to do differently
  6. Recordharness_mem_add the reflection as type "insight"

Output format

## Session Reflection

### Scores
| Dimension | Score | Evidence |
|---|---|---|
| Goal clarity | 4/5 | ... |
| Prompt quality | 3/5 | ... |
| Iteration efficiency | 4/5 | ... |
| Tool utilization | 2/5 | ... |
| Outcome alignment | 5/5 | ... |
| **Overall** | **3.6/5** | |

### What went well
- ...

### What to improve
- ...

### Top recommendation for next session
> Single most impactful change to make.

Important notes

  • This is NOT about agent performance — it's about how the human used AI
  • Be honest, not flattering — low scores are more useful than high scores
  • The "top recommendation" should be actionable and specific
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 · 67 lines · 67 tokens per session scan A 82fef61c8473

Subscribe to this mod's changes

reflect is a skill published in the GitHub repository epicsagas/plugins (2 stars, last pushed yesterday), licensed Apache-2.0. It adds 67 tokens to every session and 541 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 2026-09-05.

Related

Other skills, from other repositories

systematic-debugging

Systematic debugging approach for errors, test failures, and unexpected behavior. Use when encountering bugs, test failures, errors, or when debugging is needed. Prevents common anti-patterns like random fixes, skipping root cause analysis, and thrashing.

shrwnsan/vibekit-claude-plugins · 54 tokens

crafting-commits

Generates git commit messages following conventional commit standards with collaborative attribution. Use when user requests commit message creation, drafting, or help with formatting.

shrwnsan/vibekit-claude-plugins · 34 tokens

handoff-context

Detects natural language handoff requests and generates structured context summaries for seamless thread continuation. Use when user says "handoff", "new thread", "continue in fresh thread", or similar phrases.

shrwnsan/vibekit-claude-plugins · 43 tokens

meta-search

Recovers web content when searches fail with 403, 429, 422 errors, blocked sites, or empty results. Runs bundled Tavily/Jina extraction scripts, then falls back to manual strategies.

shrwnsan/vibekit-claude-plugins · 44 tokens

branch-hygiene

Classify and clean up merged, stale, and orphaned git branches and worktrees. Detects squash-merges that git branch --merged cannot see, stale worktrees, and remote-gone branches. Use when user asks to clean up branches, prune worktrees, tidy the repo, or perform git housekeeping.

shrwnsan/vibekit-claude-plugins · 68 tokens

hold-my-hand

Hold the user's hand through a long multi-step job. Partition the remaining work into phases and present ONLY the current one, never the phases after it beyond a one-line 'Phase 1 of 8' count. Each phase names where to be, numbered steps with exact commands, the expected output, the common failure, who performs each…

melodic-software/claude-code-plugins · 217 tokens