reflecting-on-skills

reflecting-on-skills is a skill for Claude Code from mdsakalu/agent-plugins. It costs 41 tokens per session (1,235 once invoked), scanned B, original, MIT.

An automatic self-review skill that examines how other skills were used and suggests improvements to their instructions or workflow.

In plain words
What is it for?
Use it in Claude Code to review skill usage through an automatic post-action hook and background analysis.
Why use it?
It can reveal errors, unclear guidance, missed edge cases, and inefficient steps after a skill finishes.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: reads .claude/ paths; mentions subagents; names the AskUserQuestion tool.

Part of the reflecting-on-skills plugin — 1 skill shipped together

Good fit Use it in Claude Code to review skill usage through an automatic post-action hook and background analysis.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/mdsakalu/agent-plugins/reflecting-on-skills
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 mdsakalu/agent-plugins --skill reflecting-on-skills
Clone the repo
git clone --depth 1 https://github.com/mdsakalu/agent-plugins

Made for: Claude Code.

Or install reflecting-on-skills, the plugin that ships this one along with the rest of its 1 skill.

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 reflecting-on-skills

README.md
[![agentmods](https://agentmods.dev/badge/skills/mdsakalu/agent-plugins/reflecting-on-skills/github.svg)](https://agentmods.dev/skills/mdsakalu/agent-plugins/reflecting-on-skills)
Your own site
<a href="https://agentmods.dev/skills/mdsakalu/agent-plugins/reflecting-on-skills"><img src="https://agentmods.dev/badge/skills/mdsakalu/agent-plugins/reflecting-on-skills/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 reflecting-on-skills

Your own site · 80×15
<a href="https://agentmods.dev/skills/mdsakalu/agent-plugins/reflecting-on-skills"><img src="https://agentmods.dev/badge/skills/mdsakalu/agent-plugins/reflecting-on-skills.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 41 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,235 The whole file, excluding the scripts and references it only reads on demand.
Security scan B 1 finding. 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 $0.00041 $0.01235
Opus 5 $0.00020 $0.00617
Sonnet 5 $0.00008 $0.00247
Haiku 4.5 $0.00004 $0.00123

Measured 10d ago against content hash d0f8eb650e62, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade B, and why

reflecting-on-skills scanned grade B with 1 finding 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 10d 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.

Reads agent configuration directoriesmediumAgent snooping

.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.

This skill is triggered by a PostToolUse hook in `~/.claude/settings.json`:
reflecting-on-skills/skills/reflecting-on-skills/SKILL.md · 153 lines

How it starts

The opening of the file, as written. The whole thing — 153 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Reflecting on Skills

This skill is automatically triggered after any other skill completes (via a PostToolUse hook).

Platform Compatibility

Claude Code Only: This skill uses PostToolUse hooks and the Task tool for background subagent execution. These features are specific to Claude Code and not available in Claude apps or via the API.

For the cross-platform Agent Skills specification, see agentskills.io.

Instructions

When invoked after another skill completes:

  1. Identify the skill - Determine which skill was just used from conversation context

  2. Launch background analysis - Use the Task tool:

    Task tool with:
      subagent_type: "general-purpose"
      run_in_background: true
      prompt: [see below]
    
  3. Subagent prompt template:

    Analyze the skill that was just used in this conversation.
    
    1. Read the skill's SKILL.md file at: ~/.claude/skills/[skill-name]/SKILL.md
    2. Review the conversation to identify:
       - Errors or exceptions encountered
       - Unclear or missing instructions that caused confusion
       - Edge cases the skill didn't handle
       - Inefficiencies or unnecessary steps
       - Deviations from the skill's guidance (may indicate gaps)
    
    3. If issues found, draft SPECIFIC improvements:
       - Exact text to add/change in SKILL.md
       - Keep changes minimal and focused
       - Only address observed issues, not hypotheticals
    
    4. If improvements warranted, use AskUserQuestion:
       - Present the issue observed
       - Show the proposed change
       - Ask: "Apply this improvement to [skill-name]?"
    
    5. If approved, use Edit tool to update the skill's SKILL.md
    
    If no issues observed, complete silently without prompting.
    
  4. Continue conversation - Don't wait for reflection to complete

Hook Configuration

This skill is triggered by a PostToolUse hook in ~/.claude/settings.json:

{
  "hooks": {
    "PostToolUse": [
      {
        "matcher": "Skill",
        "hooks": [
          {
            "type": "command",
            "command": "python3 ~/.claude/hooks/post-skill-reflect.py"
          }
        ]
      }
    ]
  }
}

Read the full file on GitHub · 153 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. 10d ago First seen · 153 lines · 41 tokens per session scan B d0f8eb650e62

Subscribe to this mod's changes

reflecting-on-skills is a skill published in the GitHub repository mdsakalu/agent-plugins (4 stars, last pushed 3mo ago), licensed MIT. It adds 41 tokens to every session and 1,235 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it B with 1 finding (reads agent configuration directories). 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

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

local-ai-agents

Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…

microsoft/ai-agents-for-beginners · 200 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

insight-error-page

Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…

vercel/next.js · 83 tokens

next-cache-components-optimizer

Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…

vercel/next.js · 170 tokens

next-partial-prefetching-adoption

Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…

vercel/next.js · 103 tokens