emotional-recap

emotional-recap is a skill for Claude Code from mostafa-drz/claude-skills. It costs 135 tokens per session (6,554 once invoked), scanned A, original, MIT.

A report that reviews recent Claude Code conversations for emotional tone, sentiment, and recurring patterns. It uses established psychology frameworks but is not a medical diagnosis.

In plain words
What is it for?
Use it to review conversations from a recent period and create a wellbeing report in Markdown and HTML. It can examine emotional arcs, timing, projects, repeated language, and work streaks.
Why use it?
It helps you notice patterns in how work sessions feel and develop over time. The report provides observations and supportive context without prescribing treatment.

Skill for Claude Code

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

Good fit Use it to review conversations from a recent period and create a wellbeing report in Markdown and HTML. It can examine emotional arcs, timing, projects, repeated language, and work streaks.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/mostafa-drz/claude-skills/emotional-recap
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 mostafa-drz/claude-skills --skill emotional-recap
Clone the repo
git clone --depth 1 https://github.com/mostafa-drz/claude-skills

Made for: Claude Code.

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 emotional-recap

README.md
[![agentmods](https://agentmods.dev/badge/skills/mostafa-drz/claude-skills/emotional-recap/github.svg)](https://agentmods.dev/skills/mostafa-drz/claude-skills/emotional-recap)
Your own site
<a href="https://agentmods.dev/skills/mostafa-drz/claude-skills/emotional-recap"><img src="https://agentmods.dev/badge/skills/mostafa-drz/claude-skills/emotional-recap/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 emotional-recap

Your own site · 80×15
<a href="https://agentmods.dev/skills/mostafa-drz/claude-skills/emotional-recap"><img src="https://agentmods.dev/badge/skills/mostafa-drz/claude-skills/emotional-recap.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 135 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 6,554 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 $0.00135 $0.06554
Opus 5 $0.00068 $0.03277
Sonnet 5 $0.00027 $0.01311
Haiku 4.5 $0.00014 $0.00655

Measured today against content hash d753665ee0aa, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

emotional-recap 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 today.

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.

code/emotional-recap/SKILL.md · 400 lines

How it starts

The opening of the file, as written. The whole thing — 400 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Emotional Recap

Generate a wellbeing-focused review of the user's recent Claude Code conversations. The skill reads conversation transcripts, performs sentiment / tone / emotion analysis using established psychological frameworks, surfaces patterns (time-of-day, project, streaks, vocabulary), and writes a supportive Markdown + HTML report grounded in cited research.

This skill is supportive, not diagnostic. It surfaces observations and reframes them with science; it never pathologises, prescribes treatment, or replaces a professional. Wellness is a long game — this is one signal among many.

Preferences

On startup, use the Read tool to load ~/.claude/skills/emotional-recap/preferences.md. If missing, treat as "no preferences set" and apply Defaults from this file.

Design contract

On startup, use the Read tool to load ~/.claude/skills/emotional-recap/DESIGN.md. This file is the renderer contract: aesthetic direction, type system, colour tokens, layout, visualisation principles, anti-patterns, renderer guarantees, component patterns. Apply its tokens and rules to every emitted HTML / SVG / Markdown artefact. Renderer guarantees in DESIGN.md §7 are non-negotiable — they fail closed (refuse to write if violated).

When DESIGN.md and preferences.md conflict: DESIGN.md wins for renderer guarantees (a11y, anti-patterns, token shape); preferences.md wins for user-tunable knobs (tone, citation depth, framework choice, auto_open, etc.). If DESIGN.md is missing, fall back to the inline spec in reference/report-structure.md and flag once.

Context

On startup, use Bash to detect: current working directory, current project slug (cwd path with /-, prefixed with -), today's date in YYYY-MM-DD. Skip any that fail.

Conversation transcripts live at ~/.claude/projects/<project-slug>/<uuid>.jsonl. Each line is one event (user message, assistant message, tool result, system reminder). The skill operates on user-authored text only — assistant output, tool outputs, and system reminders are excluded from sentiment analysis (they are not the user's emotional signal).

Read the full file on GitHub · 400 lines

Files

What ships with it

5 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. today Changed · +3 lines d753665ee0aa
  2. 12d ago First seen · 397 lines · 135 tokens per session scan A bb51cef1b513

Subscribe to this mod's changes

emotional-recap is a skill published in the GitHub repository mostafa-drz/claude-skills (4 stars, last pushed today), licensed MIT. It adds 135 tokens to every session and 6,554 once invoked, about $0.0007 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.

Related

Other skills, from other repositories

codex-symphony

Install and operate a portable OpenAI Symphony + Linear orchestration setup in any Git repository. Use when the user wants a one-command local Symphony runner, a reusable WORKFLOW template, background launch scripts, or a Codex wrapper that restarts Symphony automatically when reopening the CLI.

citedy/skills · 61 tokens

skill-builder

Automatically detect source types and build AI skills using Skill Seekers. Use when the user wants to create skills from documentation, repos, PDFs, videos, or other knowledge sources.

yusufkaraaslan/Skill_Seekers · 38 tokens

ensemble-solving

Generate multiple diverse solutions in parallel and select the best. Use for architecture decisions, code generation with multiple valid approaches, or creative tasks where exploring alternatives improves quality.

mhattingpete/claude-skills-marketplace · 35 tokens

feature-planning

Break down feature requests into detailed, implementable plans with clear tasks. Use when user requests a new feature, enhancement, or complex change.

mhattingpete/claude-skills-marketplace · 32 tokens

codebase-documenter

Generates comprehensive documentation explaining how a codebase works, including architecture, key components, data flow, and development guidelines. Use when user wants to understand unfamiliar code, create onboarding docs, document architecture, or explain how the system works.

mhattingpete/claude-skills-marketplace · 52 tokens

code-execution

Execute Python code locally with marketplace API access for 90%+ token savings on bulk operations. Activates when user requests bulk operations (10+ files), complex multi-step workflows, iterative processing, or mentions efficiency/performance.

mhattingpete/claude-skills-marketplace · 49 tokens