What is day-in-my-life?

A short hand-drawn film built from your own local Claude Code session history. It follows one typical session from the first message to the final lesson, and shows each line for your approval before rendering.

Use it to make a personal visual recap of coding, testing, documentation, shipping, or other work shown in your Claude Code history.

It turns a long record of agent-assisted work into a reviewable story without inventing events. It needs local transcripts and is not meant for someone else's history or shared team logs.

day-in-my-life — Skill for Claude Code and Codex by heygen-com

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 heygen-com/hyperframes-community-skills --skill day-in-my-life

Clone the repo

git clone --depth 1 https://github.com/heygen-com/hyperframes-community-skills

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/heygen-com/hyperframes-community-skills/day-in-my-life/github.svg)](https://agentmods.dev/skills/heygen-com/hyperframes-community-skills/day-in-my-life)

Your own site

<a href="https://agentmods.dev/skills/heygen-com/hyperframes-community-skills/day-in-my-life"><img src="https://agentmods.dev/badge/skills/heygen-com/hyperframes-community-skills/day-in-my-life/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/heygen-com/hyperframes-community-skills/day-in-my-life"><img src="https://agentmods.dev/badge/skills/heygen-com/hyperframes-community-skills/day-in-my-life.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 209 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,842 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.

Model	Per session	Once invoked
Fable 5.1	$0.00209	$0.01842
Opus 5.5	$0.00084	$0.00737
Sonnet 5.5	$0.00042	$0.00368
Haiku 4.5	$0.00021	$0.00184

Measured 21d ago against content hash 462099a518fb, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

day-in-my-life 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 21d ago.

The scan reads SKILL.md. This mod also ships 11 executable files (assets/kit/brush-ink.js, assets/kit/film.js, assets/kit/hf-bridge.js, …), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

skills/day-in-my-life/SKILL.md · 112 lines

How it starts

The opening of the file, as written. The whole thing — 112 lines — stays where its author put it; the contents beside it link to each section on GitHub.

A day in my life as 's agent

The agent reads its own history with the user and makes a short film about it:

Look: two-tone brush ink, hand-lettered title, one character (the blot).
Story: one average session in time order, built from what this user actually does (a coder gets a coding day), from the first message to the lesson it keeps.
Sound: a string score locked to every beat.

Every line on screen is a receipt. The user approves each one before anything renders.

When to use / when not

Use when a Claude Code user wants a personal film of their work with the agent, and has at least 10 local sessions over 5 days in ~/.claude/projects.
Do not use for someone else's history, a team's shared logs, product marketing, or content the user won't review. If there are no local transcripts (e.g. claude.ai only), stop: this skill never invents receipts.

Requirements and side effects (complete list)

Tools: Node 22+, Python 3.9+, ffmpeg on PATH. The HyperFrames CLI pinned to npx [email protected] (downloaded from the npm registry on first use).
Setup (once, manually): sh scripts/setup.sh runs npm ci from the committed lockfile: p5 2.3.2 (LGPL-2.1), p5.brush 2.2.1 (MIT), puppeteer 25.9.0 (Apache-2.0, which fetches its pinned Chrome for Testing). For score.py: python3 -m pip install -r scripts/requirements.txt (numpy, scipy).
Reads (local only): ~/.claude/projects/*/*.jsonl (the user's transcripts), ~/.claude/projects/*/memory/*.md, and the CLAUDE.md of projects those transcripts point at. Nothing is uploaded.
Network at preview/render: the page loads the Gochi Hand font (SIL OFL) from Google Fonts. Nothing else.
Writes: only inside the film folder you create: receipts.json, story.json, story.js, music/, renders/. These hold the user's words; never commit or share them.
No credentials, no paid calls.

Workflow

Setup: sh scripts/setup.sh (once), plus the pip line above.
Harvest: python3 scripts/harvest.py --out <film>/receipts.json. Stop if enough is false.
Story: build the timeline from routine (the user's average session, in order), map each step to a chapter type, and fill it from the receipts, per references/story.md. 8 to 13 chapters. Ask the user which name goes in the title.
Privacy gate: show the user one table of every on-screen line with its source (session, timestamp), take their edits, and get an explicit yes. Then set "approved": true.
Scaffold: node scripts/new-film.mjs <film>. It builds the film around the story.json already in the folder. After any later edit to story.json, run node scripts/new-film.mjs <film> --sync. It validates order, fields and captions, blocks secrets, emails and paths, and flags URLs.
Design pass: node scripts/shoot.mjs <film> chapters <film>/renders/sheet.jpg --sheet 4 (one frame per chapter, at its payload moment). Check every chapter reads (blot visible, quotes legible, nothing clipped or covering a bubble) and show the sheet to the user.
Score: python3 scripts/score.py <film>, per references/score.md.
Render: npx --yes [email protected] check <film>, then from <film>: npx --yes [email protected] render --fps 24 --crf 12 --browser-gpu -o renders/film.mp4. Render locally; the page paints with WebGL.
QC: python3 scripts/qc.py <film> <film>/renders/film.mp4 must pass. Then watch it through once, with sound, before delivering.

Read the full file on GitHub · 112 lines

Files

What ships with it

21 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.

21d ago First seen · 112 lines · 209 tokens per session scan A 462099a518fb

Subscribe to this mod's changes

day-in-my-life is a skill published in the GitHub repository heygen-com/hyperframes-community-skills (208 stars, last pushed 2d ago), licensed Apache-2.0. It adds 209 tokens to every session and 1,842 once invoked, about $0.0008 per session on Opus 5.5. 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 2026-09-25.

Creative and media Memory and context agent-skills ai-agents hyperframes video-automation

mem0-oss-to-platform

Plan, then execute, a migration of a project from the mem0 open-source / self-hosted SDK (local Memory class) to the mem0 Platform / hosted SDK (MemoryClient). TRIGGER when: the developer wants to move, switch, or migrate mem0 off OSS/self-hosted to the hosted API, e.g. "migrate my mem0 setup to the platform", "switch…

mem0ai/mem0 · 217 tokens

forget

Remove a personal fact, preference, relationship detail, topic, or prior event from Muse's active memory and stop existing copies or automations from bringing it back. Use for explicit requests such as 'forget that', 'don't remember this about me', or 'remove that from your memory'. Do not use when 'forget it' merely…

asgeirtj/system_prompts_leaks · 74 tokens

Cortex

Operate Cortex, the LifeOS memory system — the typed Knowledge Archive (People, Companies, Ideas, Research with typed related: links) plus recall of prior work sessions, ISAs, and conversations. Search, add, harvest, develop, ingest, distill, graph-navigate, recall. USE WHEN cortex, knowledge, knowledge base, search…

danielmiessler/LifeOS · 196 tokens

memory

Use when the user asks to remember, recall, forget, update, search, or inspect durable OpenSquilla memory, including profile facts in USER.md and long-term notes in MEMORY.md or memory//.md.

opensquilla/opensquilla · 44 tokens

ha-data-stores

Map of Hope Agent's local data stores and safe read-only query workflow. Use when the user asks where Hope Agent stores data, wants to inspect sessions/messages/memory/logs/background jobs/knowledge indexes/settings, asks the model to query local app data, or debugging requires checking persisted state. Trigger…

shiwenwen/hope-agent · 115 tokens

shellm

Reference for the shellm system — recursive LLM shell, identity management, memory, skills, trajectory, and all CLI tools. Use when working on shellm itself, debugging agent behavior, or understanding how the pieces fit together.

laude-institute/headlong · 49 tokens