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.
npx skills add tonydzi/second-brain-starter-kit --skill reality-showgit clone --depth 1 https://github.com/tonydzi/second-brain-starter-kitWrote 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.
[](https://agentmods.dev/skills/tonydzi/second-brain-starter-kit/reality-show)<a href="https://agentmods.dev/skills/tonydzi/second-brain-starter-kit/reality-show"><img src="https://agentmods.dev/badge/skills/tonydzi/second-brain-starter-kit/reality-show/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.
<a href="https://agentmods.dev/skills/tonydzi/second-brain-starter-kit/reality-show"><img src="https://agentmods.dev/badge/skills/tonydzi/second-brain-starter-kit/reality-show.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00070 | $0.01914 |
| Opus 5 | $0.00035 | $0.00957 |
| Sonnet 5 | $0.00014 | $0.00383 |
| Haiku 4.5 | $0.00007 | $0.00191 |
Grade A, and why
reality-show 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.
How it starts
The opening of the file, as written. The whole thing — 76 lines — stays where its author put it; the contents beside it link to each section on GitHub.
REALITY-SHOW v2 — the season continuity layer on top of a SINGLE CANON
GOAL: make the stream of episodes read like a SERIES. /episode writes one episode with dramaturgy (palette [[style-reality-show]]); THIS skill remembers the SEASON and suggests the next narrative move.
SOURCE OF TRUTH = the canon: $OBSIDIAN_VAULT/04-Projects\show-canon\
(season-01.md · arcs\ · beats\ · loops\ · rules; the map is _SHOW-CANON.md).
⛔ season-state.json is FROZEN as of 2026-07-10 (_imports\content-factory\season-state.json + season_state.py) — it was the third diverging spine after THREADS/SHOW-STATE; decision decision-single-canon-story-state. Do NOT read it as truth, do NOT update it.
MODES
status (default, read-only, 0 LLM tokens)
Read season-01.md (the season question, active arcs, open loops, the board) + the headers of arcs\*.md (status, current_state) + loops\*.md (open?) → a one-line digest for the owner: the season + arcs with their stakes + dangling cliffhanger loops + story_day. Nothing is changed.
next — propose the beat for the next episode (authorial model, cheap)
- Read: season-01.md + open loops + fresh beats in
beats\(happened, latest by occurred_on) + the 📝 inbox_imports\content-factory\triage\posts.md(fresh post material). Do NOT read the whole corpus. - Judgement (top-tier model): which OPEN arc today's material should advance; which loop to close or sharpen; which motif to bring back (running gag). It must connect to a REAL beat — never invent events.
beat_kindhints at the dramaturgy: 🌀 twist / 💥 fail = cliffhanger; 🏆 milestone = payoff; 📡 external = fuel for the season's intrigue. - Output 1-2 options: "arc X → sharpen (loop '…'), bring back the motif '…', anchored on beat-YYYY-MM-DD-slug". After that
/episodewrites the episode.
intake — process the beats inbox (sensor candidates → canon)
At night this is done by the routine canon-writer-nightly (01:00); here it is the same thing on demand.
python $IMPORTS_ROOT/content-factory\canon_intake.py list → judge fitness and the ARC (only from the live dictionary!) → ... accept <beat_id> --arcs arc-a,arc-b or ... reject <beat_id> --why "...".
The script itself: validates arc_id against the arc files, sets the derived story_day, moves it into beats\, appends the back-link into the arc, cleans _README. Never move beats by hand.
canon_intake.py verify — the detector of half-finished intake (a beat sits in beats\ while the arc does not reference it: a break, or a race between two writers). Runs at the end of the nightly pass; exit 1 = fix it.
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.
- today First seen · 76 lines · 70 tokens per session scan A 0bd45dc05775
reality-show is a skill published in the GitHub repository tonydzi/second-brain-starter-kit (6 stars, last pushed yesterday), licensed MIT. It adds 70 tokens to every session and 1,914 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 2026-09-09.
Other skills, from other repositories
canvas
Create, inspect, and update Obsidian JSON Canvas boards with text, file, link, group, and edge nodes. Use for canvas status, canvas lists, visual maps, zones, spatial layouts, adding vault notes or media to a .canvas file, and requests such as create canvas, add to canvas, or put this on the canvas.
gpt-image
Use when asked to generate, create, make, render, draw, or mock up an image, photo, picture, hero image, illustration, icon, texture, sprite, or visual asset from Claude Code, and no usable OPENAIAPIKEY is set but Codex CLI is installed and signed in to ChatGPT (OAuth). Also triggered by /gpt-image. Routes image…
image-brand
Generate on-brand post visuals through Codex CLI's built-in image generation, using the agency's exact brand colors and the owner's face reference photos. Use whenever a post needs an image, carousel slides, or a visual revision, or when the owner says "generate the image", "make the visual", or gives image feedback.…
generate-me
Generate an image of "me", "my face", "make me", "put me in", "turn me into", or a photo of the skill owner while preserving their facial identity across photoreal, illustrated, cartoon, cinematic and stylized scenes.
entertain-meme
Create a humor or meme post that resonates with the agency's ICP and stays insurance-related, visual-first. Use when the daily lane is entertain, or when the owner says "meme", "something funny", "entertain post", or "lighten up the feed". Requires brain/MyAgencyContext.md.
wiki-ingest
Ingest supplied source material into an Obsidian vault with provenance and claim tracking: pasted text, files staged in the selected vault's inbox or .raw archive, or explicitly approved URLs. Use for a single source or bounded batch, not for saving an assistant answer. Triggers: ingest, ingest this file, ingest this…