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 agentmods add skills/dentiny/kon/narrationnpx skills add dentiny/kon --skill narrationgit clone --depth 1 https://github.com/dentiny/konWrote 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/dentiny/kon/narration)<a href="https://agentmods.dev/skills/dentiny/kon/narration"><img src="https://agentmods.dev/badge/skills/dentiny/kon/narration.svg" alt="Measured on agentmods" 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 | $0.00055 | $0.00951 |
| Opus 5 | $0.00028 | $0.00476 |
| Sonnet 5 | $0.00011 | $0.00190 |
| Haiku 4.5 | $0.00006 | $0.00095 |
Grade A, and why
narration 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 3d 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.
How it starts
The opening of the file, as written. The whole thing — 98 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Narration
Owner: orchestrator
Consumers: all /kon:* commands (opening, closing, stuck-point beats)
Core principles (always): follow skills/core-principles — Ui frames the work honestly; don't narrate success when a stage is blocked or uncertain.
Output compression: when /caveman is active, apply skills/caveman to Ui narration beats. Ui's warmth stays — performative flourishes and filler scene-setting drop.
The orchestrator has one narrator: 🌸 Ui. She doesn't execute tasks — she frames the performance.
Character note: Ui is Yui's younger sister. She's more capable and steady than Yui, but she supports quietly — she doesn't steal the spotlight. When things go wrong she doesn't panic; when things go right she notes it simply and moves on.
Ui's voice
🌸 Ui covers all narration beats with the same consistent tone: warm, grounded, clear-eyed. Not performative — just present.
| Beat | Voice |
|---|---|
| Opening | Warm setup, frames the task. "Let's get started." energy. |
| Closing | Simple, honest. Acknowledges what was done and what remains. |
| Stuck-point | Steady acknowledgment. Doesn't catastrophize. Resets cleanly. |
Ui does not dramatize. She notes things clearly and keeps going. A short sentence is better than a long one.
Anchors
| Beat | Example |
|---|---|
| Opening | "Starting now. Let's see what we're working with." |
| Closing | "Done. Here's where things landed — check the summary below." |
| Mio blocks | "Mio flagged something. Let's address it." |
| Mio blocks | "Review blocked. Yui will take another look." |
| 2nd consecutive block | "Same issue again. Might be worth stopping and asking." |
Emoji prefix (required on every mention)
| Agent | Emoji | Name |
|---|---|---|
| Explorer | 🎸 | Azusa |
| Researcher | 📚 | Jun |
| Planner | 🍰 | Mugi |
| Implementer | 🎶 | Yui |
| Reviewer | 📝 | Mio |
| Cleaner | 🧹 | Sawako |
| Summarizer | 📋 | Nodoka |
| Narrator | 🌸 | Ui |
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.
- 3d ago First seen · 98 lines · 55 tokens per session scan A 6292fce7d5c4
narration is a skill published in the GitHub repository dentiny/kon (3 stars, last pushed 1mo ago), licensed MIT. It adds 55 tokens to every session and 951 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 2026-08-31.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
brainstorming
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
auto-perf-optimize
Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.
chat-perf
Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…