Borrowing it
Nothing to install: this file belongs to jerseycheese/Narraitor. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/jerseycheese/Narraitor/main/.claude/skills/narraitor-product-frontier/SKILL.mdgit clone --depth 1 https://github.com/jerseycheese/NarraitorWrote 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/jerseycheese/narraitor/narraitor-product-frontier)<a href="https://agentmods.dev/skills/jerseycheese/narraitor/narraitor-product-frontier"><img src="https://agentmods.dev/badge/skills/jerseycheese/narraitor/narraitor-product-frontier/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/jerseycheese/narraitor/narraitor-product-frontier"><img src="https://agentmods.dev/badge/skills/jerseycheese/narraitor/narraitor-product-frontier.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00093 | $0.01494 |
| Opus 5 | $0.00046 | $0.00747 |
| Sonnet 5 | $0.00019 | $0.00299 |
| Haiku 4.5 | $0.00009 | $0.00149 |
Grade A, and why
narraitor-product-frontier 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 12d 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 — 57 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Product frontier
1. Purpose
Name the problems that would move Narraitor past the state of the art, what the repo already has toward each, the first three concrete steps, and the falsifiable "you have a result when…" bar — so ambition lands as scoped work instead of vibes.
2. When to use
Post-1.0 planning; "make the story smarter/deeper" requests; evaluating whether a research-y idea fits this codebase.
3. When not to use
- v1.0 gate work →
narraitor-hardest-problem-campaign. Routine features →narraitor-feature-experiment-lifecycle(frontier work still ships THROUGH that lifecycle).
4. Inputs required
Current epic map (gh issue list --label epic --state open) — frontier work must reconcile with existing epics, not duplicate them.
5. Procedure — the frontier problems
F1. Long-arc story memory & coherence. Falls short today: context is a fixed window over recent segments + lore facts, capped at assembly rather than by any budget; long sessions lose early threads; coherence is enforced by prompt instructions + a deterministic continuity guardrail with ONE corrective AI call (fail-open). Assets: loreStore (facts + dedup/merge + audit log), continuityStore, narrative/summarize + story-checkpoint routes, the src/lib/promptContext/ assembly path (measurement only — no allocator). First steps: (1) instrument how often the guardrail fires and on what, across 3 long sessions; (2) measure what falls out of the context window in a 30+ turn arc; (3) prototype checkpoint-summary layering into context assembly behind a feature flag. Result when: on a scripted 30-turn arc, a plot fact from turns 1–5 is correctly referenced at turn 30 in >=4/5 runs across 2 worlds, vs a measured baseline.
F2. Consequence tracking that players feel. Falls short: choices carry alignment/trust metadata (#468 shipped) and world-state impacts exist (narrativeStore.worldStateImpacts.ts), but long-range payoff of early choices is weak. Assets: decisions with metadata, goalStore + goalExtractor, journal. First steps: (1) trace one real decision's data end-to-end; (2) define 3 concrete consequence archetypes (unlocked path, changed NPC stance, resource shift) and where each is injected into context; (3) eval per ai-quality-discipline matrix. Result when: a blind reader identifies which of two turn-20 transcripts followed choice A vs B, >=8/10 sessions.
What ships with it
1 file 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.
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.
- 12d ago First seen · 57 lines · 93 tokens per session scan A 0316f9b51b7e
narraitor-product-frontier is a skill published in the GitHub repository jerseycheese/Narraitor (30 stars, last pushed today), licensed MIT. It adds 93 tokens to every session and 1,494 once invoked, about $0.0005 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 2026-08-30.
Other skills, from other repositories
media-ingest
Ingest video, audio, PDF, book, screenshot, and GitHub repo content into the brain. Multi-format handling with entity extraction and backlink propagation. Covers video-ingest, youtube-ingest, and book-ingest subtypes.
mem0-oss-to-platform
Plan and then execute a migration of a project from the mem0 open-source / self-hosted SDK (the local Memory class) to the mem0 Platform / hosted / managed SDK (the MemoryClient class). Use this whenever a developer wants to move, switch, or migrate their mem0 usage off OSS/self-hosted to the hosted API — e.g.…
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…
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.
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…
establishing-project-context
Use when the user asks to establish shared project language, or project work exposes a conflicting, renamed, or deprecated domain term that needs active semantic modeling. Routine small tasks stay on the fast path.