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-feature-experiment-lifecycle/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-feature-experiment-lifecycle)<a href="https://agentmods.dev/skills/jerseycheese/narraitor/narraitor-feature-experiment-lifecycle"><img src="https://agentmods.dev/badge/skills/jerseycheese/narraitor/narraitor-feature-experiment-lifecycle/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-feature-experiment-lifecycle"><img src="https://agentmods.dev/badge/skills/jerseycheese/narraitor/narraitor-feature-experiment-lifecycle.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 | $0.00099 | $0.01244 |
| Opus 5 | $0.00049 | $0.00622 |
| Sonnet 5 | $0.00020 | $0.00249 |
| Haiku 4.5 | $0.00010 | $0.00124 |
Grade A, and why
narraitor-feature-experiment-lifecycle 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 9d 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 — 76 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Feature & experiment lifecycle
1. Purpose
Give every idea one path from hunch to decision, so work is scoped before it starts and every ending (ship, hold, retire) leaves a record.
2. When to use
New feature/improvement work; prompt or AI-behavior experiments; resurrecting old ideas; deciding the fate of half-done work.
3. When not to use
- Pure bug fixes with a reproducer → change-control's fix loop directly.
- Already-scoped issue implementation → the owner's issue pipeline (analyze-issue → tdd-implement → post-merge; owner-personal skills — may be absent for other contributors, in which case: analyze the issue, TDD the fix, open the PR per change-control). This skill wraps AROUND that pipeline, not instead of it.
4. Inputs required
The idea in one sentence; which class it is (UI, mechanics, AI-behavior, infra).
5. Procedure
P0 CAPTURE — file an issue with the matching template (.github/ISSUE_TEMPLATE/: bug_report,
enhancement, epic, feature_request, user-story). Existing labels only. Check the epic map
first — most ideas belong under an existing epic, and closed history may have already
tried it (search closed issues before proposing).
P1 SCOPE — acceptance criteria written UP FRONT, evaluator-checkable ("player can X and it
persists across reload"), plus explicit non-goals. v1.0-phase rule: polish and reliability
only — net-new features default to post-MVP labels.
P2 PREDICT — state expected behavior BEFORE coding: what changes, what must not change,
which stores/routes/templates it touches (blast radius from architecture-contract).
P3 FLAG AI EXPERIMENTS — any change to prompts/templates/generation config is an EXPERIMENT:
declare the eval matrix per narraitor-ai-quality-discipline section 5 (the single home of
the matrix minimums — name your worlds/characters) BEFORE writing code.
Prompt work additionally follows prompt-template-governance gates.
P4 BUILD — smallest diff that can prove the criteria. TDD where a wrong behavior is pinnable.
P5 LOCAL PROOF — run it in the dev server (real flow, not only /dev/* harness or Storybook).
P6 PARITY — storybook-app-parity ladder to >= S2; cross-DS + dark mode for anything visual.
P7 GATE — quality gate green; class-specific gates per change-control; AI experiments: the
full ai-quality-discipline matrix recorded.
P8 FRESH-STATE CHECK — brand-new world + character walk the feature end to end (catches
assumptions your seasoned test data hides), plus a hard-refresh persistence check.
P9 DECIDE — write the ship/hold memo (templates/ship-hold-memo.md). Ship -> PR to develop
per change-control. Hold -> memo names the failing gate and re-entry condition.
Retire -> close the issue with the memo so the battle isn't re-fought (this feeds
failure-archaeology).
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.
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.
- 9d ago First seen · 76 lines · 99 tokens per session scan A f803313ec327
narraitor-feature-experiment-lifecycle is a skill published in the GitHub repository jerseycheese/Narraitor (30 stars, last pushed today), licensed MIT. It adds 99 tokens to every session and 1,244 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
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…