Narraitor: Skill for Claude Code

.claude/skills/narraitor-change-control/SKILL.md

narraitor-change-control is a skill for Claude Code from jerseycheese/Narraitor. It costs 100 tokens per session (1,582 once invoked), scanned A, original, MIT.

A change-control guide for Narraitor that defines what evidence is required before calling work finished, fixed, validated, or verified. It covers code, documentation, and user-interface changes.

In plain words
What is it for?
Use it before reporting a Narraitor change as done, opening or merging a pull request, updating baselines, or correcting an earlier inaccurate claim.
Why use it?
A change can appear complete while tests, visual checks, or dependency checks are still missing. This guide prevents unsupported status claims and sets the minimum checks for each change type.

Skill for Claude Code

Written for Claude Code: installed under .claude/.

This is jerseycheese/Narraitor's own configuration. It tells Claude Code how to work on Narraitor itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything Narraitor configures →

Reuse

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.

Copy the file
curl -O https://raw.githubusercontent.com/jerseycheese/Narraitor/main/.claude/skills/narraitor-change-control/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/jerseycheese/Narraitor

Made for: Claude Code.

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.

agentmods badge for narraitor-change-control

README.md
[![agentmods](https://agentmods.dev/badge/skills/jerseycheese/narraitor/narraitor-change-control/github.svg)](https://agentmods.dev/skills/jerseycheese/narraitor/narraitor-change-control)
Your own site
<a href="https://agentmods.dev/skills/jerseycheese/narraitor/narraitor-change-control"><img src="https://agentmods.dev/badge/skills/jerseycheese/narraitor/narraitor-change-control/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.

agentmods 80×15 button for narraitor-change-control

Your own site · 80×15
<a href="https://agentmods.dev/skills/jerseycheese/narraitor/narraitor-change-control"><img src="https://agentmods.dev/badge/skills/jerseycheese/narraitor/narraitor-change-control.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 100 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,582 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. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00100 $0.01582
Opus 5 $0.00050 $0.00791
Sonnet 5 $0.00020 $0.00316
Haiku 4.5 $0.00010 $0.00158

Measured 9d ago against content hash ab3fba4b3a68, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

narraitor-change-control 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.

.claude/skills/narraitor-change-control/SKILL.md · 79 lines

How it starts

The opening of the file, as written. The whole thing — 79 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Narraitor change control

1. Purpose

Keep status honest. Every claim about a change has a required evidence tier; corrections append rather than overwrite; no gate gets routed around. This skill is load-bearing for all others — when in doubt about whether you may say "done", the answer is here.

2. When to use

Before any status claim; before opening/merging a PR; before re-baselining anything; after discovering a prior claim (yours or a doc's) was wrong.

3. When not to use

  • Choosing which tests to run → narraitor-validation-and-qa.
  • Deciding ship vs hold on product grounds → narraitor-feature-experiment-lifecycle.

4. Inputs required

The diff (or planned diff), its classification (below), and the artifacts you already have.

5. Procedure

Step 1 — classify the change. The class sets the minimum gate:

Class Minimum gate before "done"
Docs-only Claims in the doc verified against the tree; stale refs not propagated
Code (logic) Quality gate (test, type-check, lint, lint:css) green locally + test added/updated + original failing case re-run if it's a fix
Component / user-facing UI Code gate PLUS parity ladder >= S2 per narraitor-storybook-app-parity (S3 for user-facing features) — unit-green + story alone NEVER earns "done" for UI
Test-only The test fails without the fix / passes with it — shown, not asserted
AI-route / AI-behavior Code gate PLUS multi-world evidence per narraitor-ai-quality-discipline; prompt changes per narraitor-prompt-template-governance
Design-system / CSS Code gate PLUS lint:css, both color schemes (light + dark) checked — one design system since ADR-013 — visual baselines regenerated together if shared chrome moved
Store-shape Code gate PLUS the blast-radius checklist in narraitor-architecture-contract (persist migrate!)
Content/copy Project voice, no "AI" in user-facing strings, baseline impact checked

Step 2 — status language is earned, not decorative:

Read the full file on GitHub · 79 lines

Files

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.

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.

  1. 9d ago First seen · 79 lines · 100 tokens per session scan A ab3fba4b3a68

Subscribe to this mod's changes

narraitor-change-control is a skill published in the GitHub repository jerseycheese/Narraitor (30 stars, last pushed today), licensed MIT. It adds 100 tokens to every session and 1,582 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.