cspell-triage

cspell-triage is a skill for Claude Code from AndrewDongminYoo/cc-agents-kit. It costs 45 tokens per session (3,879 once invoked), scanned A, original, Apache-2.0.

A workflow for handling words flagged by cspell, a tool that checks spelling in source code and documentation. It decides whether a word is a typo, generated output, or valid technical vocabulary before changing dictionaries.

In plain words
What is it for?
Use it to investigate unknown or forbidden words, configure cspell, exclude committed build output, enable ecosystem dictionaries, and verify the spelling check.
Why use it?
It prevents repository dictionaries from filling up with legitimate words or hiding real spelling errors. It also helps identify missing language-specific dictionaries and incorrect scan scope.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the repo-gate plugin — 6 skills shipped together

Good fit Use it to investigate unknown or forbidden words, configure cspell, exclude committed build output, enable ecosystem dictionaries, and verify the spelling check.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/andrewdongminyoo/cc-agents-kit/cspell-triage
Install

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.

Any agent
npx skills add AndrewDongminYoo/cc-agents-kit --skill cspell-triage
Clone the repo
git clone --depth 1 https://github.com/AndrewDongminYoo/cc-agents-kit

Made for: Claude Code.

Or install repo-gate, the plugin that ships this one along with the rest of its 6 skills.

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 cspell-triage

README.md
[![agentmods](https://agentmods.dev/badge/skills/andrewdongminyoo/cc-agents-kit/cspell-triage/github.svg)](https://agentmods.dev/skills/andrewdongminyoo/cc-agents-kit/cspell-triage)
Your own site
<a href="https://agentmods.dev/skills/andrewdongminyoo/cc-agents-kit/cspell-triage"><img src="https://agentmods.dev/badge/skills/andrewdongminyoo/cc-agents-kit/cspell-triage/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 cspell-triage

Your own site · 80×15
<a href="https://agentmods.dev/skills/andrewdongminyoo/cc-agents-kit/cspell-triage"><img src="https://agentmods.dev/badge/skills/andrewdongminyoo/cc-agents-kit/cspell-triage.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 45 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,879 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.
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 $0.00045 $0.03879
Opus 5 $0.00023 $0.01939
Sonnet 5 $0.00009 $0.00776
Haiku 4.5 $0.00005 $0.00388

Measured 6d ago against content hash d7653b036733, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

cspell-triage 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 6d 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.

plugins/repo-gate/skills/cspell-triage/SKILL.md · 266 lines

How it starts

The opening of the file, as written. The whole thing — 266 lines — stays where its author put it; the contents beside it link to each section on GitHub.

cspell Triage

Overview

An unknown word is a question about where it came from — not a word to add.

Most hits disappear before any word is written down, because the dictionaries the project's own ecosystem ships were never enabled. Measured on a real repository: 371 unknown words fell to 233 with one ignorePaths entry for committed build output, then to 159 by naming six bundled dictionaries. 57% were never dictionary candidates.

The gate — most requests are step 3 alone

Run the repo's own gate command first (npx -y cspell ., or whatever grep -rn cspell .trunk/trunk.yaml package.json says actually runs). What it reports decides how much of this skill applies:

The run shows Scope
A handful of unknown words, and a root config exists Step 3 only. Dispose of the words, re-run, canary, stop.
Unknown words dominated by ecosystem vocabulary (pytest flagging in Markdown, xcassets, …) Step 2, then step 3.
No root config, several configs, or a gate command carrying scope flags the config should own Step 1, then onward.
An inherited dictionary suspected of dead weight, or an explicit audit request Step 4.

A setup step you did not enter is not skipped work — it is work that was never needed. In the basic case the whole task is four commands: run, dispose, re-run, canary. Do not modify a working config's scan surface on the way past it.

When setup IS needed, work in this order. Skipping to step 3 there is what produces 300-entry dictionaries full of stemmer fragments.

Read the full file on GitHub · 266 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. 6d ago Changed · +4 lines d7653b036733
  2. 10d ago First seen · 262 lines · 45 tokens per session scan A 1b61455fdb63

Subscribe to this mod's changes

cspell-triage is a skill published in the GitHub repository AndrewDongminYoo/cc-agents-kit (2 stars, last pushed yesterday), licensed Apache-2.0. It adds 45 tokens to every session and 3,879 once invoked, about $0.0002 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.