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 skills add AndrewDongminYoo/cc-agents-kit --skill cspell-triagegit clone --depth 1 https://github.com/AndrewDongminYoo/cc-agents-kitWrote 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/andrewdongminyoo/cc-agents-kit/cspell-triage)<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.
<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>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 | $0.00045 | $0.03879 |
| Opus 5 | $0.00023 | $0.01939 |
| Sonnet 5 | $0.00009 | $0.00776 |
| Haiku 4.5 | $0.00005 | $0.00388 |
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.
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.
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.
- 6d ago Changed · +4 lines d7653b036733
- 10d ago First seen · 262 lines · 45 tokens per session scan A 1b61455fdb63
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.
Other skills, from other repositories
bash-defensive-patterns
Master defensive Bash programming techniques for production-grade scripts. Use when writing robust shell scripts, CI/CD pipelines, or system utilities requiring fault tolerance and safety.
setup
One-command setup for usage-guard's real plan quota. Use this whenever the user runs /usage-guard:setup, asks to enable/activate/turn on the real 5-hour and weekly quota reading, asks to wire up the status line, or when /usage-guard:usage shows no "Real plan quota" block (only the weighted fallback). Detects the…
bun-test-mocking
Use for mock functions in Bun tests, spyOn, mock.module, implementations, and test doubles.
api-response-optimization
Optimizes API performance through payload reduction, caching strategies, and compression techniques. Use when improving API response times, reducing bandwidth usage, or implementing efficient caching.
sync-forks
Check how many of your GitHub forks are out of date and sync them.
codex
Run the Codex CLI directly in the user's checkout for code analysis, refactoring, or automated editing without Claude Architect's verified delegation lifecycle.