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 LeahyCC/claude-skills --skill gotchasgit clone --depth 1 https://github.com/LeahyCC/claude-skillsWrote 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/leahycc/claude-skills/gotchas)<a href="https://agentmods.dev/skills/leahycc/claude-skills/gotchas"><img src="https://agentmods.dev/badge/skills/leahycc/claude-skills/gotchas/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/leahycc/claude-skills/gotchas"><img src="https://agentmods.dev/badge/skills/leahycc/claude-skills/gotchas.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 | $0.00153 | $0.01901 |
| Opus 5.5 | $0.00061 | $0.00760 |
| Sonnet 5.5 | $0.00031 | $0.00380 |
| Haiku 4.5 | $0.00015 | $0.00190 |
Grade A, and why
gotchas 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 today.
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 — 91 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Gotchas
The bugs that survive tsc, the linter, and the first green test run. Both humans and LLMs miss them for the same reason: the code is locally well-formed, and the failure lives in the gap between what a call looks like it does and what the runtime, network, or clean checkout actually does.
If a failure path returns a valid-looking value, you do not have error handling. You have a bug that hides.
If state changes before the work that can fail, a failure leaves the UI and the data talking about different worlds.
Source checks and dates: SOURCES.md.
Procedure
- Read the diff or the files under review, plus
.gitignore,package.jsonscripts, and the test files that cover the change. - Walk the five lenses in the table below. Only load the resource file for a lens that touches the code in front of you.
- For every async action, trace two paths on paper before running anything:
- What happens when the network, parser, or worker rejects halfway through?
- What happens when the user clicks twice and the first call settles after the second?
- Check the proof. A green test counts only if it ran after the last edit, hit the real code path, and fails when the fix is reverted.
read the diff
|
+-- calls fetch, fs, clipboard, timers, URL, worker, JSON? --> web-and-runtime.md
|
+-- sets state around an await, or shares module state? ----> state-and-async.md
|
+-- has try/catch, fallbacks, defaults, or quiet returns? ---> silent-failures.md
|
+-- touches build, public/, env, hooks, or package.json? ----> fresh-clone.md
|
+-- adds or edits tests, mocks, or assertions? --------------> false-green-tests.md
Where to read
| Lens | Resource |
|---|---|
| Silent fallbacks, swallowed catches, partial batch drops, hidden UI actions | silent-failures.md |
State committed before await, stale completions, module singletons across requests |
state-and-async.md |
fetch 200 HTML stand-ins, FormData headers, URL base rules, workers, Safari clipboard, Date, sort |
web-and-runtime.md |
Gitignored generated files, .git in postinstall, case-sensitive paths, hoisted imports, engines |
fresh-clone.md |
| Edited assertions, mocked units under test, 0-assertion tests, stale green runs, piped exit codes | false-green-tests.md |
What ships with it
7 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.
- today First seen · 91 lines · 153 tokens per session scan A e5d5740dc83b
gotchas is a skill published in the GitHub repository LeahyCC/claude-skills (3 stars, last pushed today), licensed MIT. It adds 153 tokens to every session and 1,901 once invoked, about $0.0006 per session on Opus 5.5. 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 2026-10-25.
Other skills, from other repositories
project-audit
Run a full-spectrum senior engineering audit of an existing codebase or product across 15 domains — security, data, testing, architecture, API, DevOps, observability, performance, accessibility, SEO/web presence, privacy, docs, dependencies, DX and cost — producing a prioritised, verifiable findings report with a…
Accessibility Audit Helper
Reviews UI code and components for WCAG 2.1 accessibility violations and provides specific fixes.
bug-reporting
Load this skill whenever you are filing, reviewing, or generating accessibility bug reports — whether from automated tool output, manual testing, or AI agent scans. The purpose of this skill is to make accessibility errors easier to report accurately, so that developers can reproduce, understand, and fix them without…
drupal-a11y-patch-eval
Evaluate a Drupal accessibility patch end-to-end: baseline evidence, patch hygiene, after-patch verification, manual/AT checks, critic gate, and upstream handoff. Evidence-gated — never VERIFIED without before/after proof under the same conditions.
web-a11y-debugging
Debugs accessibility issues with automated scanners, browser accessibility trees, keyboard checks, screen reader smoke tests, custom CSS/JS rules, and CI gates. Use when triaging barriers or building accessibility validation pipelines.
a11y-ally
Use when running comprehensive WCAG accessibility audits with axe-core + pa11y + Lighthouse, generating context-aware remediation, or testing video accessibility. Supports 3-tier browser cascade with graceful degradation.