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 agentmods add commands/koolamusic/claudefiles/hardengit clone --depth 1 https://github.com/koolamusic/claudefilesWrote 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/commands/koolamusic/claudefiles/harden)<a href="https://agentmods.dev/commands/koolamusic/claudefiles/harden"><img src="https://agentmods.dev/badge/commands/koolamusic/claudefiles/harden.svg" alt="Measured on agentmods" 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 | $0.00030 | $0.01006 |
| Opus 5 | $0.00015 | $0.00503 |
| Sonnet 5 | $0.00006 | $0.00201 |
| Haiku 4.5 | $0.00003 | $0.00101 |
Grade A, and why
harden 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 — 93 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Strengthen interfaces against real-world usage: edge cases, errors, internationalization, performance bottlenecks, and cross-device adaptation.
First: Use the ux skill for design principles and anti-patterns.
Assess
- Test with extreme inputs: very long/short text, special characters (emoji, RTL), large numbers, many items (1000+), no data
- Test error scenarios: network failures, API errors (400-500), validation, permissions, rate limiting, concurrent ops
- Test i18n: long translations (German +30%), RTL, CJK characters, date/number formats, pluralization
- Measure performance: Core Web Vitals (LCP, INP, CLS), bundle size, frame rate, network waterfall
- Test responsiveness: mobile (320px), tablet, desktop, different inputs (touch, mouse, keyboard), orientations
Text Overflow & i18n
Overflow handling:
text-overflow: ellipsisfor single-line truncation-webkit-line-clampfor multi-linemin-width: 0on flex/grid items to allow shrinkingclamp()for fluid typography
i18n:
- 30-40% space budget for translations. Use flexible containers, not fixed widths.
- Logical properties (
margin-inline-start,padding-inline) for RTL support Intl.DateTimeFormatandIntl.NumberFormatfor locale-aware formatting- UTF-8 everywhere, test with CJK and emoji
Error Handling
- Network errors: clear message + retry button + offline mode if applicable
- Form validation: inline errors near fields, specific messages, preserve user input
- API errors: handle each status (400=validation, 401=login redirect, 403=permission, 404=not found, 429=rate limit, 500=generic+support)
- Graceful degradation: core functionality works without JS, progressive enhancement
Edge Cases
- Empty states with clear next action
- Loading states with context ("Loading your projects...")
- Large datasets: pagination or virtual scrolling
- Concurrent ops: prevent double-submit, handle race conditions
- Permission states: explain why, show path to access
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 First seen · 93 lines · 30 tokens per session scan A 6c5ad42cde06
harden is a command published in the GitHub repository koolamusic/claudefiles (132 stars, last pushed 7d ago), licensed MIT. It adds 30 tokens to every session and 1,006 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 2026-08-30.
Other commands, from other repositories
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
constitution
Create or update the project constitution from interactive or provided principle inputs.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.