A command for checking data-driven interfaces beyond the normal success case, including loading, empty, error, offline, and slow-network situations.

Use it to review screens, add fallback messages and actions, handle network interruptions, and check behavior with very little or very much data.

It helps find the states and edge cases that are often missing when an interface is designed only for successful requests.

harden — Command for Claude Code by Dragoon0x/canon

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.

Clone the repo

git clone --depth 1 https://github.com/Dragoon0x/canon

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.

README.md

[![agentmods](https://agentmods.dev/badge/commands/dragoon0x/canon/harden/github.svg)](https://agentmods.dev/commands/dragoon0x/canon/harden)

Your own site

<a href="https://agentmods.dev/commands/dragoon0x/canon/harden"><img src="https://agentmods.dev/badge/commands/dragoon0x/canon/harden/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.

Your own site · 80×15

<a href="https://agentmods.dev/commands/dragoon0x/canon/harden"><img src="https://agentmods.dev/badge/commands/dragoon0x/canon/harden.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 46 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 571 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.

Model	Per session	Once invoked
Fable 5.1	$0.00046	$0.00571
Opus 5.5	$0.00018	$0.00228
Sonnet 5.5	$0.00009	$0.00114
Haiku 4.5	$0.00005	$0.00057

Measured 1mo ago against content hash 0179194de90c, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

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 1mo 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.

source/commands/harden.md · 69 lines

How it starts

The opening of the file, as written. The whole thing — 69 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/harden

Every interface has 4 states. Most ship 1. Harden fills in the other 3.

Coverage map

For every data-driven view in the app, confirm:

Loading

400ms delay before any spinner
Skeleton if content shape is known
Spinner animates at 1000–1500ms per cycle
Label changes to present-continuous on the triggering button ("Saving…")
Fixed button width prevents layout shift

Empty

First-time empty: illustration + headline + description + primary CTA
User-cleared empty: brief confirmation
Filtered empty: "No results" + "Clear filters" escape
Search empty: "No results for X" + alternative suggestions

Error

Network error: retry button + calm tone
Server error: "Something went wrong" + retry + support link
404: friendly explanation + home link
403: sign-in prompt or request-access flow
Validation: inline at the field, specific cause, how to fix

Populated (the happy path)

Already designed. Just verify it degrades gracefully at low data volumes (1 item) and high (1000 items).

Network resilience

Offline banner if app requires network
Queue mutations during offline; sync on reconnect
Toast confirmation on reconnect: "Back online. Synced N changes."
Read-only mode for cached views when network is gone

Slow-network UX

Simulate 3G and check:

Is LCP < 2.5s on 75th percentile mobile?
Does the page render progressively or wait for everything?
Are fonts using font-display: swap so text appears immediately?
Is the LCP image preloaded with fetchpriority="high"?

Destructive actions

Prefer Undo toast (5s window) over confirmation dialog
Irreversible actions get explicit dialog with action verb: "Delete forever"
Destructive button styled as such: red background or outlined-red
Keyboard focus lands on the safe default (Cancel), not the destructive button

Copy hardening

Every error has recovery action text
Every empty state has next-step CTA
Every loading state identifies what's loading (when > 1s)
Every success state is brief and non-blocking (toast, not dialog)

Read the full file on GitHub · 69 lines

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.

1mo ago First seen · 69 lines · 46 tokens per session scan A 0179194de90c

Subscribe to this mod's changes

harden is a command published in the GitHub repository Dragoon0x/canon (6 stars, last pushed 6mo ago), licensed MIT. It adds 46 tokens to every session and 571 once invoked, about $0.0002 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 2026-08-31.

Claude Code Debugging Frontend accessibility ai-agent ai-coding audit codex

debug

Systematic debugging with hypotheses and evidence gathering.

primeline-ai/evolving-lite · 8 tokens

improve

/improve Scan and fix all improvement categories /improve arch Architectural improvements only /improve duplication Duplicate code / abstraction consolidation /improve quality Code quality (GuardLoop patterns GL-01 through GL-10) /improve security Security posture improvements /improve --dry-run Show what would be…

samibs/skillfoundry · 0 tokens

detectar-ambiguedad

Detectar ambigüedades y contradicciones en specs de forma exhaustiva.

doncheli/don-cheli-sdd · 16 tokens

doctor

Diagnosticar y reparar problemas del framework Don Cheli, git y entorno. Usa cuando el usuario dice "doctor", "problemas del framework", "don cheli no funciona", "repair Don Cheli", "debug setup", "setup broken", "framework broken", "reparar entorno". Detecta y repara issues de configuración, git y dependencias…

doncheli/don-cheli-sdd · 76 tokens

diagnostico

Verificar la salud del setup de Don Cheli en el proyecto actual.

doncheli/don-cheli-sdd · 14 tokens

code-locate

Locate code paths and line ranges for a described behavior: up to 10 candidates with HIGH/MEDIUM/LOW confidence and a search trail, plus a proposed SOURCEOFTRUTH.md update. Use when the first question is where one specific behavior lives and paths are unknown. Do not use when paths are explicit, the codebase is tiny…

Mozurok/fhorja.dev · 0 tokens