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 Dragoon0x/canon --skill canon-error-handlinggit clone --depth 1 https://github.com/Dragoon0x/canonWrote 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/dragoon0x/canon/canon-error-handling)<a href="https://agentmods.dev/skills/dragoon0x/canon/canon-error-handling"><img src="https://agentmods.dev/badge/skills/dragoon0x/canon/canon-error-handling/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/dragoon0x/canon/canon-error-handling"><img src="https://agentmods.dev/badge/skills/dragoon0x/canon/canon-error-handling.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 | $0.00087 | $0.01120 |
| Opus 5.5 | $0.00035 | $0.00448 |
| Sonnet 5.5 | $0.00017 | $0.00224 |
| Haiku 4.5 | $0.00009 | $0.00112 |
Grade A, and why
canon-error-handling 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 2mo 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 — 120 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CANON · Error Handling
Errors are inevitable. Showing them well is the difference between a product that feels reliable and one that feels broken.
Error message anatomy
Every error message answers three questions:
- What failed? — Name the thing. "Couldn't save your changes."
- Why? — Give the cause if known. "The server didn't respond."
- How to fix? — Give the action. "Check your connection and try again."
Bad: "Error."
Bad: "Something went wrong."
Good: "Couldn't save your changes — connection lost. Check your network and retry."
Error display patterns
| Pattern | Use when |
|---|---|
| Inline (below the field) | Field-level validation errors |
| Banner (top of page/section) | Page-level errors affecting multiple things |
| Toast | Non-critical background errors ("Couldn't sync — retrying") |
| Modal | Critical errors requiring explicit acknowledgment |
| Full page (error page) | Route-level failure (404, 500, auth expired) |
| Error boundary | Component crash that shouldn't take down the page |
Validation timing
From canon-forms:
- Validate on blur (when user leaves the field), not on every keystroke.
- Show error after first submission attempt, then live-validate on change.
- Never show errors before the user has interacted with the field.
Retry logic
| Strategy | Use |
|---|---|
| Immediate retry button | User-triggered (network errors, form submission) |
| Auto-retry with backoff | Background operations (sync, polling) |
| Retry with exponential backoff | API calls: wait 1s, 2s, 4s, 8s, cap at 30s |
| No retry | Permanent errors (404, auth revoked, validation failure) |
Show the retry state: "Retrying in 3s... [Retry now]"
Optimistic UI rollback
When using optimistic updates (show success instantly, sync in background), the error case is the rollback:
- Apply the change immediately in the UI.
- Send the request.
- On failure: revert the UI, show a toast explaining what happened.
- "Couldn't delete item — restored. [Try again]"
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.
- 2mo ago First seen · 120 lines · 87 tokens per session scan A a6acd1bf356a
canon-error-handling is a skill published in the GitHub repository Dragoon0x/canon (6 stars, last pushed 6mo ago), licensed MIT. It adds 87 tokens to every session and 1,120 once invoked, about $0.0003 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.
canon-error-handling compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| canon-error-handlingDragoon0x/canon | Skill | 6 | 6mo ago | MIT | A | 87 | Claude Code, Codex |
| accessibilitydiegosouzapw/awesome-omni-skills | Skill | 170 | 4mo ago | MIT | C | 119 | Claude Code, Codex |
| accessibilityericrisco/rsc-harness | Skill | 503 | 2d ago | MIT | A | 86 | Claude Code, Codex |
| accessibility-auditoyi77/1ai-skills | Skill | 17 | yesterday | MIT | A | 29 | Claude Code |
| a11y-auditgreglas75/zuvo | Skill | 7 | 3d ago | MIT | A | 147 | Claude Code |
| axe-audittonone-ai/tonone | Skill | 77 | 23d ago | MIT | A | 47 | Claude Code |
| accessibility-compliance-accessibility-audit-v2diegosouzapw/awesome-omni-skills | Skill | 170 | 4mo ago | MIT | A | 76 | Claude Code |