errors

A workflow for adding error handling and resilience to Bun and TypeScript services. Resilience means continuing safely or failing clearly when dependencies or requests go wrong.

In plain words
What is it for?
Use it to design error types, validate inputs, add retries and timeouts, configure circuit breakers, or review code that should fail more gracefully.
Why use it?
It helps prevent hidden failures and makes validation errors, timeouts, retries, and service outages easier to handle safely.

Command

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.

agentmods
npx agentmods add commands/madappgang/magus/errors
Clone the repo
git clone --depth 1 https://github.com/MadAppGang/magus
Per session 30 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 282 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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.

ModelPer sessionOnce invoked
Fable 5 $0.00030 $0.00282
Opus 5 $0.00015 $0.00141
Sonnet 5 $0.00006 $0.00056
Haiku 4.5 $0.00003 $0.00028

Measured yesterday against content hash 2fd6d4f36a12, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

errors 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 yesterday.

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.

plugins/bunjs/commands/errors.md · 22 lines

What it actually says

<user_request>$ARGUMENTS</user_request>

  1. Read skills/errors/SKILL.md in full first, resolved against this plugin's own directory (the tree this command was loaded from). It is the router: it names which files in skills/errors/references/ your task actually needs. Read those too before writing code.

Use this for error handling, custom error types, validation boundaries, retries, timeouts, circuit breakers, or any "this should fail more gracefully" task.

  1. Copy skills/errors/assets/errors/ into the project rather than retyping the hierarchy. The operational-vs-programmer distinction is the whole design; AppError.isOperational() returns false for anything unrecognised, which is the safe default.
  2. Before reporting done: grep the diff for the four swallow patterns in the skill's Acceptance section, and confirm every fetch/DB call on a request path is wrapped in withTimeout. catch (e) { throw new Error(e.message) } destroys the stack AND the cause.
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.

  1. yesterday First seen · 22 lines · 30 tokens per session scan A 2fd6d4f36a12

Subscribe to this mod's changes

errors is a command published in the GitHub repository MadAppGang/magus (9 stars, last pushed 3d ago), licensed MIT. It adds 30 tokens to every session and 282 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.