error-messages

error-messages is a skill for Claude Code from navraj007in/architecture-cowork-plugin. It costs 18 tokens per session (5,219 once invoked), scanned B, original, Apache-2.0.

A template for writing clear software error messages in four parts: what went wrong, why it matters, how to fix it, and optional context.

In plain words
What is it for?
Use it when designing error output for commands, tools, and development workflows.
Why use it?
It makes failures easier to understand and act on. Better explanations can reduce the time users spend diagnosing problems.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the architect plugin — 48 skills, 63 commands, 19 agents, 7 MCP servers shipped together

Good fit Use it when designing error output for commands, tools, and development workflows.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/navraj007in/architecture-cowork-plugin/error-messages
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.

Any agent
npx skills add navraj007in/architecture-cowork-plugin --skill error-messages
Clone the repo
git clone --depth 1 https://github.com/navraj007in/architecture-cowork-plugin

Made for: Claude Code.

Or install architect, the plugin that ships this one along with the rest of its 48 skills, 63 commands, 19 agents, 7 MCP servers.

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.

agentmods badge for error-messages

README.md
[![agentmods](https://agentmods.dev/badge/skills/navraj007in/architecture-cowork-plugin/error-messages/github.svg)](https://agentmods.dev/skills/navraj007in/architecture-cowork-plugin/error-messages)
Your own site
<a href="https://agentmods.dev/skills/navraj007in/architecture-cowork-plugin/error-messages"><img src="https://agentmods.dev/badge/skills/navraj007in/architecture-cowork-plugin/error-messages/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.

agentmods 80×15 button for error-messages

Your own site · 80×15
<a href="https://agentmods.dev/skills/navraj007in/architecture-cowork-plugin/error-messages"><img src="https://agentmods.dev/badge/skills/navraj007in/architecture-cowork-plugin/error-messages.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 18 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 5,219 The whole file, excluding the scripts and references it only reads on demand.
Security scan B 1 finding. 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00018 $0.05219
Opus 5 $0.00009 $0.02610
Sonnet 5 $0.00004 $0.01044
Haiku 4.5 $0.00002 $0.00522

Measured 9d ago against content hash aeb643b903d4, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade B, and why

error-messages scanned grade B with 1 finding 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 9d 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.

Asks for rootmediumPrivilege escalation

A mod that escalates privileges can change anything on the machine, not only the project.

Ubuntu: sudo apt-get install git
docs/archive/skills/error-messages/SKILL.md · 814 lines

How it starts

The opening of the file, as written. The whole thing — 814 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Error Messages Skill

Provides clear, actionable error messages that help users understand what went wrong, why it matters, and how to fix it. Better error messages reduce debugging time and user frustration.

Error Message Structure

Every error should follow this 4-part template:

❌ [WHAT WENT WRONG]

[WHY THIS MATTERS]

[HOW TO FIX IT]

[OPTIONAL CONTEXT]

Part 1: What Went Wrong

Clear, specific statement of the error. No jargon unless unavoidable.

Bad:

Error: ENOENT: no such file or directory, open '_state.json'

Good:

❌ State file not found (_state.json)

Better:

❌ State file not found (_state.json)
Project state required to generate tests.

Part 2: Why This Matters

1-2 sentences explaining impact. What breaks if user ignores this?

Bad:

(skipped — no explanation)

Good:

Without state, I can't determine your project's tech stack, components, or design tokens.
This means tests won't know what framework to use or what components to test.

Part 3: How to Fix It

Actionable steps to resolve. Start with the simplest fix.

Bad:

(skipped — vague)

Good:

How to fix:
1. Run /architect:blueprint to create initial project state
   (Estimated time: 20 minutes)
2. Once complete, try this command again: /architect:generate-tests

Part 4: Optional Context

Links to related commands, documentation, or debugging info. Skip if irrelevant.

Good addition:

Want to understand the prerequisite chain? Run /architect:next-steps

Error Categories & Examples

1. Missing Prerequisites

Trigger: User tries to run command X, but required input for X doesn't exist.

Template:

❌ [COMMAND] requires [PREREQUISITE], which hasn't been created yet.

[PREREQUISITE] is necessary because [WHY].

How to fix:
1. Run /architect:[FIX_COMMAND] (estimated X min)
2. Once complete, try /architect:[COMMAND] again

Questions? Run /architect:next-steps to see all recommendations.

Read the full file on GitHub · 814 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.

  1. 9d ago First seen · 814 lines · 18 tokens per session scan B aeb643b903d4

Subscribe to this mod's changes

error-messages is a skill published in the GitHub repository navraj007in/architecture-cowork-plugin (2 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 18 tokens to every session and 5,219 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it B with 1 finding (asks for root). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.

Related

Other skills, from other repositories

analyze-github-issue

A workflow for deeply assessing one GitHub issue, including whether it is a real bug or a reasonable feature request.

TNT-Likely/honeycomb · 166 tokens

diagnose

Bundle a redacted, support-grade snapshot of the current nyann state for inclusion in a bug report or support request. Combines explain-state + doctor + git config (token-redacted) + installed hook contents + nyann user-config (token-redacted) + check-prereqs into a single JSON or human-readable summary. TRIGGER when…

thettwe/nyann · 202 tokens

Data Flow & State Ownership

Ensure designs define data flow, state ownership, consistency boundaries, and cross-boundary writes to prevent drift and incidents.

s977043/river-review · 29 tokens

doctor

Use when the capstone docs area needs a consistency check or repair - torn writes, done markers without ledger entries, voided plan approvals, index rows pointing at missing files, absorption gaps - reports findings with their owning rules, then applies only the repairs the user approves.

GentBajko/capstone · 56 tokens

refactor

Automated iterative code refactoring with swarm-orchestrated specialist agents including deep codebase discovery, confidence-scored code review, and security analysis. Use this skill when the user wants to improve existing code quality, clean up messy code, restructure, simplify, reduce tech debt, or perform…

zircote-plugins/refactor · 112 tokens

debug

Interactive debugging workflow with hypothesis-driven probe loop. Use when: unknown bugs, script errors, silent failures, troubleshooting. Not for: known bugs (use bug-fix), GitHub issue analysis (use issue-analyze), code understanding (use code-explore). Output: debug report with probe journal + root cause + fix.

sd0xdev/sd0x-harness · 67 tokens