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 varunk130/ai-workflow-playbooks --skill error-interpretationgit clone --depth 1 https://github.com/varunk130/ai-workflow-playbooksWrote 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/varunk130/ai-workflow-playbooks/error-interpretation)<a href="https://agentmods.dev/skills/varunk130/ai-workflow-playbooks/error-interpretation"><img src="https://agentmods.dev/badge/skills/varunk130/ai-workflow-playbooks/error-interpretation/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/varunk130/ai-workflow-playbooks/error-interpretation"><img src="https://agentmods.dev/badge/skills/varunk130/ai-workflow-playbooks/error-interpretation.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 | $0.00021 | $0.01467 |
| Opus 5.5 | $0.00008 | $0.00587 |
| Sonnet 5.5 | $0.00004 | $0.00293 |
| Haiku 4.5 | $0.00002 | $0.00147 |
Grade A, and why
error-interpretation 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.
How it starts
The opening of the file, as written. The whole thing — 107 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Error Interpretation
What This Skill Enables
Agents with this skill can diagnose failures methodically by reading what the system is actually telling them. Without it, agents fall into shotgun debugging -- trying random fixes, changing multiple things at once, and hoping something sticks. A skilled agent reads the error, forms a hypothesis, and verifies it before writing a single line of corrective code.
Core Competencies
1. Read the Actual Error Message First
This sounds obvious but is the most commonly skipped step. Before doing anything:
- Copy the full error output, not just the first line.
- Identify the error type or code (e.g.,
TypeError,ECONNREFUSED,HTTP 403, exit code 137). - Identify the error message (the human-readable explanation after the type).
- Note any file path and line number referenced.
# Example: Don't just see "TypeError". Read the whole thing.
TypeError: Cannot read properties of undefined (reading 'map')
at renderList (src/components/UserList.tsx:14:22)
at processChild (node_modules/react-dom/cjs/react-dom.development.js:1234:12)
# What to extract:
# Type: TypeError
# Message: Cannot read properties of undefined (reading 'map')
# Where: src/components/UserList.tsx, line 14, column 22
# What: Something is undefined when .map() is called on it
2. Parse Stack Traces Correctly
Stack traces list frames from most recent call to oldest. Your job is to find the boundary between your code and framework/library code.
| Frame Type | How to Identify | What to Do |
|---|---|---|
| Your code | File path is in src/, app/, lib/, or your project directories. |
This is where the bug lives. Start here. |
| Framework code | Path is in node_modules/, standard library, or runtime internals. |
Usually not the bug. Tells you what the framework was doing when your code failed. |
| Generated code | Path references .next/, dist/, build/, __pycache__/. |
Map back to the source file. Don't edit generated code. |
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 · 107 lines · 21 tokens per session scan A af4e02b4f570
error-interpretation is a skill published in the GitHub repository varunk130/ai-workflow-playbooks (2 stars, last pushed 24d ago), licensed MIT. It adds 21 tokens to every session and 1,467 once invoked, about $0.0001 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.
Other skills, from other repositories
incident-postmortem
Escribe un postmortem de incidente estructurado o revisión post-incidente. Úsalo cuando se te pida escribir un postmortem, reporte de incidente, revisión P1/P2, reporte de apagón o RCA (análisis de causa raíz). Produce un postmortem sin culpables con cronología, causa raíz, factores contribuyentes, resumen de impacto…
agent-design-review
Review an LLM agent design and find where it will be unreliable, expensive, or unsafe. Use when asked to review an agent architecture, critique a multi-step/tool-using agent, debug an agent that loops or goes off-task, or harden an agent before launch. Produces a structured review — task fit, control flow, tools…
agent-incident-postmortem
Run a blameless postmortem for an incident caused by an AI agent or LLM feature — hallucinated facts shipped to users, runaway tool use, prompt injection, cost blowouts, or wrong actions taken autonomously. Use when asked to write up an AI incident, analyse why an agent did something wrong, or produce corrective…
prompt-debugging
Figure out why a prompt isn't working and fix it — diagnose the actual failure (ambiguity, missing context, wrong format, conflicting instructions) instead of randomly rewording. Use when asked why isn't my prompt working, the AI keeps ignoring my instructions, my prompt gives inconsistent results, or how do I fix…
rag-architecture-review
Review an existing Retrieval-Augmented Generation system and find why it underperforms. Use when asked to review or audit a RAG pipeline, diagnose wrong/ungrounded answers from a 'chat with your docs' feature, or improve an already-built knowledge assistant. Produces a staged review — ingestion, chunking, retrieval…
prompt-optimizer
Diagnose and rewrite an underperforming LLM prompt so it produces reliable, well-structured output. Use when asked to improve a prompt, fix a prompt that gives inconsistent or wrong results, reduce hallucination/refusals, or make output follow a format. Produces a rewritten prompt with a diagnosis of what was failing…