analyze-errors

An investigation tool for recurring errors and failures. It searches past records, arranges occurrences over time, and looks for patterns behind repeated problems.

In plain words
What is it for?
It helps collect related error records, build timelines, identify root causes, and create prevention strategies alongside an immediate fix.
Why use it?
It helps distinguish a one-time failure from a systemic cause, so the same issue is not repeatedly fixed by hand.

Skill for Claude CodeCodex

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 skills/ozmasterai/torus-framework/analyze-errors
Any agent
npx skills add OZmasterAI/Torus-Framework --skill analyze-errors
Clone the repo
git clone --depth 1 https://github.com/OZmasterAI/Torus-Framework

Made for: Claude Code, Codex.

Per session 0 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,210 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 $0.00000 $0.01210
Opus 5 $0.00000 $0.00605
Sonnet 5 $0.00000 $0.00242
Haiku 4.5 $0.00000 $0.00121

Measured 2d ago against content hash 3c0eda80b48a, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

analyze-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 2d 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.

dormant/skills/self-improve/analyze-errors/SKILL.md · 122 lines

How it starts

The opening of the file, as written. The whole thing — 122 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/analyze-errors — Recurring Error Deep Analysis

When to use

When the user says "analyze error", "why failing", "pattern", "recurring", "diagnose", "root cause", or wants to understand why an error keeps happening, find patterns in failures, or build a prevention strategy.

Complements /fix (immediate resolution) by doing historical pattern analysis across all memory to find systemic causes and build prevention playbooks.

Steps

1. DEEP QUERY

  • search_knowledge("[error pattern or message]", top_k=50) — get all historical instances
  • search_knowledge("[error keywords]") — catch keyword matches the semantic search may miss
  • search_knowledge("[error pattern]", mode="all") — also includes auto-captured observations
  • Collect every memory entry related to this error for comprehensive analysis

2. TIMELINE

Organize findings chronologically:

  • Sort all occurrences by timestamp
  • Build a progression view:
    Date       | Occurrence | Context              | Resolution
    -----------+------------+----------------------+------------------
    2026-01-15 | First seen | After deploying v2.1 | Manual fix
    2026-01-22 | Recurred   | Same endpoint        | Same manual fix
    2026-02-01 | Recurred   | Different trigger    | Attempted new fix
    2026-02-10 | Still open | Expanded scope       | Under investigation
    
  • Assess trend: getting worse, stable, improving, or resolved
  • Note any periodicity (daily, weekly, after deploys, after specific operations)

3. ROOT CAUSE

Read full entries with get_memory(id) for each occurrence. Classify the error:

Category Indicators Examples
Flaky test Passes sometimes, fails sometimes; no code change between runs Race condition in async test, timing-dependent assertion
Edge case Specific input triggers it; works for most inputs Unicode in filenames, empty arrays, null values
Environment Works locally, fails in CI; or vice versa Missing env var, different Python version, disk space
Race condition Intermittent; depends on timing/ordering Concurrent writes, async callback ordering
Integration failure External dependency changed or unavailable API version mismatch, service downtime, schema change
Regression Worked before, broke after specific commit Side effect of refactor, dependency update

Read the full file on GitHub · 122 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. 2d ago First seen · 122 lines · 0 tokens per session scan A 3c0eda80b48a

Subscribe to this mod's changes

analyze-errors is a skill published in the GitHub repository OZmasterAI/Torus-Framework (5 stars, last pushed 3mo ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 1,210 tokens. 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.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

brainstorming

You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.

obra/superpowers · 37 tokens

chat-pet-sprite-creation

Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.

microsoft/vscode · 53 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens

agent-host-chat-contributions

Build and review cross-cutting agent-host chat behavior through lifecycle contributions. Use when adding turn lifecycle side effects, prompt or context injection, restored-history transformation, protocol-action observation, or when reviewing changes that add code to AgentSideEffects or AgentService.

microsoft/vscode · 56 tokens

auto-perf-optimize

Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.

microsoft/vscode · 62 tokens