pattern-check

A pre-debugging checklist that compares a reported bug with known root-cause patterns. It reports possible matches, confidence, and suggested checks.

In plain words
What is it for?
Use it at the start of an investigation to classify an error, choose initial checks, and decide whether to proceed to reproducing the problem.
Why use it?
It helps developers check familiar causes before spending time on open-ended debugging.

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/soleimanmansouri/debug-bank/pattern-check
Any agent
npx skills add soleimanmansouri/debug-bank --skill pattern-check
Clone the repo
git clone --depth 1 https://github.com/soleimanmansouri/debug-bank

Made for: Claude Code, Codex.

Per session 39 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 458 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 $0.00039 $0.00458
Opus 5 $0.00019 $0.00229
Sonnet 5 $0.00008 $0.00092
Haiku 4.5 $0.00004 $0.00046

Measured 2d ago against content hash 2522728ee3f0, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

pattern-check 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.

skills/pattern-check/SKILL.md · 69 lines

What it actually says

Pattern Check — Quick Scan

You are performing a pattern check before debugging. This is Step 1 of the debug trajectory protocol.

Instructions

  1. Read the symptom/error description provided
  2. Scan each pattern (P01-P19+) in the pattern bank
  3. For each pattern, check: "Could this symptom be caused by this root cause type?"
  4. Report your findings

Output Format

If Match Found

PATTERN MATCH: P[XX] — [Pattern Name]

Confidence: HIGH / MEDIUM / LOW
Reasoning: [Why this pattern matches the symptom]

Suggested checks:
- [ ] [Check 1 from the pattern's check list]
- [ ] [Check 2]
- [ ] [Check 3]

If checks confirm, apply fix strategy from P[XX].

If No Match

NO PATTERN MATCH

Closest patterns considered:
- P[XX]: [Why it was close but doesn't match]
- P[XX]: [Why it was close but doesn't match]

Proceed to Step 2 (Reproduce) of the debug trajectory protocol.

If Multiple Matches

MULTIPLE PATTERN MATCHES (ranked by likelihood):

1. P[XX] — [Name] (CONFIDENCE: HIGH)
   Reasoning: [Why]
   
2. P[XX] — [Name] (CONFIDENCE: MEDIUM)
   Reasoning: [Why]

Start with the highest-confidence match. If its checks fail, try the next.

Speed Requirement

This check should take under 60 seconds. Do not investigate, reproduce, or attempt fixes during a pattern check. Only scan and report.

The value of this step is SPEED — a 30-second check that saves hours of re-investigation. If you spend more than 60 seconds, you're over-investigating.

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 · 69 lines · 39 tokens per session scan A 2522728ee3f0

Subscribe to this mod's changes

pattern-check is a skill published in the GitHub repository soleimanmansouri/debug-bank (1 stars, last pushed 3mo ago), licensed MIT. It adds 39 tokens to every session and 458 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.