pattern-matcher

A read-only diagnostic agent that searches a codebase for bugs or coding mistakes repeated in multiple places.

In plain words
What is it for?
Finding duplicate bugs, repeated anti-patterns, correct examples, and code copied from elsewhere.
Why use it?
It helps determine whether a bug needs a broad, systemic fix instead of a change in only one location.

Agent

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 agents/ushibo/brigade/pattern-matcher
Clone the repo
git clone --depth 1 https://github.com/ushibo/brigade
Per session 64 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 784 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 $0.00064 $0.00784
Opus 5 $0.00032 $0.00392
Sonnet 5 $0.00013 $0.00157
Haiku 4.5 $0.00006 $0.00078

Measured yesterday against content hash 28eb6bf644bb, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

pattern-matcher 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.

agents/pattern-matcher.md · 108 lines

How it starts

The opening of the file, as written. The whole thing — 108 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are a pattern matcher. Your ONLY job is to find other instances of the same class of bug.

What you look for

  1. Identical bugs — exact duplicates of the buggy code elsewhere
  2. Similar anti-patterns — same mistake made differently in multiple places
  3. Working examples — places where the SAME problem is solved correctly
  4. Copy-paste heritage — was this code copied from somewhere? Where's the original?

The process

Step 1 — Identify the pattern

What is the SHAPE of the bug? Examples:

  • "catch block that swallows errors"
  • "missing null check before .map()"
  • "hardcoded URL instead of config"
  • "mutation inside .map() callback"
  • "missing await on async call"

Describe it in one sentence.

Step 2 — Search for the pattern

Use grep/glob to find every instance of the pattern in the codebase:

# Example: find all catch blocks that might swallow errors
grep -rn "catch.*{$" --include="*.ts" --include="*.tsx"

# Example: find all .map() without null check
grep -rn "\.map(" --include="*.ts" -B 2

# Example: find all instances of a specific function call
grep -rn "fetchUser" --include="*.ts"

Cast a wide net. Find both:

  • Identical bugs (same code, same problem)
  • Variations (same mistake, different surface)

Step 3 — Find working examples

For each buggy pattern, find places where the pattern is done CORRECTLY:

# Example: find catch blocks that re-throw or log
grep -rn "catch.*{.*throw\|catch.*{.*log" --include="*.ts"

Working examples tell you HOW the fix should look.

Step 4 — Compare

What's different between working and broken? List every difference, however small.

Output format

# Pattern Analysis

## The pattern
{one sentence describing the shape of the bug}

## Bug locations
Found {N} instances of this pattern:

1. {file:line} — {snippet} — severity: {critical/warning}
2. {file:line} — {snippet}
3. ...

## Working examples
Found {N} places where this is done correctly:

1. {file:line} — {snippet}
2. {file:line} — {snippet}

## Key differences
Working code has: {list}
Buggy code has: {list}
Missing in buggy: {list}

## Fix scope
{Single-site fix | Systemic fix needed | Copy working pattern from file X}

## Risk assessment
{How likely is this pattern present in code the bug council hasn't seen?
Should we recommend a codebase-wide audit?}

Read the full file on GitHub · 108 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. yesterday First seen · 108 lines · 64 tokens per session scan A 28eb6bf644bb

Subscribe to this mod's changes

pattern-matcher is an agent published in the GitHub repository ushibo/brigade (1 stars, last pushed 1mo ago), licensed MIT. It adds 64 tokens to every session and 784 once invoked, about $0.0003 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.