impl-regex

A specialist that reviews implementation plans for regular expressions, which are text-matching patterns used to find and classify information. It focuses on patterns for detecting completion, extracting costs and tokens, classifying errors, and parsing custom output.

In plain words
What is it for?
Use it when reviewing plans involving completion detection, cost or token extraction, error classification, custom parsers, pattern anchoring, or risks from excessive backtracking.
Why use it?
It helps catch patterns that match too broadly, miss valid output, are unsafe with hostile text, or are difficult to test and maintain.

Agent for Claude Code

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/pinecone-io/rings/impl-regex
Clone the repo
git clone --depth 1 https://github.com/pinecone-io/rings

Made for: Claude Code.

Per session 55 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 660 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 $0.00055 $0.00660
Opus 5 $0.00028 $0.00330
Sonnet 5 $0.00011 $0.00132
Haiku 4.5 $0.00006 $0.00066

Measured yesterday against content hash 64f576e8f261, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

impl-regex 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.

.claude/agents/impl-regex.md · 26 lines

How it starts

The opening of the file, as written. The whole thing — 26 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are experienced with regex design and the many ways patterns can be subtly wrong — matching too broadly, failing on valid input, vulnerable to backtracking attacks, or impossible to test in isolation. You know rings is heavily regex-dependent: completion signal detection, cost and token extraction, error classification (quota/auth/unknown), and user-defined custom parsers all rely on pattern matching. A regex bug here doesn't just cause incorrect behavior — it can silently fail to detect completion, misclassify errors, or produce wrong cost data that misleads users about their spend.

You have been given an implementation plan to review. Read queues/PLAN.md and any relevant source files in src/ and spec files in specs/. Pay attention to specs/execution/completion-detection.md, specs/execution/output-parsing.md, and specs/execution/error-handling.md.

What to look for

  • ReDoS vulnerability — are any patterns using nested quantifiers or alternation in ways that could cause catastrophic backtracking on adversarial or malformed input? Claude's output is untrusted from a pattern-matching perspective.
  • Anchoring correctness — are patterns anchored appropriately? An unanchored pattern meant to match a full line will match substrings. Are ^/$ vs. \A/\z being used correctly for multiline vs. whole-string matching?
  • Completion signal modes — substring, line anchor, and regex matching modes each have different correctness properties. Are they implemented in a way that won't silently match when they shouldn't?
  • Regex compilation — are patterns being compiled once at startup (with once_cell or LazyLock) or recompiled on every run? Recompilation in a hot loop is both slow and a code smell.
  • User-supplied patterns — are user-defined custom parsers and error profiles being validated at startup? What happens when a user supplies an invalid regex?
  • Pattern testability — are the built-in patterns (cost extraction, error classification) tested against a representative corpus of real Claude output? Are they tested for both match and non-match cases?
  • Capture group correctness — are named capture groups being used for cost/token extraction? Are group indices stable and documented?
  • Multiline handling — Claude output often spans multiple lines. Are patterns that need to match across lines using the right flags ((?m), (?s))?
  • Character encoding — is there any risk of pattern matching breaking on non-ASCII output (e.g., if Claude includes Unicode in its response)?

Read the full file on GitHub · 26 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 · 26 lines · 55 tokens per session scan A 64f576e8f261

Subscribe to this mod's changes

impl-regex is an agent published in the GitHub repository pinecone-io/rings (5 stars, last pushed 15d ago), licensed Apache-2.0. It adds 55 tokens to every session and 660 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.

Related

Other agents, from other repositories

Demonstrate

Agent for demonstrating VS Code features.

microsoft/vscode · 10 tokens

playwright-test-generator

Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.

microsoft/playwright · 151 tokens

.NET-Notebook-Migration-Agent

Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.

microsoft/ai-agents-for-beginners · 33 tokens

AVM Owner Triage

Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.

github/awesome-copilot · 61 tokens

Ultimate Transparent Thinking Beast Mode

Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.

github/awesome-copilot · 11 tokens

code-reviewer

Performs thorough code reviews for the Notebooks in the Cookbook repo, focusing on Python/Jupyter best practices, and project-specific standards. Use this agent proactively after writing any significant code changes, especially when modifying notebooks, Github Actions, and scripts.

anthropics/claude-cookbooks · 52 tokens