neo-pattern

neo-pattern is a skill for Claude Code from Parslee-ai/neo. It costs 71 tokens per session (919 once invoked), scanned A, original, Apache-2.0.

A coding assistant for extracting reusable ways of solving problems from code, or finding similar patterns already used in a codebase. A code pattern is a repeatable approach that can guide future work.

In plain words
What is it for?
Use it to document a proven pattern or locate matching implementations across the codebase.
Why use it?
It helps identify useful project conventions while avoiding abstractions based on only one example. Extracted lessons are stored as durable shared memory.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: mentions Codex; $skill-name invocation.

Part of the neo plugin — 9 skills, 18 commands, 1 agent, 1 hook shipped together

Good fit Use it to document a proven pattern or locate matching implementations across the codebase.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/parslee-ai/neo/neo-pattern
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.

Any agent
npx skills add Parslee-ai/neo --skill neo-pattern
Clone the repo
git clone --depth 1 https://github.com/Parslee-ai/neo

Made for: Claude Code.

Or install neo, the plugin that ships this one along with the rest of its 9 skills, 18 commands, 1 agent, 1 hook.

Wrote 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.

agentmods badge for neo-pattern

README.md
[![agentmods](https://agentmods.dev/badge/skills/parslee-ai/neo/neo-pattern.svg)](https://agentmods.dev/skills/parslee-ai/neo/neo-pattern)
Your own site
<a href="https://agentmods.dev/skills/parslee-ai/neo/neo-pattern"><img src="https://agentmods.dev/badge/skills/parslee-ai/neo/neo-pattern.svg" alt="Measured on agentmods" height="20"></a>
Per session 71 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 919 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
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 5.1 $0.00071 $0.00919
Opus 5 $0.00036 $0.00460
Sonnet 5 $0.00014 $0.00184
Haiku 4.5 $0.00007 $0.00092

Measured 8d ago against content hash da830477aaa2, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

neo-pattern 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 8d 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.

plugins/neo/skills/neo-pattern/SKILL.md · 75 lines

How it starts

The opening of the file, as written. The whole thing — 75 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Neo Pattern Extraction

When the user invokes this skill ($neo-pattern <code reference or description>), do the following:

  1. Determine direction. Is the user asking neo to: (a) Extract a pattern from a piece of code they're pointing at? — gather the code, then ask Neo to articulate the reusable pattern. (b) Find instances of a pattern in the codebase based on a description? — gather the description, then ask Neo to locate matching code.

  2. For extraction: read the source code the user referenced. Include enough surrounding context that the pattern is intelligible.

  3. For pattern-finding: translate the user's description into search terms. Use Grep/Glob to gather candidate files; pass them to Neo for semantic matching against the description.

  4. Apply the provider and learning boundary. Redact secrets, credentials, tokens, cookies, and session material. Before an external-provider call, tell the user which Neo provider will receive which files or data categories. Production, private, or customer code requires explicit authorization for that provider and scope. Because this learning workflow uses shared Neo memory, also disclose that relevant stored facts may be selected for the provider prompt and that learn records an episode candidate.

  5. Invoke Neo with a pattern-framed prompt. Allow up to 5 minutes. Use Codex's approval flow for required network access, naming the provider, summarized data, and candidate-learning effect in the approval description.

    neo --json --no-scan --mode learn <<'QUERY'
    <Extract a reusable pattern from> | <Find code matching this pattern>:
    
    <code or description here>
    
    Articulate: name, signature/shape, when to apply, when NOT to apply, common pitfalls.
    QUERY
    
  6. Present the pattern with concrete examples. A named pattern with two example sites is more useful than an abstract description of one.

--no-scan is mandatory: Codex already selected the pattern evidence, so Neo must not silently add working-directory files to the provider request.

Read the full file on GitHub · 75 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. 8d ago First seen · 75 lines · 71 tokens per session scan A da830477aaa2

Subscribe to this mod's changes

neo-pattern is a skill published in the GitHub repository Parslee-ai/neo (16 stars, last pushed yesterday), licensed Apache-2.0. It adds 71 tokens to every session and 919 once invoked, about $0.0004 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 2026-08-30.