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.
npx skills add Arcadi4/nerdy --skill string-matchinggit clone --depth 1 https://github.com/Arcadi4/nerdyWrote 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.
[](https://agentmods.dev/skills/arcadi4/nerdy/string-matching)<a href="https://agentmods.dev/skills/arcadi4/nerdy/string-matching"><img src="https://agentmods.dev/badge/skills/arcadi4/nerdy/string-matching/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/arcadi4/nerdy/string-matching"><img src="https://agentmods.dev/badge/skills/arcadi4/nerdy/string-matching.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00056 | $0.03868 |
| Opus 5.5 | $0.00022 | $0.01547 |
| Sonnet 5.5 | $0.00011 | $0.00774 |
| Haiku 4.5 | $0.00006 | $0.00387 |
Grade A, and why
string-matching 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 1mo 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.
How it starts
The opening of the file, as written. The whole thing — 365 lines — stays where its author put it; the contents beside it link to each section on GitHub.
String Matching
Overview
String matching is about preserving information from previous character comparisons. The right method depends on whether the text is scanned once, patterns repeat, hashes are acceptable as filters, a full automaton is affordable, or the corpus should be indexed for many later queries.
Core principle: choose the matcher by workload and model assumptions, then state the invariant that makes skipped comparisons safe.
Shared CLRS Conventions
Follow the parent clrs skill for mathematical formatting, formula-free headings, direct polished answers, and CLRS-wide answer style. Keep string indices, costs, recurrences, and asymptotic bounds in display LaTeX blocks rather than inline prose.
When a table needs a cost or formula, keep the cell verbal and place the expression in a display block nearby.
For pressure-test answers, treat concrete assignments and indexed values as formulas too. Do not write prefix-function updates, array entries, or length equalities inline; introduce them in prose and put the symbolic expression in a display block.
When to Use
- A prompt asks for exact pattern occurrences, valid shifts, overlaps, string-matching automata, Rabin-Karp, KMP, suffix arrays, LCP arrays, cyclic rotations, or Burrows-Wheeler transforms.
- You need to compare naive matching, rolling hashes, finite automata, KMP, and suffix-array indexing under a workload constraint.
- A proof asks why a shift is safe after a mismatch, why automaton states mean longest matched prefixes, or why suffix-array matches form a consecutive block.
- A production question involves collision risk, adversarial text, large alphabets, static corpora, many pattern queries, or reuse of learned comparisons.
Do not use this skill for approximate matching, edit distance, regular-expression engines, suffix trees, tries, or general dynamic programming unless exact substring search is the core issue.
String-Matching Model
Name the text, pattern, alphabet, and valid shift before choosing an algorithm.
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.
- 1mo ago First seen · 365 lines · 56 tokens per session scan A 58bb8b7be660
string-matching is a skill published in the GitHub repository Arcadi4/nerdy (6 stars, last pushed 6mo ago), licensed MIT. It adds 56 tokens to every session and 3,868 once invoked, about $0.0002 per session on Opus 5.5. 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.
Other skills, from other repositories
agent-state-bar
A design guide for an agent status bar: a short, automatically updated summary of progress, remaining tasks, tool counts, errors, and system state placed near the latest model input.
context-engineering
A guide to organizing the instructions and information an AI agent receives at each step. It covers system prompts, tool descriptions, conversation history, on-demand skills, and protections against unsafe outside content.
kv-cache-design
A guide to arranging an AI agent's conversation so previously processed text can be reused. A KV cache stores intermediate results for earlier tokens, while a prompt cache reuses a stable beginning across requests.
multi-agent-design
A guide to deciding when several AI agents should work together and how they should share tasks, context, and files. It compares peer, manager-led, and decentralised arrangements and explains common coordination failures.
reward-design
A guide to defining the scores that an AI agent receives during trial-and-error training. It covers checks based on rules, human preferences, or another model, and distinguishes rewarding the final result from rewarding the steps taken.
loop-engineering
A guide to building reliable loops for AI agents that plan, act, check their work, and continue until a task is truly complete. It includes independent verification and a proposer-reviewer pattern in which one agent's work is checked using outside evidence.