A project-specific reference for the code patterns and conventions used in a software project. It includes named patterns with explanations and code examples.

Use it when designing, implementing, verifying, or reviewing code that must follow the project's established approaches, such as safe file access, rollback, validation, and request handling.

It gives coding work a shared set of rules, so new or reviewed code is more consistent with the rest of the project.

patterns — Skill by nklisch

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/nklisch/skilltap/patterns

Any agent

npx skills add nklisch/skilltap --skill patterns

Clone the repo

git clone --depth 1 https://github.com/nklisch/skilltap

Made for: Claude Code, Codex.

Per session 30 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 390 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.

Model	Per session	Once invoked
Fable 5	$0.00030	$0.00390
Opus 5	$0.00015	$0.00195
Sonnet 5	$0.00006	$0.00078
Haiku 4.5	$0.00003	$0.00039

Measured yesterday against content hash 9366778c37b6, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

patterns 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/skills/patterns/SKILL.md · 23 lines

What it actually says

Project Patterns Reference

This skill contains detailed pattern documentation for this project. See individual pattern files for full details with code examples.

Available patterns:

revalidated-execution-port.md — Bind planned operations to adapter requests, revalidate them under lock, then apply through ExecutionPort.
root-confined-filesystem-port.md — Access managed descendant files through a canonical root and no-follow relative-path operations.
drift-checked-managed-projection-plan.md — Plan skill trees and MCP config as fingerprinted writes, re-observe owned projections, and fail on drift.
target-local-resource-state.md — Mutate lifecycle evidence on exact harness bindings and preserve unselected sibling state.
identity-aware-rollback.md — Roll back only proven owned identities and report post-observed residuals when restoration is incomplete.
validated-wire-contract.md — Serialize domain values through private wire DTOs and rebuild them through validating constructors.
validated-string-newtypes.md — Represent bounded domain text with one validated, serde-aware newtype rather than raw String.
bounded-native-process-port.md — Resolve binaries and run direct argument vectors through the bounded runner with explicit limits.
isolated-native-fixture-roots.md — Exercise native and filesystem behavior only inside test-support-owned temporary roots and fake binaries.

Files

What ships with it

9 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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.

yesterday First seen · 23 lines · 30 tokens per session scan A 9366778c37b6

Subscribe to this mod's changes

patterns is a skill published in the GitHub repository nklisch/skilltap (6 stars, last pushed 17d ago), licensed MIT. It adds 30 tokens to every session and 390 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.

agent-skills ai-agents bun claude cli codex

format-specific-extraction

Format-specific document extraction workflows.

xberg-io/xberg · 10 tokens

api-server-mcp

REST API server and MCP protocol integration.

xberg-io/xberg · 12 tokens

rust-system-calls

Guides using bunsys for system calls and file I/O in Rust. Use when implementing file operations, opening fds, or any syscall path instead of std::fs or libc.

oven-sh/bun · 42 tokens

bunqueue-dev

Internal skill for contributing to bunqueue - architecture, testing, code conventions, and development workflow.

egeominotti/bunqueue · 22 tokens

decocms-ui

Build or style React UI with the decocms product design system (@decocms/ui). Use when creating interfaces, pages, or components in a project that should look like decocms products, when the user mentions "design system", "@decocms/ui", "decocms style", or asks to make UI consistent with Studio. Covers installation…

decocms/studio · 91 tokens

google-meet

Google Meet via gws: create spaces, fetch join links, list recordings.

Open-Curiosity/gini-agent · 20 tokens