skill-patterns AGENTS.md

Repository instructions for maintaining a catalog and its installable plugins across separate Git branches. Generated website files are produced automatically and should not be edited by hand.

In plain words
What is it for?
Adding or editing catalog patterns, rebuilding generated snapshots, checking required metadata, and preparing changes for a pull request.
Why use it?
They prevent edits in the wrong branch and keep generated catalog data consistent with its source files.

Instructions file for CodexOpenCode

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 instructions/borkweb/skill-patterns/agents-md
Clone the repo
git clone --depth 1 https://github.com/borkweb/skill-patterns

Made for: Codex, OpenCode.

Per session 654 This file is loaded in full into every session.
When invoked 654 The same file — it is already loaded in full.
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 $0.00654 $0.00654
Opus 5 $0.00327 $0.00327
Sonnet 5 $0.00131 $0.00131
Haiku 4.5 $0.00065 $0.00065

Measured yesterday against content hash 2f98b4a3668d, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

skill-patterns AGENTS.md 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.md · 33 lines

How it starts

The opening of the file, as written. The whole thing — 33 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md

Guidance for AI agents (and humans) working in this repository.

Two branches, two jobs

  • main (default) — the canonical home of the catalog and the installable plugin for Claude / Codex / Gemini. Holds patterns/*.md (the catalog source), categories.yml, the generator scripts/build.mjs, the .claude-plugin/ manifests, and skills/skill-patterns/.
  • gh-pages — the website that publishes skillpatterns.ai (a Jekyll site). Its catalog inputs (_patterns/, _data/categories.yml, llms.txt, patterns.json) are generated from main and synced in by CI. Do not hand-edit them there.

Adding or editing a pattern

  1. Edit (or add) one file in patterns/ on main. Frontmatter: title, slug (must match the filename), icon (FontAwesome Free), category (a key in categories.yml), summary, adds (list), related (list of {slug, note}, optional), prompt (block scalar).
  2. Run npm run build — regenerates the plugin snapshot at skills/skill-patterns/references/patterns.md (and build/llms.txt, build/patterns.json).
  3. Open one PR against main. The Sync catalog workflow's snapshot-check job fails the PR if you skipped step 2. On merge, the sync-to-pages job regenerates and pushes _patterns/, _data/categories.yml, llms.txt, and patterns.json to gh-pages, and the site rebuilds.

No Jekyll, no second branch to edit.

Never hand-edit generated files

All produced by scripts/build.mjs — edit patterns/ + categories.yml and rebuild:

  • on main: skills/skill-patterns/references/patterns.md
  • on gh-pages: _patterns/*.md, _data/categories.yml, llms.txt, patterns.json

Conventions

  • Patterns sort alphabetically by title within their category; the pattern order field is unused. Category order comes from order in categories.yml.
  • The build validates input and fails with a named error on: unknown category; duplicate or filename-mismatched slug; adds that isn't a list; a related entry missing slug/note or pointing at a nonexistent pattern; a category missing a numeric order.

Read the full file on GitHub · 33 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 · 33 lines · 654 tokens per session scan A 2f98b4a3668d

Subscribe to this mod's changes

skill-patterns AGENTS.md is an instructions file published in the GitHub repository borkweb/skill-patterns (5 stars, last pushed 3mo ago), licensed MIT. It adds 654 tokens to every session, about $0.0033 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 instructions, from other repositories

ai-toolkit AGENTS.md

Instructions for pipefy/ai-toolkit, covering repository guidelines, documentation map, project structure, import namespace migration: pipefysdk → pipefy and src/pipefysdk/init.py (transitional shim).

pipefy/ai-toolkit · 3,184 tokens

superpowers-reasonix AGENTS.md

Instructions for christopherarter/superpowers-reasonix, covering project guidance, skills — stop. load a skill before you act, red flags — these thoughts mean stop. you are rationalizing and priority.

christopherarter/superpowers-reasonix · 761 tokens

ai-mind AGENTS.md

Instructions for HWYD/ai-mind, covering agents, version spec workspace continuity (mandatory), 项目定位, 事实来源优先级 and 开始大改前先读什么.

HWYD/ai-mind · 3,170 tokens

finding-unknowns-skills CLAUDE.md

Claude Code instructions for Neeeophytee/finding-unknowns-skills, covering repo notes, what ships, and the gate that decides, version lives in three manifests — move them together, files that must be edited together and shipped guidance is not this file.

Neeeophytee/finding-unknowns-skills · 1,447 tokens

vvvv-skills CLAUDE.md

Claude Code instructions for tebjan/vvvv-skills, covering vvvv gamma, when to patch vs code, core concepts, live environment and important conventions.

tebjan/vvvv-skills · 987 tokens

pi AGENTS.md

AGENTS.md instructions for counterposition/pi, covering agents.md, commands, pattern: pnpm --filter @counterposition/pi-web-search run, single test file and single test by name.

counterposition/pi · 806 tokens