Context Engineering
abashev/vfs-s3
Optimizes agent context setup. An agent skill from abashev/vfs-s3.
Catalog of obstacles, anti-patterns and patterns for working with AI coding agents, covering context management and reliability, from a published patterns collection.
Install Augmented Coding Patterns Reference
$ npx skills add lexler/skill-factory --skill ai-patterns -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install lexler/skill-factory ai-patterns --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/lexler/skill-factory.git skills-src && mkdir -p .claude/skills && cp -r skills-src/output_skills/ai/ai-patterns .claude/skills/ai-patterns && rm -rf skills-srcUse ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.
Claude Code skills documentation · loads skills from .claude/skills/
Install the "ai-patterns" agent skill from https://github.com/lexler/skill-factory/tree/main/output_skills/ai/ai-patterns into .claude/skills/ai-patterns/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "ai-patterns", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/lexler/skill-factory/tree/main/output_skills/ai/ai-patternsType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add lexler/skill-factory --skill ai-patterns -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install lexler/skill-factory ai-patterns --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/lexler/skill-factory.git skills-src && mkdir -p .agents/skills && cp -r skills-src/output_skills/ai/ai-patterns .agents/skills/ai-patterns && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "ai-patterns" agent skill from https://github.com/lexler/skill-factory/tree/main/output_skills/ai/ai-patterns into .agents/skills/ai-patterns/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "ai-patterns", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add lexler/skill-factory --skill ai-patterns -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install lexler/skill-factory ai-patterns --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/lexler/skill-factory.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/output_skills/ai/ai-patterns .cursor/skills/ai-patterns && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "ai-patterns" agent skill from https://github.com/lexler/skill-factory/tree/main/output_skills/ai/ai-patterns into .cursor/skills/ai-patterns/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "ai-patterns", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/lexler/skill-factory.git --path output_skills/ai/ai-patterns--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add lexler/skill-factory --skill ai-patterns -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install lexler/skill-factory ai-patterns --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/lexler/skill-factory.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/output_skills/ai/ai-patterns .gemini/skills/ai-patterns && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "ai-patterns" agent skill from https://github.com/lexler/skill-factory/tree/main/output_skills/ai/ai-patterns into .gemini/skills/ai-patterns/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "ai-patterns", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install lexler/skill-factory ai-patternsInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add lexler/skill-factory --skill ai-patterns -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/lexler/skill-factory.git skills-src && mkdir -p .github/skills && cp -r skills-src/output_skills/ai/ai-patterns .github/skills/ai-patterns && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "ai-patterns" agent skill from https://github.com/lexler/skill-factory/tree/main/output_skills/ai/ai-patterns into .github/skills/ai-patterns/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "ai-patterns", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add lexler/skill-factory --skill ai-patterns -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install lexler/skill-factory ai-patterns --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/lexler/skill-factory.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/output_skills/ai/ai-patterns .opencode/skills/ai-patterns && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "ai-patterns" agent skill from https://github.com/lexler/skill-factory/tree/main/output_skills/ai/ai-patterns into .opencode/skills/ai-patterns/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "ai-patterns", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
Facts
- Skill name
ai-patterns- GitHub stars
- 239
- Token cost
- ~1.5k tokens
- SKILL.md length
- 591 words
- Files
- 2 (incl. scripts)
- Skills in repo
- 25
- Repo updated
- First seen
- Licence
- Apache-2.0
At a glance
Catalog of obstacles, anti-patterns and patterns for working with AI coding agents, covering context management and reliability, from a published patterns collection.
- Looking up a named AI-coding pattern or anti-pattern
- SKILL.md covers First Step: Ensure Repository…, Patterns Location, Context Management and Reliability & Quality, plus 4 more sections
- Diagnosing why an agent loses earlier instructions as a conversation grows
- Choosing how to split knowledge into focused files for an agent to load
What it does
The skill is a lookup index for a patterns collection by Lada Kesseler (lexler), Llewellyn Falco, Ivett Ördög and Nitsan Avni. Its first step is to run the bundled `ensure-patterns-repo` script, which makes sure the collection exists locally and is current; the documents are then read from a cache folder under `~/.cache/claude-skills`.
Entries are grouped by theme. Context management lists obstacles such as context rot, the limited context window and excess verbosity, the distracted-agent anti-pattern, and patterns such as knowledge documents, ground rules, extracting knowledge during a session, focused agents, reference docs and semantic zoom. Reliability and quality adds obstacles including non-determinism, hallucinations, degradation under complexity and selective hearing. Each item has a one-line summary. The excerpt is truncated partway through that second group.
When your agent uses it
- Looking up a named AI-coding pattern or anti-pattern
- Diagnosing why an agent loses earlier instructions as a conversation grows
- Choosing how to split knowledge into focused files for an agent to load
Example prompts
- “What does the ground-rules pattern recommend for keeping instructions in every session?”
- “My agent keeps ignoring instructions late in long sessions, which patterns apply?”
- “List the obstacles in the reliability section and how to steer around each.”
Requirements
- A local copy of the patterns repository, kept current by the bundled script
What it can do on your machine
Read from SKILL.md and the folder at commit 8017333. It shows what the files ask for, not the result of running them.
Tool permissions
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Runs code
Ships 1 file in scripts/, which the agent can run.
From the folder's file list and the shell code blocks in SKILL.md.
Network
Links to these hosts (documentation or services it may open):
lexler.github.io
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Context cost
Augmented Coding Patterns Reference loads about 1.5k tokens when it runs. Until then it costs about 51 tokens; SKILL.md has 591 words of instructions outside code blocks.
Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.
Safety
Auto-check passed
The automated check found no risky patterns in SKILL.md.
Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); the scripts in this folder are not scanned.
SKILL.md
The full file from lexler/skill-factory at commit 8017333, republished under its Apache-2.0 licence (© lexler). 591 words, ~1,473 tokens.
Download SKILL.mdSave it as
.claude/skills/ai-patterns/SKILL.md (or your agent's skills folder). This skill also uses 1 other file; get the full folder from GitHub.- name
- ai-patterns
- description
- Reference patterns for augmented coding with AI. Use when discussing AI coding patterns, anti-patterns, obstacles, context management, steering AI, or looking up Lexler's patterns collection.
AI Patterns Reference
Patterns for effective AI-augmented software development by Lada Kesseler (github nickname lexler), Llewellyn Falco, Ivett Ördög, and Nitsan Avni.
First Step: Ensure Repository Exists and Update
~/.claude/skills/ai-patterns/scripts/ensure-patterns-repoPatterns Location
Base path: ~/.cache/claude-skills/augmented-coding-patterns/documents
Context Management
Managing AI context, knowledge, and focus.
Obstacles
- context-rot - Earlier instructions lose influence as conversation grows
- cannot-learn - LLMs can't learn from interactions; fixed weights prevent adaptation
- limited-context-window - Fixed context size forces choices about what to keep loaded
- limited-focus - Too much context causes diluted or misdirected attention
- excess-verbosity - AI defaults to verbose output with low signal-to-noise ratio
Anti-patterns
- distracted-agent - Using one agent for everything spreads attention; instructions inconsistently followed
Patterns
- context-management - Treat context as scarce resource requiring active append/reset operations
- knowledge-document - Save important information as markdown files for session loading
- ground-rules - Essential behavioral rules auto-loaded into every session
- extract-knowledge - Save emerging insights and corrections from ephemeral context to files immediately during sessions
- focused-agent - Single narrow responsibility gives AI cognitive space to follow rules better
- reference-docs - On-demand knowledge loaded only when needed for current task
- knowledge-composition - Split knowledge into focused, composable files with single responsibilities
- semantic-zoom - Control abstraction levels—zoom out for overview or zoom in for details
- noise-cancellation - Explicitly ask AI to be succinct and strip filler from responses
Reliability & Quality
Handling non-determinism, complexity, and verification.
Obstacles
- non-determinism - Same input produces different outputs; results unpredictable
- hallucinations - AI invents non-existent APIs, methods, or syntax
- degrades-under-complexity - AI performance drops with complex multi-step tasks
- selective-hearing - AI ignores certain instructions; training data overrides explicit directives
Anti-patterns
- perfect-recall-fallacy - Expecting AI to perfectly remember library details instead of letting it discover
- unvalidated-leaps - Building on unverified assumptions instead of validating each step
- ai-slop - Using AI output without human judgment, just light editing
Patterns
- knowledge-checkpoint - Checkpoint planning before implementation to preserve thinking investment
- parallel-implementations - Run multiple implementations in parallel; pick best or combine
- offload-deterministic - Use code scripts for deterministic work instead of asking AI repeatedly
- playgrounds - Create isolated folders for AI to experiment and test assumptions safely
- chain-of-small-steps - Break complex goals into small, focused, verifiable steps
- hooks - Lifecycle event hooks intercept workflow; inject targeted corrections
- reminders - Repeat critical instructions as explicit steps; structural compliance
- feedback-flip - Have different AI focus on evaluation; flip from producing to finding problems
- refinement-loop - Give AI specific improvement goal and loop it; each pass removes one layer
Show full SKILL.md (215 more words)Show less
Communication
Directing AI behavior, getting honest feedback, and alignment.
Obstacles
- black-box-ai - AI's reasoning is hidden; you can only see inputs and outputs
- compliance-bias - AI prioritizes following instructions over questioning unclear requests
Anti-patterns
- silent-misalignment - AI accepts nonsensical instructions instead of asking clarifying questions
- answer-injection - Putting solutions in questions limits AI's breadth and better approaches
- tell-me-a-lie - Forcing AI to provide answers that don't exist causes fabrication
Patterns
- active-partner - Grant permission for AI to push back, disagree, and flag contradictions
- check-alignment - Force AI to show understanding before implementing to catch misalignment early
- context-markers - Visual emoji signals to show what instructions AI is currently following
- cast-wide - Push AI to show alternatives you haven't considered; avoid first-solution bias
- reverse-direction - Break monologue inertia—ask AI what it thinks instead
- polyglot-ai - Use right modality for task—voice for convenience, images for visual problems
- text-native - Keep everything as text; enables direct editing, version control, instant iteration
Additional Patterns
Patterns not on the main journey but useful in practice.
- shared-canvas - Markdown files as shared specs/docs; all humans and AI collaborate together
- softest-prototype - Use markdown instructions + AI agent instead of code for flexible exploration
- take-all-paths - Build multiple prototypes not one; test all, pick best through exploration
- borrow-behaviors - Give AI example and it adapts—styles, patterns, code across languages
Browse All
List patterns by category:
ls ~/.cache/claude-skills/augmented-coding-patterns/documents/patterns/
ls ~/.cache/claude-skills/augmented-coding-patterns/documents/anti-patterns/
ls ~/.cache/claude-skills/augmented-coding-patterns/documents/obstacles/Online
View at: https://lexler.github.io/augmented-coding-patterns/
© lexler, Apache-2.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
Files
SKILL.md and 1 other file (scripts) in output_skills/ai/ai-patterns of lexler/skill-factory.
- SKILL.md
- scripts/ensure-patterns-repo
Open the folder on GitHubat commit 8017333
Compare with similar skills
Augmented Coding Patterns Reference next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Augmented Coding Patterns Reference this skilllexler/skill-factory | 239 | — | ~1.5k | Automated safety check: Pass | Apache-2.0 | |
| Context Engineeringabashev/vfs-s3 | 106 | 9 repos | ~2.6k | Automated safety check: Notes | Apache-2.0 | |
| Harness Engineering10xChengTu/harness-engineering | 102 | 1 repos | ~1k | Automated safety check: Pass | None | |
| Cc Dev Agentsangrokjung/claude-forge | 849 | — | ~771 | Automated safety check: Pass | MIT | |
| Caveman Learn Token FixesJuliusBrussee/caveman | 110k | — | ~2.8k | Automated safety check: Pass | Apache-2.0 | |
| Context Routing Auditwithkynam/vibecode-pro-max-kit | 1.1k | — | ~1.2k | Automated safety check: Pass | MIT |
Similar skills
Harness Engineering
10xChengTu/harness-engineering
Set up and improve harness engineering (AGENTS.md, docs/, lint rules, eval systems, project-level prompt engineering) for AI-agent-friendly codebases.
Cc Dev Agent
sangrokjung/claude-forge
A skill your agent uses when starting Claude Code projects, writing CLAUDE.md/spec.md, dispatching subagents, or requesting Agent Teams parallel development.
Caveman Learn Token Fixes
JuliusBrussee/caveman
Acts on a Caveman learn report: reviews ranked token sinks, applies cost-lowering edits one at a time with your consent, and reports what each fix returned.
Context Routing Audit
withkynam/vibecode-pro-max-kit
Audits a project's context routing, skill discoverability and skill wiring by running a chain of validator scripts and fixing whatever they report.
Context Budget Check
poshan0126/dotclaude
Estimates the per-turn token cost of a project's .claude folder and CLAUDE.md, split into always-loaded, path-scoped and invoked-only files, and flags what runs over budget.
More from lexler/skill-factory
All 25 skills in this repoC4 Architecture Diagrams
lexler/skill-factory
Creates C4 model diagrams at every zoom level, from system landscape to code, in ASCII, Mermaid or Structurizr, for designing or documenting software architecture.
Launching Agent Teams
lexler/skill-factory
Plans and launches Claude Code agent teams with distinct roles, right-sized tasks and detailed spawn prompts, and says when subagents or worktrees fit better.
Claude Code Statusline Writer
lexler/skill-factory
Guides writing and debugging Claude Code status line scripts that read session JSON from stdin and print one line of text.
Approval Testing Toolkit
lexler/skill-factory
Writes snapshot-style approval tests in Python, JavaScript, TypeScript or Java, comparing output against an approved file instead of writing individual assertions.
Hotspots
lexler/skill-factory
Find where a codebase actually costs time by mining its git history (Tornhill hotspot analysis).
Nullables Testing Pattern
lexler/skill-factory
Teaches the Nullables pattern for testing without mocking libraries: production classes with an off switch, stubbed only at the third-party edge.
Related
Categories
Questions about Augmented Coding Patterns Reference
What does Augmented Coding Patterns Reference do?
Catalog of obstacles, anti-patterns and patterns for working with AI coding agents, covering context management and reliability, from a published patterns collection. The skill is a lookup index for a patterns collection by Lada Kesseler (lexler), Llewellyn Falco, Ivett Ördög and Nitsan Avni.cache/claude-skills`.
When should I use Augmented Coding Patterns Reference?
Augmented Coding Patterns Reference fits situations like: looking up a named AI-coding pattern or anti-pattern; diagnosing why an agent loses earlier instructions as a conversation grows; choosing how to split knowledge into focused files for an agent to load.
How do I install Augmented Coding Patterns Reference in Claude Code?
Run `npx skills add lexler/skill-factory --skill ai-patterns -a claude-code`. Or copy the skill folder (output_skills/ai/ai-patterns in lexler/skill-factory) into .claude/skills/ai-patterns in your project. Claude Code loads it when a task matches its description.
How do I install Augmented Coding Patterns Reference in Codex?
Run `npx skills add lexler/skill-factory --skill ai-patterns -a codex`. Or copy the skill folder (output_skills/ai/ai-patterns in lexler/skill-factory) into .agents/skills/ai-patterns in your project. Codex loads it when a task matches its description.
Can I use Augmented Coding Patterns Reference in Cursor, Gemini CLI or GitHub Copilot?
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add lexler/skill-factory --skill ai-patterns -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/ai-patterns, .gemini/skills/ai-patterns, .github/skills/ai-patterns and .opencode/skills/ai-patterns in your project.
What does Augmented Coding Patterns Reference need to run?
SKILL.md names no scripts, command-line tools or credentials: Augmented Coding Patterns Reference is instructions for the agent only. Our summary lists: A local copy of the patterns repository, kept current by the bundled script.
Does Augmented Coding Patterns Reference access the network?
SKILL.md names 1 domain. As links in the text: lexler.github.io. This is read from the text; nothing was executed.
Is Augmented Coding Patterns Reference safe to install?
Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. The check reads SKILL.md only: the scripts in the folder are not scanned, so read them before running anything.
What licence does Augmented Coding Patterns Reference use?
Augmented Coding Patterns Reference is published under the Apache-2.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
How many tokens does Augmented Coding Patterns Reference use?
About 1.5k tokens (SKILL.md is roughly 5.9k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.
What are the alternatives to Augmented Coding Patterns Reference?
Skills that share tags, products or a category with Augmented Coding Patterns Reference: Context Engineering (abashev/vfs-s3, 106 stars), Harness Engineering (10xChengTu/harness-engineering, 102 stars), Cc Dev Agent (sangrokjung/claude-forge, 849 stars) and Caveman Learn Token Fixes (JuliusBrussee/caveman, 110k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Augmented Coding Patterns Reference?
lexler (a GitHub user) maintains it in lexler/skill-factory, which has 239 GitHub stars. The repository holds 25 skills in this directory. The repository was last updated on August 26, 2026.
Source: lexler/skill-factory on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.