// blog
Notes on prompts, agents and versioning.
Worked examples and dated tool comparisons, each with sources. Want a starting point? The Pattern Library has copy-ready templates.
live now
Prompt Pattern Library
10 prompt structures with copy-ready templates you can drop straight into your library.
Prompt version control: what to track and how to start in two minutes
What to record for each prompt change, when git is enough, and a no-account local setup: save, log, diff and rollback with the ple CLI.
worked example · 5 min
How to version prompts in git (and where git falls short)
A file-per-prompt layout, commit messages that say why, word-level diffs, tags and a rollback that keeps history, plus the cases git does not cover.
worked example · 6 min
How to diff two prompts: git, diff and the ple CLI compared
Four ways to see which words moved between two prompts, with the real output of each.
worked example · 4 min
Prompt management for Claude Code with MCP
Connect Claude Code to your saved prompts with one command, then use slash commands, @-resources and add-only writes.
worked example · 5 min
A prompt changelog template you can copy
Version, change, reason, model and result in a copy-paste format, with a filled-in example and where to keep it.
worked example · 3 min
What Anthropic, Google, and OpenAI all agree on about prompts
We read all three labs' official prompting docs. Five rules appear in every one — and the disagreements (XML vs Markdown, CoT, prefill) are just as useful. With sources.
worked example · 7 min
Stop writing "think step by step"
Reasoning models internalized chain-of-thought. OpenAI and Google now say prompting it is unnecessary and can hurt — here's the per-model-class cheat sheet.
worked example · 5 min
Context rot: why your agent gets dumber as the session grows
An 18-model study confirmed what practitioners named context rot. The attention budget, and four habits that keep agent sessions sharp.
worked example · 6 min
Shrink your CLAUDE.md: the 300-token rule
Bloated instruction files get ignored — Anthropic says so itself. The one-line decision test, and what belongs in rules vs. a prompt library.
worked example · 6 min
Test your prompts with your own agent
LLM-as-judge without the eval platform: generate variants, run each through your real agent, keep the winner as a new version. Sized for one developer.
worked example · 6 min
The security-review prompt: why "find all vulns" fails
The broad scan produces confident noise. The pattern that finds real bugs: a one-sentence threat model, then one trust boundary at a time.
worked example · 5 min
Spec-driven development with plan files
The maturity shift in agentic coding: spec → reviewed plan → implementation against test gates. The plan-file anatomy that survives contact.
worked example · 6 min
Skills vs prompts vs a prompt library: what goes where
Three mechanisms, three questions: procedures, standing rules, and task prompts. A sorting rule for which layer owns what.
worked example · 5 min
Your MCP servers are silently eating your context window
Tool definitions load before you type a word. How to measure the overhead, and three cuts that keep the tools without the tax.
worked example · 5 min
A senior-engineer debugging prompt: minimal blast radius
AI debuggers love the big rewrite. The fix: separate diagnosis from repair, and make the model state what its fix does NOT change.
worked example · 5 min
/clear or /compact? A token decision tree
Topic change vs phase change vs the third option nobody mentions: restarting with a better prompt. When each one wins.
worked example · 4 min
A code-review prompt that improves itself
Start with a rough reviewer prompt, run it through Loop against Claude, and let the version history record which phrasing actually caught more bugs.
worked example · 6 min
One prompt, from your terminal to your agent
A single {{variables}} template, filled three ways: copied on the web, piped from the CLI, and pulled by Claude Code over MCP, always the same version.
worked example · 5 min
Prompt management tools compared (2026)
Langfuse, PromptLayer, Promptfoo, PingPrompt, claude-prompts and PLE answer three different questions. Current pricing, which fits a solo developer, and when to pick someone else.
worked example · 8 min
Best prompt manager for Claude Code (2026)
Copy-paste, CLI-reachable or agent-reachable: the one axis that decides how much copying you do. PingPrompt, PromptHub, Langfuse, dotfiles and PLE on it.
worked example · 6 min
PromptLikeEngineer vs PromptHub (2026)
Web and API vs CLI, web and MCP. Where PromptHub is the cheaper, better fit, where a flat Team price wins, and when the price gap buys you something.
worked example · 5 min
PromptLikeEngineer vs dotfiles and Gists for prompts
A folder of Markdown files is free and yours forever. What it costs as the collection grows, and when to keep it.
worked example · 5 min
Prompt versioning from the CLI: a practical guide
Save locally with no account, sync when ready, pipe prompts into agents, and test changes against your own agent with ple.
worked example · 6 min
Workbench is now Playground: where should your prompts live?
What Anthropic's release notes and news coverage say about the legacy Workbench sunset, and why a testing console isn't a prompt store.
worked example · 4 min
OpenAI prompt objects shut down on November 30, 2026: a migration checklist
What OpenAI says about retiring reusable prompt objects, a five-step checklist, and where a prompt library fits (and where it doesn't).
worked example · 4 min
Planned guides
- 01Grade-then-refactor: a refactoring prompt that won't rewrite your app
- 02Sharing a prompt library with a team without the chaos
- 03What a version-pinned permalink is good for
Want one of these first? Tell us at zeynepaslierhan@gmail.com.