optimizing-prompts

A prompt-editing guide that rewrites prompts and coding-agent definitions using established prompt-writing practices.

In plain words
What is it for?
It reviews a prompt from a file, agent definition, pasted text, or directory, then produces a revised version and explains the changes.
Why use it?
It helps make unclear instructions more direct, organized, and predictable for the model using them.

Skill for Claude CodeCodex

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/agentic-dev3o/devx-plugins/prompt-optimizer
Any agent
npx skills add agentic-dev3o/devx-plugins --skill prompt-optimizer
Clone the repo
git clone --depth 1 https://github.com/agentic-dev3o/devx-plugins

Made for: Claude Code, Codex.

Per session 99 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,346 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.

ModelPer sessionOnce invoked
Fable 5 $0.00099 $0.01346
Opus 5 $0.00049 $0.00673
Sonnet 5 $0.00020 $0.00269
Haiku 4.5 $0.00010 $0.00135

Measured 2d ago against content hash db62bf3bdebb, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

optimizing-prompts 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 2d 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.

plugins/agentic-engineering/skills/prompt-optimizer/SKILL.md · 139 lines

How it starts

The opening of the file, as written. The whole thing — 139 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Prompt Optimizer

Target: $ARGUMENTS (path to a prompt file, agent definition, or pasted prompt text)

Workflow

Progress checklist:

Prompt Optimization:
- [ ] Step 1: Capture the target prompt
- [ ] Step 2: Identify intent, model, and runtime
- [ ] Step 3: Diagnose against eight techniques
- [ ] Step 4: Rewrite the prompt
- [ ] Step 5: Produce before/after report with rationale

Step 1: Capture the Target Prompt

Determine whether $ARGUMENTS is:

  • A file path → read the file
  • An agent definition (markdown with frontmatter, JSON/YAML) → extract the system prompt and any few-shot examples
  • Inline prompt text → use as-is
  • A directory → list it and ask the user to pick one prompt to optimize

If the prompt is part of a larger agent (tools, examples, memory layout), capture the surrounding shape but keep the rewrite scoped to the prompt itself. Do not rewrite tool definitions in this skill — the audit skill flags those, and tool rewrites belong in their own pass.

Step 2: Identify Intent, Model, and Runtime

Before optimizing, answer:

  • What does the prompt do? Classification, extraction, generation, agent loop, chat?
  • Who is the end user? Internal engineer, customer, batch pipeline?
  • What model runs it? Claude Opus 4.7 / Sonnet 4.6 / Haiku 4.5 / GPT-x / etc. — affects defaults (verbosity, thinking, effort) and which features apply (caching, adaptive thinking, structured outputs).
  • Is this interactive or autonomous? Single-turn API, multi-turn chat, long-horizon agent? Verbosity and update-frequency guidance differs.

If any of these are ambiguous and would materially change the rewrite, ask one focused question. Do not ask if the answer is inferable from the prompt itself.

Step 3: Diagnose Against Eight Techniques

For each technique below, read the matching reference and decide whether the current prompt applies it well, partially, or not at all. Note the gap concretely (quote the offending text or note its absence).

Read the full file on GitHub · 139 lines

Files

What ships with it

8 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.

  1. 2d ago First seen · 139 lines · 99 tokens per session scan A db62bf3bdebb

Subscribe to this mod's changes

optimizing-prompts is a skill published in the GitHub repository agentic-dev3o/devx-plugins (11 stars, last pushed 14d ago), licensed MIT. It adds 99 tokens to every session and 1,346 once invoked, about $0.0005 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 2026-08-30.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

babysit-pr

Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…

openai/codex · 114 tokens

imagegen

Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…

openai/codex · 113 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens

next-cache-components-optimizer

Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…

vercel/next.js · 170 tokens