optimize

A workflow skill for algorithm-focused research quests that manages possible improvements, compares candidate approaches, and records each justified advance. An optimization quest seeks a better result than an existing baseline.

In plain words
What is it for?
Use it to choose between optimization directions, test promising candidates, combine approaches, investigate failures, or decide when to stop.
Why use it?
It keeps optimization work focused and prevents producing many weak or poorly tested ideas.

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/researai/deepscientist/optimize
Any agent
npx skills add ResearAI/DeepScientist --skill optimize
Clone the repo
git clone --depth 1 https://github.com/ResearAI/DeepScientist

Made for: Claude Code, Codex.

Per session 32 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,825 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 $0.00032 $0.02825
Opus 5 $0.00016 $0.01412
Sonnet 5 $0.00006 $0.00565
Haiku 4.5 $0.00003 $0.00282

Measured 3d ago against content hash 495cd3cee9a5, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

optimize 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 3d 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.

src/skills/optimize/SKILL.md · 255 lines

How it starts

The opening of the file, as written. The whole thing — 255 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Optimize

Use this skill for algorithm-first quests where the goal is the strongest justified optimization result rather than paper packaging. The goal is to move the frontier by one justified step at a time, not to generate a large pile of low-information candidates.

Match signals

Use optimize when:

  • the quest is algorithm-first
  • the baseline gate is already confirmed or waived
  • the task has at least one plausible optimization direction
  • multiple candidate directions exist and the system should rank them before promotion
  • a durable line exists and the next step is to manage explore, exploit, fusion, debug, or stop

Do not use optimize when:

  • the baseline gate is unresolved
  • the main need is a paper draft, rebuttal, review, or finalize task
  • the quest is still in broad literature scouting with no concrete optimization handle
  • the real blocker is still idea-family selection rather than bounded optimization search inside an accepted family

One-sentence summary

Recover the current frontier, choose one optimize submode, advance one justified move, then record the new frontier or explicit stop condition.

Control workflow

  1. Recover the current frontier and recent durable optimization state. Read the frontier, recent memory, and current quest state before creating or promoting anything.
  2. Choose exactly one primary optimize submode for this pass. Keep the pass legible: one dominant optimize move, not several unrelated route changes.
  3. Keep the candidate slate or active pool small and differentiated. If the direction is still fuzzy, shape and rank branchless candidate briefs; if a durable line already exists, manage a bounded implementation pool inside that line.
  4. Promote or execute only bounded candidates with explicit evidence criteria. Promote only the strongest briefs into durable lines, and record implementation-level attempts separately from durable line creation.
  5. Route from evidence to exactly one dominant next action. End in explore, exploit, fusion, debug, or stop, and record that route durably.

Read the full file on GitHub · 255 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. 3d ago First seen · 255 lines · 32 tokens per session scan A 495cd3cee9a5

Subscribe to this mod's changes

optimize is a skill published in the GitHub repository ResearAI/DeepScientist (3,310 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 32 tokens to every session and 2,825 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 2026-08-30.

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

brainstorming

You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.

obra/superpowers · 37 tokens

auto-perf-optimize

Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.

microsoft/vscode · 62 tokens

chat-perf

Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.

microsoft/vscode · 51 tokens

chat-pet-sprite-creation

Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.

microsoft/vscode · 53 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