Chalk Labs
Need help deploying optima?
Chalk Labs sets up agents like this inside real teams: connected to your tools, tested on your data, with a human in the loop where it matters.
Install
Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.
npx agentmarket install skill/julienlhk-optima-166fa6
Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.
Get the weekly diff
The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.
About
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
Permissions: not checked yet.
What's inside
- Skill name
optima- Description
- None
- License
- MIT
- Instructions
- 70 lines in SKILL.md · view on GitHub
Agent Skills spec issues
- invalid YAML frontmatter: Nested mappings are not allowed in compact mappings at line 2, column 14:
- name: missing
- description: missing
Files (1)
- SKILL.md
SKILL.md (first lines)
# Optima ## Overview Optima is the optimization layer for AI coding agents in this repository. Cut avoidable tokens without sacrificing correctness. ## When to use - User asks to save tokens, reduce cost, or stop verbose agent output - Long sessions approaching context limits - Setting up Cursor / Claude / Codex FinOps rules - Designing API prompts for prompt caching ## Install (for humans) ```bash npm i -D optima-ai npx optima init ``` ## Levels `/optima off|lite|on|ultra` (or ask to set diet level) - **off** — no diet - **lite** — compress chat only - **on** — default (answer-first + surgical context) - **ultra** — telegraphic chat; never telegraph code/docs/tests/IDs ## Process 1. Confirm diet level and zone (sacred wins for code/docs). 2. Prefer **search/index → span read** over dumping files or blind truncation (`npx optima retrieve --query …`). 3. Compress **tool logs** (tests/git/json noise) — not sacred source. 4. Respect ignore boundaries (`.cursorignore`, `.optimaignore`, …). 5. For API work: stable prefix, cache breakpoints, no timestamps in cached prefixes. 6. At ~60–75% context, compact or hand off to a fresh session. ## Buckets | Bucket | Rule | |--------|------| | A Replies | Answer-first | | B Docs/plans | Dense | | C Tests | Key + edge; never skip money/auth/data-loss | | D Code | YAGNI, idiomatic — not cryptic | | E Context | Search → span read (not blind trim); min turns | | F Tools | Batch, stop early | | G Sub-agents | Cheap bounded search; strong model verifies | ## Zones 0 Sacred · 1 Premium · 2 Hybrid · 3 Ops — see `OPTIMA_RUNTIME.md`. ## Rationalizations to reject | Excuse | Response | |--------|----------| | "I'll dump the whole repo to be safe" | Surgical retrieval is safer and cheaper | | "Ultra mode on the PRD" | Premium/sacred content stays precise | | "Skip auth tests to save tokens" | Forbidden — quality floor | ## Verification - [ ] Code/docs remain precise - [ ] No critical tests skipped - [ ] Context from ignores avoided unless required - [ ] Zone 3 did not pollute Zone 0
From julienlhk/optima, MIT.
More from julienlhk/optima
- 0.524score
optima
julienlhk
Token and agent FinOps — diet levels, zone routing, context hygiene, cache-aware API guidance.
SkillBFreshness: BClaude Code +9 - 0.524score
context-engineering
julienlhk
Pack agent context efficiently — progressive disclosure, trim thresholds, lost-in-the-middle ordering, session handoffs.
SkillBFreshness: BClaude Code +9 - 0.521score
optima-debug
julienlhk
Structured debugging — frame the bug, list 5–7 category-diverse hypotheses, distill to 1–2, validate with local logs/doctor before any code fix.
SkillBFreshness: BClaude Code +9 - 0.518score
finops-zones
julienlhk
Four-zone output routing for coding agents (sacred/premium/hybrid/ops).
SkillBFreshness: BClaude Code +9
Signals
- Stars
- 0
- Forks
- 0
- Open issues
- 0
- Last commit (this folder)
- Sep 21, 2026 (1 month ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- MIT
- Repository
- github.com/julienlhk/optima
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from julienlhk
- 0.524score
optima
julienlhk
Token and agent FinOps — diet levels, zone routing, context hygiene, cache-aware API guidance.
SkillBFreshness: BClaude Code +9 - 0.524score
context-engineering
julienlhk
Pack agent context efficiently — progressive disclosure, trim thresholds, lost-in-the-middle ordering, session handoffs.
SkillBFreshness: BClaude Code +9 - 0.521score
optima-debug
julienlhk
Structured debugging — frame the bug, list 5–7 category-diverse hypotheses, distill to 1–2, validate with local logs/doctor before any code fix.
SkillBFreshness: BClaude Code +9 - 0.518score
finops-zones
julienlhk
Four-zone output routing for coding agents (sacred/premium/hybrid/ops).
SkillBFreshness: BClaude Code +9
Done for you
Rather not set it up yourself?
Chalk Labs scopes, builds and runs agents for your team: the task audit, the eval harness, the integrations and the weekly ops report. Fixed scope, priced before we start.
See how we build AI agents →Read the case studies
Chalk Labs is a two-founder AI and growth studio. We build AI agents, CRMs and MVPs for Web3 and AI companies, and have shipped 50+ product and token launches.
- launches shipped
- 50+
- launches shipped
- media placements
- 500+
- media placements
- founders on every account
- 2
- founders on every account
Press we've placed: Forbes · CoinDesk · Decrypt · Cointelegraph · The Block
Rahil Jain, Co-founder, Chalk Labs. Ex-Goldman Sachs engineer. You talk to the person who builds it.
Get optima running in your business
Tell us what you want to automate. A founder replies within one working day with a plan, not a pitch deck.
Cite this page
optima skill. Agent Mart. https://agentmart.dev/skills/julienlhk-optima-166fa6 (last updated 2026-10-24)