agentmods.dev

ultraexpertise

ultraexpertise is a command for Claude Code from xingchengxu/OpenExpertise. It costs 26 tokens per session (547 once invoked), scanned A, original, MIT.

A command that creates a draft standard operating procedure, or SOP—a written sequence of steps for completing a task—using OpenExpertise. It reports the draft location, chosen stages, unanswered questions, and validation result.

In plain words
What is it for?
Use it to draft, test, revise, and promote reusable OpenExpertise procedures for tasks such as bug handling or other multi-step workflows.
Why use it?
It turns a task description into a structured procedure that can be tried, revised, and later stored in a project. It also shows what information is still missing before the procedure can run fully.

Command for Claude Code

Written for Claude Code: $ARGUMENTS substitution.

not rated 4repo 3mo ago A scan 26 tokens original MIT

Good fit Use it to draft, test, revise, and promote reusable OpenExpertise procedures for tasks such as bug handling or other multi-step workflows.

Compare 6 commands from other repositories ↓
Install with agentmods
npx agentmods add commands/xingchengxu/openexpertise/ultraexpertise
View source ↗ xingchengxu/OpenExpertise xingchengxu.github.io
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.

Clone the repo
git clone --depth 1 https://github.com/xingchengxu/OpenExpertise

Made for: Claude Code.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for ultraexpertise

README.md
[![agentmods](https://agentmods.dev/badge/commands/xingchengxu/openexpertise/ultraexpertise/github.svg)](https://agentmods.dev/commands/xingchengxu/openexpertise/ultraexpertise)
Your own site
<a href="https://agentmods.dev/commands/xingchengxu/openexpertise/ultraexpertise"><img src="https://agentmods.dev/badge/commands/xingchengxu/openexpertise/ultraexpertise/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for ultraexpertise

Your own site · 80×15
<a href="https://agentmods.dev/commands/xingchengxu/openexpertise/ultraexpertise"><img src="https://agentmods.dev/badge/commands/xingchengxu/openexpertise/ultraexpertise.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 26 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 547 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00026 $0.00547
Opus 5 $0.00013 $0.00273
Sonnet 5 $0.00005 $0.00109
Haiku 4.5 $0.00003 $0.00055

Measured 12d ago against content hash 713d8fe4e920, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

ultraexpertise 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 12d 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.

packages/skill-experience-creator/commands/ultraexpertise.md · 34 lines

How it starts

The opening of the file, as written. The whole thing — 34 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are the user's authoring assistant for OpenExpertise. The user has invoked /ultraexpertise with the following task description:

$ARGUMENTS

Your job

  1. Verify oe is on PATH (which oe). If not, suggest building from workspace: pnpm -r build && node $(pwd)/packages/cli/dist/bin.js ultra "...".
  2. Decide the draft directory. If the user is inside an OpenExpertise repo (an experience.yaml exists nearby), use .openexpertise/drafts/. Otherwise use ./openexpertise-drafts/.
  3. Run oe ultra "<task>" --draft-root <chosen draft root>. Surface the structured result to the user:
    • The slug and draft path
    • The phases and node kinds the LLM chose
    • Any open questions
    • Whether validation passed
  4. After the draft lands, summarize what to do next:
    • oe run <draft path> to try it.
    • mv <draft path> examples/<slug> to promote it for permanent storage and version control.
    • If open_questions[] is non-empty, list each one as a thing the user needs to answer before the SOP is fully runnable.
    • If the user wants to refine the draft with natural-language feedback (e.g. "split the bugs node into security + logic"), run oe ultra-revise <draft path> "<their feedback>" — this re-reads the draft, applies one steered critique→revise pass, and writes the incremental edit back in place.
  5. If validation failed, read the generated experience.yaml and explain WHAT the schema rejected, in plain English. Offer to fix it.

Boundaries

  • Do not run oe ultra without ANTHROPIC_API_KEY or OPENAI_API_KEY set. Check env | grep -E "(ANTHROPIC|OPENAI)_API_KEY"; if neither is present, tell the user which to set and stop.
  • Do not modify the generated draft beyond pointing out problems; let the user decide.
  • Do not promote (mv) the draft on the user's behalf.
  • For oe ultra-revise, pass the EXISTING draft directory path as the first argument and the user's verbatim feedback as the second — never re-derive the path from the slug.

Reply concisely. The user wants the draft + a clear next action, not a wall of text.

Read the full file on GitHub · 34 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. 12d ago First seen · 34 lines · 26 tokens per session scan A 713d8fe4e920

Subscribe to this mod's changes

ultraexpertise is a command published in the GitHub repository xingchengxu/OpenExpertise (4 stars, last pushed 3mo ago), licensed MIT. It adds 26 tokens to every session and 547 once invoked, about $0.0001 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 2026-08-31.

Claude CodePlanningagenticagentsai-workflowclicodex
Related

Other commands, from other repositories

hatch3r-pr-resolve

Read open PR comments, evaluate each against current code via the rigor contract, implement accepted findings, reply inline. Multi-platform.

hatch3r/hatch3r · 25 tokens

hatch3r-workflow

Guided development lifecycle with 4 phases (Analyze, Plan, Implement, Review) and scale-adaptive Quick Mode for small tasks; --plan-file executes an approved plan document without re-deriving it.

hatch3r/hatch3r · 42 tokens

hatch3r-codebase-map

Reverse-engineer a brownfield codebase into current-state module boundaries, integration-point inventory, tech-debt register, and dependency graph via static analysis.

hatch3r/hatch3r · 29 tokens

hatch3r-release

Release-workflow orchestrator — preflight, SemVer bump, changelog sync, build + CycloneDX SBOM, adapter-output verification, quality gates, release-notes reconciliation, then stop before publish/merge for human approval.

hatch3r/hatch3r · 47 tokens

hatch3r-roadmap

Sequence delivery phases over time into a dependency-ordered milestone plan with business and technical lenses, emitting a todo.md rollout schedule rather than design docs.

hatch3r/hatch3r · 28 tokens

hatch3r-api-spec

Generate or validate an OpenAPI specification from the codebase. Scans route definitions, extracts schemas, and produces a complete API spec.

hatch3r/hatch3r · 27 tokens