New: 98,000+ skills indexed from GitHub repos with 100+ stars · every skill safety-checkedBrowse top skillsTop skills
Esc to closeBrowse all skills
Submit a skillBrowse skills
Submit a skillBrowse skills

Agent skill

Hyperflow

by jeremylongshore in jeremylongshore/tons-of-skills-marketplace

A skill your agent uses when applying Hyperflow's orchestration doctrine in Codex, Antigravity, Grok, or another single-agent surface.

MITAuto-check passedAgent Workflows

Install Hyperflow

skills CLI
$ npx skills add jeremylongshore/tons-of-skills-marketplace --skill hyperflow -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install jeremylongshore/tons-of-skills-marketplace hyperflow --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/jeremylongshore/tons-of-skills-marketplace.git skills-src && mkdir -p .claude/skills && cp -r skills-src/plugins/ai-agency/hyperflow/skills/hyperflow .claude/skills/hyperflow && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
hyperflow
GitHub stars
2.8k
Token cost
~2.3k tokens
SKILL.md length
1,061 words
Files
37
Skills in repo
3,342
Repo updated
First seen
Licence
MIT

At a glance

A skill your agent uses when applying Hyperflow's orchestration doctrine in Codex, Antigravity, Grok, or another single-agent surface.

  • Works in 6 steps: Execute task-shaped requests without… → Clarify only after reading the relevant… → Keep long-form plans, specs, task… → …
  • Applying Hyperflows orchestration doctrine in Codex
  • SKILL.md covers Runtime Adaptation, Portable Function Router…, Subagents And Auto-Chain and Interaction Fallback, plus 3 more sections
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Hyperflow is an agent skill from jeremylongshore/tons-of-skills-marketplace. Use when applying Hyperflow's orchestration doctrine in Codex, Antigravity, Grok, or another single-agent surface. Auto-invoke for non-trivial engineering work: build, implement, add, refactor, debug, fix, review, audit, plan, scope, design, brainstorm, ship, or deploy. Trigger with /hyperflow:hyperflow, "use hyperflow", "apply the doctrine", or automatically on any task-shaped message.

Its SKILL.md is about 2.3k tokens, which your agent loads only when the skill is triggered. The skill folder holds 36 other files (for example `DOCTRINE.md`, `adaptive-brainstorming.md` and `artefact-format.md`). Compatibility notes: Portable doctrine — Claude Code, Codex App/CLI, OpenCode, Antigravity, Cursor, Grok

It sits in Agent Workflows, covering Brainstorming. The repository describes itself as: Model-agnostic agent-skills platform with a harness-free canonical layer, verified adapters, and the ccpi package manager. Explore at tonsofskills.com. The licence is MIT.

When your agent uses it

  • Applying Hyperflows orchestration doctrine in Codex
  • Another single-agent surface
  • With /hyperflow:hyperflow
  • Apply the doctrine

Example prompts

  • “use hyperflow”
  • “apply the doctrine”
  • “/hyperflow”

Requirements

  • Compatibility (from SKILL.md): Portable doctrine — Claude Code, Codex App/CLI, OpenCode, Antigravity, Cursor, Grok
  • Pre-approved tools (allowed-tools): Read, Write, Edit, Glob, Grep, Agent, Skill, AskUserQuestion, WebSearch, WebFetch, Bash(git:*), Bash(gh:*), Bash(npm:*), Bash(pnpm:*), Bash(npx:*), Bash(python3:*)

Workflow steps

6 steps, taken from the first numbered list in SKILL.md.

  1. Execute task-shaped requests without confirmation.
  2. Clarify only after reading the relevant code and only for genuine ambiguity.
  3. Keep long-form plans, specs, task decompositions, and audits under .hyperflow/.
  4. Use conventional commits, one distinct user task per commit.
  5. Never reference the model as the actor in commits, docs, comments, task files, or memory.
  6. Respect the security blocklist in security.md.

What it can do on your machine

Read from SKILL.md and the folder at commit 23ea8d4. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves these tools, so the agent can use them without asking each time:

    • Read
    • Write
    • Edit
    • Glob
    • Grep
    • Agent
    • Skill
    • AskUserQuestion
    • WebSearch
    • WebFetch

    …and 6 more on the same allowed-tools line.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md.

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

  • Compatibility

    Portable doctrine — Claude Code, Codex App/CLI, OpenCode, Antigravity, Cursor, Grok

    From compatibility in the SKILL.md frontmatter.

Context cost

Hyperflow loads about 2.3k tokens when it runs. Until then it costs about 100 tokens; SKILL.md has 1,061 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~100
When it runs · the whole SKILL.md, loaded when a task matches
~2.3k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from jeremylongshore/tons-of-skills-marketplace at commit 23ea8d4, republished under its MIT licence (© jeremylongshore). 1,061 words, ~2,332 tokens.

Download SKILL.mdSave it as .claude/skills/hyperflow/SKILL.md (or your agent's skills folder). This skill also uses 36 other files; get the full folder from GitHub.
name
hyperflow
description
Use when applying Hyperflow's orchestration doctrine in Codex, Antigravity, Grok, or another single-agent surface. Auto-invoke for non-trivial engineering work: build, implement, add, refactor, debug, fix, review, audit, plan, scope, design, brainstorm, ship, or deploy. Trigger with /hyperflow:hyperflow, "use hyperflow", "apply the doctrine", or automatically on any task-shaped message.
allowed-tools
Read, Write, Edit, Glob, Grep, Agent, Skill, AskUserQuestion, WebSearch, WebFetch, Bash(git:*), Bash(gh:*), Bash(npm:*), Bash(pnpm:*), Bash(npx:*), Bash(python3:*)
compatibility
Portable doctrine — Claude Code, Codex App/CLI, OpenCode, Antigravity, Cursor, Grok
argument-hint
[task]
version
1.0.0
license
MIT
tags
orchestration, doctrine, autonomy, multi-agent, portable

Hyperflow Doctrine (single-agent port)

Apply Hyperflow's behavioral floor in surfaces that load skills but do not provide the full Claude Code multi-agent runtime.

Runtime Adaptation

Codex, OpenCode, Antigravity, and Grok often run one foreground agent (or a host-specific subagent API). Where the full doctrine says to dispatch parallel workers under reviewers:

  • Prefer the host's subagent API when it exists (Codex spawn, OpenCode Task, Grok spawn_subagent).
  • Otherwise do the work yourself, one coherent batch at a time.
  • Self-review each batch before moving on.
  • Run a final integration self-review over the cumulative diff.
  • Preserve the same autonomy, clarification, commit cadence, file-first artefact, no-attribution, and security rules.

Portable Function Router (Codex / OpenCode / Grok)

These hosts load Hyperflow as skills, not as native Claude-style slash commands. Treat these user messages as function aliases and execute the matching skill workflow inline in the current thread:

User saysRun
/hyperflow:plan, hyperflow plan, design with hyperflow, decompose with hyperflowplan
/hyperflow:dispatch, hyperflow dispatch, run the hyperflow plandispatch
/hyperflow:workflow, hyperflow workflow, run a workflowworkflow
/hyperflow:trace, hyperflow trace, debug with hyperflowtrace
/hyperflow:audit, hyperflow audit, review with hyperflowaudit
/hyperflow:deploy, hyperflow deploy, ship with hyperflowdeploy
/hyperflow:cache, hyperflow cachecache
/hyperflow:status, hyperflow statusstatus
/hyperflow:sticky, hyperflow stickysticky
/hyperflow:bridge, hyperflow bridgebridge
/hyperflow:flush, hyperflow flushflush
/hyperflow:background, hyperflow backgroundbackground
/hyperflow:scaffold, hyperflow scaffoldscaffold

Do not answer that /hyperflow:* is an unknown command on these surfaces. Strip the alias, load the matching skills/<name>/SKILL.md, and follow its workflow. If that workflow says to use unavailable Claude Code tools (Agent, Skill, or AskUserQuestion), emulate them: do worker/reviewer steps inline with visible labels, continue chained skills inline, and use the interaction fallback below when a structured question UI is missing.

Subagents And Auto-Chain

Codex

When Codex exposes multi-agent tools, map Hyperflow agent dispatches to Codex subagents instead of falling back to inline work:

  • Hyperflow Agent worker/searcher/writer calls map to Codex worker or explorer subagents.
  • If the callable tool is named multi_agent_v1.spawn_agent, use agent_type: worker for implementer/writer execution and agent_type: explorer for search/codebase-research tasks, then collect results before review.
  • Spawn independent sibling workers together when the runtime supports parallel subagent calls.
  • Every agent runs on the current session model — do not switch models per role. Match reasoning effort to task complexity: low for trivial docs/config checks, medium for normal planning/review, high for debugging, architecture, security, or final integration review.
  • Never request or default to xhigh.

When Codex does not expose subagent tools in the current session, use the single-agent port above: execute worker/reviewer phases inline with clear labels and continue.

Grok

Grok CLI / Grok Build loads skills from ~/.grok/skills/, project .grok/skills/, and compatible Claude/Cursor skill dirs. Project rules come from AGENTS.md / CLAUDE.md and .grok/rules/. Runtime signal often includes GROK_AGENT=1.

When Grok exposes spawn_subagent, map Hyperflow dispatches as follows:

Hyperflow roleGrok subagent_type
implementer / writer / general workergeneral-purpose
searcher / codebase researchexplore
plan-only research (no file writes)plan
domain specialists (architect, security-reviewer, …)matching type if registered; else general-purpose with the specialist charter in the prompt
  • Spawn independent sibling workers together when the runtime supports parallel subagent calls.
  • If subagents are disabled (GROK_SUBAGENTS=0 or config), run worker/reviewer phases inline with clear labels.
  • Prefer the native AskUserQuestion tool for structural gates when available.
  • Every agent runs on the current session model — no per-role model selection.
  • Do not invent Claude Code Agent tool calls; use spawn_subagent or inline work.
Show full SKILL.md (507 more words)Show less
Auto-chain (all portable hosts)

For /hyperflow:workflow, use the portable workflow adapter (Codex / OpenCode / Grok branches in the workflow skill) instead of falling back to scope: research and planning, .hyperflow/tasks/ progress tracking when needed, parallel subagents when exposed, inline worker/reviewer phases otherwise, adversarial verification, quality gates, per-task conventional commits, and final synthesis. Do not describe this as native Claude Code dynamic workflow support.

These hosts may not expose Claude Code's Skill handoff tool. Treat every Hyperflow handoff as an inline auto-chain:

  • plan runs amplify → design → decompose inline, then stops at its build-location gate (always asked). It never auto-implements: on "this session" it continues into dispatch inline; on "another session" it writes a handoff package; on "stop" it keeps the plan.
  • dispatch offers audit and deploy structural gates, then runs the selected follow-up inline.
  • audit fix gates continue into plan with the generated audit-fix task (which then stops at its own build-location gate).

Do not stop with "Skill tool unavailable". Auto-chain is a behavior contract, not a host API requirement.

Interaction Fallback

When a host lacks a structured question UI (or AskUserQuestion is unavailable), do not skip the question or silently choose the recommended option. Render the same structural gate as a concise chat block and wait for the user's answer:

text
Hyperflow Question
<question>

1. <recommended option> (Recommended) — <short consequence>
2. <option> — <short consequence>

Use this fallback for every required clarification or structural gate: Amplify handoff, Spec chain mode, Spec brainstorming questions, Scope ambiguity questions, Dispatch audit/deploy gates, Audit fix gate, Deploy commit-inclusion and push gates, and any security/irreversibility escalation. It is still banned to ask invented confirmation questions such as "should I proceed?".

On Grok, prefer the native AskUserQuestion tool when present; use the chat-block fallback only if that tool is missing.

Reasoning Policy

  • Every agent runs on the current session model — there is no per-role model selection.
  • Resolve reasoning effort by task/profile: low for trivial docs/config checks, medium for normal planning/review, and high for debugging, architecture, security, and final integration.
  • Never default portable hosts to exotic max-effort modes (e.g. Codex xhigh).

Core Rules

  1. Execute task-shaped requests without confirmation.
  2. Clarify only after reading the relevant code and only for genuine ambiguity.
  3. Keep long-form plans, specs, task decompositions, and audits under .hyperflow/.
  4. Use conventional commits, one distinct user task per commit.
  5. Never reference the model as the actor in commits, docs, comments, task files, or memory.
  6. Respect the security blocklist in security.md.

Workflow Routing

IntentWorkflow
brainstorm, design, explore, "should we"Research first, ask material questions, then propose approaches
scope, decompose, "plan out"Map affected files, then write a task graph under .hyperflow/tasks/
big task, large migration, repo-wide audit, run a workflow, dynamic workflowUse the workflow skill: Claude Code native workflow, or Codex/OpenCode/Grok portable adapter, otherwise decompose through scope
build, implement, add, refactorDecompose, execute batches, self-review, commit per task
debug, fix it, "why is X failing"Root-cause before patching
audit, review, "check for issues"Review findings first, then offer/apply fixes
ship, push, release, deployRun gates, commit/release, ask before push

For full multi-agent doctrine, read DOCTRINE.md and the linked reference files in this directory.

© jeremylongshore, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 36 other files in plugins/ai-agency/hyperflow/skills/hyperflow of jeremylongshore/tons-of-skills-marketplace.

  • SKILL.md
  • DOCTRINE.md
  • VERSION
  • adaptive-brainstorming.md
  • artefact-format.md
  • background-agents.md
  • brainstorming-advanced.md
  • consultation.md
  • design-system.md
  • doctrine-extensions.md
  • escalation.md
  • failure-recovery.md
  • feature-phases.md
  • flow-profiles.md
  • git-workflow.md
  • latency-patterns.md
  • memory-system.md
  • mobile.md
  • model-config.md
  • motion.md
  • output-style.md
  • … and 16 more

Open the folder on GitHubat commit 23ea8d4

Compare with similar skills

Hyperflow next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Hyperflow compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Hyperflow this skilljeremylongshore/tons-of-skills-marketplace2.8k—~2.3kAutomated safety check: PassMIT
Brainstormingxpinjection/test-driven-spring-boot11254 repos~2.6kAutomated safety check: PassMIT
LLM Councilgcpdev/llm-council-skill4611 repos~1kAutomated safety check: NotesMIT
Typesafe AIOpenAgentsInc/openagents4559 repos~2.5kAutomated safety check: PassMIT
Yao Meta Skillyaojingang/yao-meta-skill2.7k—~768Automated safety check: PassMIT
Trellis StartROYIANS/foliq-print-template-designer1356 repos~646Automated safety check: PassMIT

Similar skills

  • Brainstorming

    xpinjection/test-driven-spring-boot

    You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior.

    112 GitHub starsUsed in 54 repos~2.6k tokens
    Agent WorkflowsAuto-check passed

  • LLM Council

    gcpdev/llm-council-skill

    Multi-LLM collaborative brainstorming and planning. An agent skill from gcpdev/llm-council-skill.

    461 GitHub starsUsed in 1 repo~1k tokens
    Agent WorkflowsAuto-check: notes

  • Typesafe AI

    OpenAgentsInc/openagents

    Build AI-powered software with TypeSafe: small units of AI intelligence you can use like programming primitives.

    455 GitHub starsUsed in 9 repos~2.5k tokens
    Agent WorkflowsAuto-check passed

  • Yao Meta Skill

    yaojingang/yao-meta-skill

    Create, improve, or evaluate an existing skill from workflows, prompts, SOPs, scripts.

    2.7k GitHub stars~768 tokensUpdated 1 mo ago
    Agent WorkflowsAuto-check passed

  • Trellis Start

    ROYIANS/foliq-print-template-designer

    Initializes an AI development session by reading workflow guides, developer identity, git status, active tasks, and project guidelines from .trellis/.

    135 GitHub starsUsed in 6 repos~646 tokens
    Agent WorkflowsAuto-check passed

  • Brainstorming Before Building

    jnMetaCode/superpowers-zh

    Turns a rough idea into an approved design before any code is written, sorting the request into spike, bounded or architectural and enforcing an approval gate.

    8.3k GitHub stars~1.8k tokensUpdated 4 days ago
    Agent WorkflowsAuto-check passed

More from jeremylongshore/tons-of-skills-marketplace

All 3,342 skills in this repo

  • Performing Security Code Review

    jeremylongshore/tons-of-skills-marketplace

    Execute this skill enables AI assistant to conduct a security-focused code review using the security-agent plugin.

    2.8k GitHub starsUsed in 2 repos~1.3k tokens
    Auto-check: notes

  • Analyzing Text With NLP

    jeremylongshore/tons-of-skills-marketplace

    Execute this skill enables AI assistant to perform natural language processing and text analysis using the nlp-text-analyzer plugin.

    2.8k GitHub starsUsed in 1 repo~819 tokens
    Auto-check passed

  • Building Neural Networks

    jeremylongshore/tons-of-skills-marketplace

    Execute this skill allows AI assistant to construct and configure neural network architectures using the neural-network-builder plugin.

    2.8k GitHub starsUsed in 1 repo~1k tokens
    Auto-check passed

  • Detecting Data Anomalies

    jeremylongshore/tons-of-skills-marketplace

    Process identify anomalies and outliers in datasets using machine learning algorithms.

    2.8k GitHub starsUsed in 1 repo~1.4k tokens
    Auto-check passed

  • Explaining Machine Learning Models

    jeremylongshore/tons-of-skills-marketplace

    Build this skill enables AI assistant to provide interpretability and explainability for machine learning models.

    2.8k GitHub starsUsed in 1 repo~1k tokens
    Auto-check passed

  • Optimizing Prompts

    jeremylongshore/tons-of-skills-marketplace

    Execute this skill optimizes prompts for large language models (llms) to reduce token usage, lower costs, and improve performance.

    2.8k GitHub starsUsed in 1 repo~1k tokens
    Auto-check passed

Categories

Questions about Hyperflow

What does Hyperflow do?

A skill your agent uses when applying Hyperflow's orchestration doctrine in Codex, Antigravity, Grok, or another single-agent surface. Hyperflow is an agent skill from jeremylongshore/tons-of-skills-marketplace. Use when applying Hyperflow's orchestration doctrine in Codex, Antigravity, Grok, or another single-agent surface.

When should I use Hyperflow?

Hyperflow fits situations like: applying Hyperflows orchestration doctrine in Codex; another single-agent surface; with /hyperflow:hyperflow; apply the doctrine.

How do I install Hyperflow in Claude Code?

Run `npx skills add jeremylongshore/tons-of-skills-marketplace --skill hyperflow -a claude-code`. Or copy the skill folder (plugins/ai-agency/hyperflow/skills/hyperflow in jeremylongshore/tons-of-skills-marketplace) into .claude/skills/hyperflow in your project. Claude Code loads it when a task matches its description.

How do I install Hyperflow in Codex?

Run `npx skills add jeremylongshore/tons-of-skills-marketplace --skill hyperflow -a codex`. Or copy the skill folder (plugins/ai-agency/hyperflow/skills/hyperflow in jeremylongshore/tons-of-skills-marketplace) into .agents/skills/hyperflow in your project. Codex loads it when a task matches its description.

Can I use Hyperflow in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add jeremylongshore/tons-of-skills-marketplace --skill hyperflow -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/hyperflow, .gemini/skills/hyperflow, .github/skills/hyperflow and .opencode/skills/hyperflow in your project.

What does Hyperflow need to run?

SKILL.md names no scripts, command-line tools or credentials: Hyperflow is instructions for the agent only. Its frontmatter pre-approves these tools: Read, Write, Edit, Glob, Grep, Agent, Skill, AskUserQuestion, WebSearch, WebFetch, Bash(git:*), Bash(gh:*), Bash(npm:*), Bash(pnpm:*), Bash(npx:*), Bash(python3:*). Compatibility (from SKILL.md): Portable doctrine — Claude Code, Codex App/CLI, OpenCode, Antigravity, Cursor, Grok.

Does Hyperflow access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Hyperflow safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Hyperflow use?

Hyperflow is published under the MIT licence (declared in SKILL.md). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Hyperflow use?

About 2.3k tokens (SKILL.md is roughly 9.3k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Hyperflow?

Skills that share tags, products or a category with Hyperflow: Brainstorming (xpinjection/test-driven-spring-boot, 112 stars), LLM Council (gcpdev/llm-council-skill, 461 stars), Typesafe AI (OpenAgentsInc/openagents, 455 stars) and Yao Meta Skill (yaojingang/yao-meta-skill, 2.7k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Hyperflow?

jeremylongshore (a GitHub user) maintains it in jeremylongshore/tons-of-skills-marketplace, which has 2,821 GitHub stars. The repository holds 3,342 skills in this directory. The repository was last updated on October 8, 2026.

Source: jeremylongshore/tons-of-skills-marketplace on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.