agentmods.dev

pull-workflow

pull-workflow is a skill for Claude Code from Brainrot-Creations/claude-plugins. It costs 27 tokens per session (289 once invoked), scanned A, original, MIT.

A workflow retriever that gets a complete, multi-step procedure from Hive, a shared store of browser instructions, and runs it in order.

In plain words
What is it for?
Use it when Hive finds a matching workflow for tasks such as navigating a site, filling forms, or completing a multi-step browser process.
Why use it?
It avoids rediscovering how to complete a website task and records whether the procedure still works.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the hive plugin — 6 skills shipped together

not rated 23repo 4mo ago A scan 27 tokens original MIT

Good fit Use it when Hive finds a matching workflow for tasks such as navigating a site, filling forms, or completing a multi-step browser process.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/brainrot-creations/claude-plugins/pull-workflow
View source ↗ Brainrot-Creations/claude-plugins brainrotcreations.com
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.

Any agent
npx skills add Brainrot-Creations/claude-plugins --skill pull-workflow
Clone the repo
git clone --depth 1 https://github.com/Brainrot-Creations/claude-plugins

Made for: Claude Code.

Or install hive, the plugin that ships this one along with the rest of its 6 skills.

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 pull-workflow

README.md
[![agentmods](https://agentmods.dev/badge/skills/brainrot-creations/claude-plugins/pull-workflow/github.svg)](https://agentmods.dev/skills/brainrot-creations/claude-plugins/pull-workflow)
Your own site
<a href="https://agentmods.dev/skills/brainrot-creations/claude-plugins/pull-workflow"><img src="https://agentmods.dev/badge/skills/brainrot-creations/claude-plugins/pull-workflow/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 pull-workflow

Your own site · 80×15
<a href="https://agentmods.dev/skills/brainrot-creations/claude-plugins/pull-workflow"><img src="https://agentmods.dev/badge/skills/brainrot-creations/claude-plugins/pull-workflow.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 27 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 289 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 $0.00027 $0.00289
Opus 5.5 $0.00011 $0.00116
Sonnet 5.5 $0.00005 $0.00058
Haiku 4.5 $0.00003 $0.00029

Measured 2mo ago against content hash ba3923286285, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

pull-workflow 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 2mo 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.

Origin

Copies of this mod

1 near-identical copy found in the catalogue:

plugins/hive/skills/pull-workflow/SKILL.md · 24 lines

What it actually says

When hive_search shows a workflow for your goal, pull and execute the full sequence:

  1. Call hive_pull_workflow(domain, workflow_key) with the workflow key from hive_search.
  2. Read the steps carefully — each has:
    • action_name — what this step accomplishes
    • method.type — "css", "xpath", "aria", or "visual"
    • method.value — the selector or description to use
    • notes — optional context hint from the contributor
  3. Execute each step in order using your browser tool:
    • css/xpath/aria → pass directly to your selector-based tool
    • visual → use as a description for screenshot-based targeting
  4. If a step fails, note which step and try alternatives from hive_pull(domain, action_name).
  5. After completing the full workflow (or failing), call hive_vote_workflow:
    • "up" if the full sequence worked end-to-end
    • "down" if the workflow is broken or outdated
    • Include the workflow ID shown in the hive_pull_workflow output

Your vote tells every future agent whether this procedure is reliable.

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. 2mo ago First seen · 24 lines · 27 tokens per session scan A ba3923286285

Subscribe to this mod's changes

pull-workflow is a skill published in the GitHub repository Brainrot-Creations/claude-plugins (23 stars, last pushed 4mo ago), licensed MIT. It adds 27 tokens to every session and 289 once invoked, about $0.0001 per session on Opus 5.5. 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.

Browser automationClaude Codeai-agentsanthropicclaude-code-pluginmcpmodel-context-protocol
Related

pull-workflow compared with skills from other repositories

pull-workflow next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
pull-workflowBrainrot-Creations/claude-pluginsSkill234mo agoMITA27Claude Code
proof-e2etonone-ai/tononeSkill7723d agoMITA63Claude Code
e2e-panther-playwrightdev-toolings/superpowers-symfonySkill2311mo agoMITA29Claude Code
browser-qaHigorAlves/orcSkill7yesterdayMITA42Claude Code
qa-targetsHigorAlves/orcSkill7yesterdayMITA42Claude Code
agent-browserHigorAlves/orcSkill7yesterdayMITA32Claude Code
octen-web-searchOcten-Team/octen-mcpSkill239d agoMITA98Claude Code