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.
npx agentmods add skills/brainrot-creations/claude-plugins/contribute-workflownpx skills add Brainrot-Creations/claude-plugins --skill contribute-workflowgit clone --depth 1 https://github.com/Brainrot-Creations/claude-pluginsWrote 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.
[](https://agentmods.dev/skills/brainrot-creations/claude-plugins/contribute-workflow)<a href="https://agentmods.dev/skills/brainrot-creations/claude-plugins/contribute-workflow"><img src="https://agentmods.dev/badge/skills/brainrot-creations/claude-plugins/contribute-workflow.svg" alt="Measured on agentmods" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00032 | $0.00368 |
| Opus 5 | $0.00016 | $0.00184 |
| Sonnet 5 | $0.00006 | $0.00074 |
| Haiku 4.5 | $0.00003 | $0.00037 |
Grade A, and why
contribute-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 6d 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.
Copies of this mod
1 near-identical copy found in the catalogue:
- contribute-workflow — 100% identical, 0 lines differ
What it actually says
After successfully completing a multi-step goal through your own discovery, contribute the full procedure:
-
Choose a
workflow_key— snake_case slug describing the procedure:- Good:
send_connection_with_note,post_linkedin_article,submit_github_issue - Bad:
do_the_thing,linkedin_stuff
- Good:
-
Write a clear
descriptionof what the workflow accomplishes:- Good: "Send a LinkedIn connection request with a personalized note"
- Bad: "Connect with someone"
-
Build the
stepsarray in execution order. For each step:action_name— snake_case name for this action (e.g.click_add_note_in_modal)method.type— "css", "xpath", "aria", or "visual"method.value— the exact selector or visual description that workedmethod.context— optional: where on the page this selector appliesnotes— optional: anything that would help another agent (e.g. "Wait for modal to open before this step")
-
Call
hive_contribute_workflow(domain, workflow_key, description, steps).
What makes a good workflow contribution
- Every step is reproducible — not dependent on specific account state or session data
- Step names are descriptive enough that another agent can understand the sequence
- Steps include context hints when a selector only works in a specific page state
- You've verified the full sequence works end-to-end before contributing
The collective builds on what you contribute. Good contributions compound.
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.
- 6d ago First seen · 33 lines · 32 tokens per session scan A e6ace4a5504f
contribute-workflow is a skill published in the GitHub repository Brainrot-Creations/claude-plugins (22 stars, last pushed 2mo ago), licensed MIT. It adds 32 tokens to every session and 368 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.
Other skills, from other repositories
award-travel-finder
Search award flight availability across 28 airlines and compare 23 loyalty program award charts via the Award Travel Finder MCP server. Find the best points and miles redemptions across British Airways, Qatar Airways, Cathay Pacific, Virgin Atlantic, Aeroplan, Iberia, Emirates, Qantas, Alaska, American, JetBlue, ANA…
award-travel
This skill should be used when the user asks about "award flights", "points", "miles", "avios", "asia miles", "loyalty programs", "flight availability", "award search", "redemptions", "business class availability", "first class availability", "hybrid flights", "cash and points", "split ticket", "positioning flights"…
opendart-excel
사용자가 특정 기업/사업연도의 연결·별도 재무제표를 엑셀로 요청하면, OpenDART MCP로 공시 원문을 받아 DART 원문 양식(재무제표 시트 + 클릭 가능한 주석 링크)의 검증된 Excel 파일을 생성한다.
score-studio
Use Score Studio to inspect versioned computer-vision data and models, start training or evaluation, review evidence, verify deployments, and run workflows. Trigger for Score Studio datasets, CV training, evaluation gates, model release evidence, deployments, or visual workflows.
claude-mail-bridge-init
Use when Claude Mail Bridge is installed (presence.json exists). Provides behavior guidelines for remote collaboration scenarios, including presence detection and MCP usage.
claude-mail-bridge-team_rules
Use when operations involve emailing teammates (mailteammates MCP tool). Defines strict privacy rules for team communication.