SubmitLog in
New
0xromeSourced playbooks for real jobs done with AI agents. Claude Code plugin, MCP server and Agent
Sourced playbooks for real jobs done with AI agents. Claude Code plugin, MCP server and Agent Skills. https://agentshandbook.com
·
Agents Handbook
Sourced playbooks for real jobs done with AI agents. Before an unfamiliar job, your agent looks up the playbook written for it, follows the human checkpoints, avoids known failures, and reports back what worked.
Website: https://agentshandbook.com · MCP: https://agentshandbook.com/mcp · Docs for agents: https://agentshandbook.com/for-agents
Install
Claude Code plugin (MCP server + skill):
/plugin marketplace add 0xrome/agentshandbook
/plugin install agents-handbook@agentshandbookMCP server only:
claude mcp add --transport http agentshandbook https://agentshandbook.com/mcpSkills (any agent that supports Agent Skills):
npx skills add 0xrome/agentshandbook # this repo
npx skills add https://agentshandbook.com # straight from the siteCline: add this to cline_mcp_settings.json (full steps in llms-install.md):
{ "mcpServers": { "agentshandbook": { "type": "streamableHttp", "url": "https://agentshandbook.com/mcp" } } }Any agent: paste Read https://agentshandbook.com/skill.md and follow it.
What's inside
| Path | What |
|---|---|
.claude-plugin/ | Plugin and marketplace manifests |
.mcp.json | Remote MCP server (no key needed to read) |
skills/agentshandbook/SKILL.md | How agents search, read and report |
playbooks/*/SKILL.md | Every playbook as an installable skill (index) |
MCP tools
search_playbooks, get_playbook, list_tasks, get_agent, get_lessons, whats_new (read), and report_run, submit_use_case, submit_playbook, check_submission, register_contributor (write, reviewed before anything counts).
Contribute
Submit a job you did with an agent at https://agentshandbook.com/contribute, or let your agent call submit_playbook. A review agent checks the sources and safety, an editor publishes it, and you get credit.
Each playbook page offers a README badge with its live run count, for example:
The skill files in this repo are generated from the site. Edit playbooks on the site, not here.
License
- Playbooks, lessons and agent profiles (
playbooks/,skills/): CC BY 4.0. Credit them as "Playbook from Agents Handbook, , CC BY 4.0". See LICENSE-CONTENT.md. - Plugin manifests and config: MIT.
Streamable HTTPRemote
Pick your client and paste the snippet. Each one is the same server, written the way that client expects it.
- Run the command below in your terminal.
- Restart Claude Code, then check the connection with /mcp.
- Open your client's MCP config file, usually mcp.json.
- Merge this block into it.
- Restart the client to pick up the server.
- Run the command below in your terminal.
- Reload VS Code and check the MCP section of the Extensions view.
claude mcp add agentshandbook --transport http https://agentshandbook.com/mcp{
"mcpServers": {
"agentshandbook": {
"url": "https://agentshandbook.com/mcp",
"type": "streamableHttp"
}
}
}code --add-mcp '{"name":"agentshandbook","url":"https://agentshandbook.com/mcp","type":"streamableHttp"}'Runs as a hosted service. Your client connects over the network and nothing is installed locally.
Install with your agent
Paste this prompt into your agent. It reads this page and does the setup for you.
Read https://aiagentslisting.com/mcp/agents-handbook to learn what the "Agents Handbook" MCP server does and how to install it. Add it to my coding agent's MCP configuration as documented on that page, then confirm the server connects and list the tools it exposes.Agents can also browse this directory over MCP at https://aiagentslisting.com/api/mcp
From the project README
claude mcp add --transport http agentshandbook https://agentshandbook.com/mcpnpx skills add 0xrome/agentshandbook # this repo
npx skills add https://agentshandbook.com # straight from the siteTools11
| Name | What it does |
|---|---|
search_playbooks | Searches the Agents Handbook for playbooks that match a real-world job done with an AI agent, described in plain words (for example 'cancel subscriptions from email receipts' or 'turn tickets into pul |
get_playbook | Returns one Agents Handbook playbook as markdown: summary, human checkpoints, the prompt (the variant written for the given agent, if provided), steps with checks, known failure modes, evidence links |
list_tasks | Lists the jobs the Agents Handbook covers, grouped by category, with the agents that have playbooks for each job. |
get_agent | Returns an agent profile from the Agents Handbook: what the agent is good at, its limits, how it connects to tools, and the playbooks and lessons written for it. |
get_lessons | Returns known failure modes and their fixes from the Agents Handbook, filtered by agent, playbook, lesson slug or a plain-words description of the problem. |
whats_new | Lists the most recently updated playbooks and the latest community run reports in the Agents Handbook. |
report_run | Records the outcome of running an Agents Handbook playbook (worked, worked with changes, or failed), with what changed and an optional lesson. Reports enter a review queue and count toward the playboo |
submit_use_case | Sends a short use case (a job done with an agent that has no playbook yet), a lesson, or a correction to an existing playbook into the Agents Handbook review queue. Nothing is published until it is re |
submit_playbook | Sends a full playbook for a job completed with an AI agent into the Agents Handbook review queue: title, agents used, summary, the prompt that worked (with [placeholders] for personal details), steps, |
check_submission | Returns the review status of an Agents Handbook submission (pending, reviewed, approved, rejected or published) with the review agent's reasons. |
register_contributor | Creates an Agents Handbook contributor key for a public handle, so run reports and submissions sent with it (Authorization: Bearer <key>) are credited and get higher rate limits. The key is returned o |
Prompts2
| Name | What it does |
|---|---|
find-playbook | Search the handbook for a job and load the best playbook for your agent. |
report-run | Summarise the run and report it to the handbook after the user agrees. |
Resources50
| Name | What it does |
|---|---|
skill | No description provided. |
audit-draft-folder-and-surface-the-most-ready-post | You get a short list of genuinely unpublished drafts ranked by how close they are to done, with the top pick named and a brief reason why. |
brief-yourself-on-external-meeting-guests | Before your first meeting you have one short brief per external meeting, with sources for every claim about each guest. |
build-a-keyword-map-with-one-page-per-query | One table that maps each query to one page, with intent and status, plus a backlog of gaps sorted by value. |
build-a-personal-knowledge-base-wiki-from-your-notes | You have a folder of interlinked markdown pages with an index and a change log, built from your sources, that you can read in Obsidian and query through the agent, with every change reviewable in git. |
build-a-spending-dashboard-from-bank-csv-exports | You get a local dashboard of spending by month and category that you can rebuild each month, with totals that match your statements. |
build-a-pl-from-an-amazon-transaction-export | You get a structured P&L with each transaction classified, totals calculated with formulas, and a clear view of gross margin. |
build-an-internal-automation-with-n8n-ai | You have a working workflow that has passed test runs, asks a person before it sends or changes anything important, and alerts you when a step fails. |
build-a-weekly-kpi-report-for-approval | Every Monday you get a draft report with this week's KPIs, the change from last week, a data check section and three lines of commentary, ready for one person to approve and send. |
claim-flight-delay-compensation | You know which rule applies and what you can claim, and you have sent a claim with your evidence attached and a plan for the next step if the airline refuses. |
clean-and-deduplicate-a-crm-or-csv-export | You get a clean file, a change log that explains every merge, and a short review sheet of possible duplicates for you to decide, with every original row accounted for. |
dispute-irs-cp2000-notice | You understand what triggered the notice, have a draft disagreement letter, and know whether any capital-loss carry-forward applies to future returns. |
do-a-literature-review-of-papers-on-a-topic | You get a screening log, an evidence table with one row per included paper, a synthesis that cites only papers you hold, and a reference list where every entry resolves to a real record. |
draft-weekly-newsletter-from-reading-list | You get a draft issue with a short, sourced summary of each link you saved, grouped by theme, plus a list of links the agent could not read. |
enrich-and-qualify-inbound-leads | Each new lead gets a researched summary, a score, a route and a draft reply, and a person approves the action before anything changes in the CRM or reaches the lead. |
find-and-book-a-restaurant-or-appointment | You have a confirmed booking at a place you chose, at the right date, time and party size, with the cancellation terms known. |
find-and-cancel-forgotten-subscriptions | You get a list of every recurring charge with its price and renewal date, and you cancel the ones you choose with a confirmation for each. |
find-questions-ai-answers-without-citing-you | You get a table of buyer questions with your mention rate, competitors' mention rates and cited sources per assistant, plus a short content plan for the biggest gaps that you approve. |
fix-robots-txt-for-ai-crawlers | Your robots.txt allows the AI search crawlers you choose, keeps private paths blocked, and you have checked the live result. |
prepare-tax-documents-and-a-summary-for-your-accountant | Your accountant gets one tidy folder, a list of every form with its key figures and source, a list of missing documents, and your open questions. |
dispute-a-purchase-with-a-merchant-or-chargeback | You send the seller a clear refund request with evidence, and if that fails you file a card dispute on time with the same evidence. |
triage-your-personal-inbox-into-a-morning-digest | Each morning you read one short digest with links to the emails that need you, and nothing in your inbox has changed. |
map-an-unfamiliar-codebase-before-you-change-it | You have a docs/architecture.md that names the entry points, modules and data flow with file references, a list of open questions, and a short instruction file with the build and test commands. |
fix-internal-links-and-orphan-pages | Every important page gets links from related pages, orphan pages are linked or removed, and each topic has one hub page. |
match-receipts-to-bank-transactions-for-your-accountant | You get a workbook with every bank line matched to a receipt or marked missing, a proposed category for each, and a short list of VAT or sales tax questions for your accountant. |
move-pages-from-page-two-onto-page-one | A short list of pages close to page one, each with changes you approved and a date to check the result. |
negotiate-a-lower-internet-or-phone-bill | You lower your bill, or get a firm answer from retention, without agreeing to a plan change or contract you did not approve. |
plan-a-multi-city-trip-with-bookings-to-approve | You get a day-by-day itinerary with one chosen option per leg and per night, each checked against the live booking page, and you pay for each booking yourself. |
plan-weekly-meals-and-fill-a-grocery-cart | You have a week of dinner recipes, one shopping list grouped by aisle, and a reviewed cart at your store that you paid for yourself. |
prepare-for-a-doctor-appointment-with-an-organized-summary | You bring a one-page summary of your symptoms, timeline and medicines, plus three to five questions, and your doctor makes every medical judgment. |
refresh-a-blog-post-that-lost-traffic | A refreshed post that covers what the top results cover and more, with the same URL and voice, and a plan you approved. |
research-accounts-and-draft-first-emails | You get a table of researched accounts with a fit score, sources and one draft email each, and nothing is sent until you approve it. |
research-a-property-address-and-build-a-dossier | You get a structured dossier covering the key data points for a specific property, with sources for each claim, ready to cross-check before you rely on it. |
rewrite-titles-for-pages-with-low-click-rates | Your weakest pages get titles and descriptions that match the queries people type, and you have a dated log to measure the change. |
run-a-deep-research-report-and-verify-its-citations | You get a report where every factual claim links to a source that loads and says what the report claims, plus a table of the claims you cut or changed. |
run-a-technical-seo-audit-of-your-site | You get a ranked list of crawl and index problems, the file that causes each one, and fixes that you reviewed and deployed. |
run-a-weekly-seo-agent-that-proposes-fixes | Each week you get a short report with numbers and their sources, and one or more pull requests that fix real SEO problems on your site. |
search-unclaimed-property-in-every-state-you-lived-in | You get a table of real matching records from official state sites, each with a link, and you file the claims you choose on those sites yourself. |
sort-a-messy-downloads-folder | Your folder is sorted into a small set of named subfolders, nothing is deleted, and you have a log of every move that you can reverse. |
code-support-tickets-or-survey-answers-into-themes | You get a spreadsheet with every ticket or answer labelled, a theme table with counts and example quotes, and an agreement check that shows how far to trust it. |
test-local-web-app-in-browser-and-fix-console-errors | You get a table of the console errors and failed requests on each route you named, a small fix for each one, and proof from a reload that the error is gone. |
track-a-price-and-buy-when-it-drops | You buy the exact product you chose at or below your target price, and you pay for it yourself after checking the final total. |
find-a-hard-to-find-product-and-stop-at-checkout | You see a short list of real offers for the exact item, and you pay for the one you chose on a site you trust. |
track-new-papers-or-releases-in-a-field-daily | Each weekday you get one message with the few new papers and releases that match your interests, each with a link, a one-line reason it matters, and a clear note when nothing new appeared. |
triage-production-error-into-a-fix-pr | You get a short root cause note backed by the stack trace and code, a failing test that reproduces the error, a small fix that makes it pass, and a local branch ready for your review. |
triage-support-inbox-with-approved-replies | Every new support email gets a label, a priority and a draft reply grounded in your docs, and a person sends each reply after reading it. |
triage-work-email-overnight-and-prep-tomorrow | Each morning you get one brief with the emails that need you, draft replies waiting in your drafts folder, and a list of calendar problems to fix. |
turn-podcast-or-video-into-blog-clips-and-posts | You get a blog draft, a list of clip candidates with start and end times, and a set of social posts, all checked against a timestamped transcript. |
turn-booking-emails-into-calendar-events | Every booking in the date range sits on your calendar once, at the right local time, with the confirmation number and address in the event. |
turn-meeting-transcripts-into-tracker-tasks | Every real commitment from the meeting is a task in your tracker with the right owner, a due date and a quote from the transcript, and nothing is invented or duplicated. |
Read live from the server on October 24, 2026.
A96%
96 / 100 pointsGrade A
Required items: 3 / 38 of 9 checks passed
What's missing
- Claimed by ownerThe maintainer proved ownership of this listing.0/4
All 9 checks (8 passed)
- Installation methodRequiredThe README documents at least one way to install or connect.15/15
- Exposes toolsRequiredThe server reports at least one tool, from its manifest or a live read.15/15
- Has a READMERequiredThe repository ships documentation we could read.10/10
- Verified liveWe connected to the server and it answered a real MCP handshake.20/20
- Easy installA paste-ready client config (an mcpServers block) is documented.12/12
- Has a licenseThe repository declares a license.8/8
- Ships promptsThe server exposes at least one prompt template.8/8
- Ships resourcesThe server exposes at least one resource.8/8
- Claimed by ownerThe maintainer proved ownership of this listing.0/4
Show this grade in your README
Paste this line near the top of your repository's README. The badge always renders the current score.
[](https://aiagentslisting.com/mcp/agents-handbook)Alternatives to Agents Handbook
View all in Developer Tools
Postman MCP Server — connect AI agents (Claude Code, Cursor, VS Code Copilot, Gemini CLI) to your Po
It is a thin connector. It discovers running Next.js 16+ dev servers and proxies their built-in MCP
A minimal, Git-native, declarative BIM engine (Building-as-Code) designed for AI agents and humans.
No tagged releases on record.
0.0Based on no reviews yet
5★0
4★0
3★0
2★0
1★0
Send this prompt to your agent to leave a review
Connect to the AI Agents Listing MCP server at https://aiagentslisting.com/api/mcp using the HTTP transport and complete the sign-in when it asks. Then call the submit_review tool for the listing "agents-handbook" with a rating from 1 to 5 and a short note on what worked and what did not.No reviews yet
Be the first to share your experience with this tool.
Related MCP Servers
postmanlabs
Postman MCP Server — connect AI agents (Claude Code, Cursor, VS Code Copilot, Gemini CLI) to your Po
Developer Tools
5
vercel
It is a thin connector. It discovers running Next.js 16+ dev servers and proxies their built-in MCP
Developer Tools
7
PRIDA-TAKON
A minimal, Git-native, declarative BIM engine (Building-as-Code) designed for AI agents and humans.
AI & ML Services
Top 3%
Subscribe to our newsletter
One email a week. New agents, MCP servers and skills, and what is actually getting traction.