Skip to trial filters
~/agentstafferAgentStaffer

Find, trial, compare, and govern AI agents before hiring

Trials Trial safely Next best action: Run a sandbox trial
Trials

Trial work queue

A compact sandbox trial queue for choosing a safe first task, checking fit and trust, and opening the full review package before any local run. Use this before hiring community-sourced agents into production workflows.

33available profiles
Filter optionsRole, protocol, trust, setup, and sorting stay available here.
First queue itemAutoresearchReview trust and setup, then run a small code review trial.Review preflight
Setup coverage12 guided / 0 manualAcross 12 candidates on this page. A setup path is not safety approval; trust review and a sandbox trial are still required.Setup guide
Recent evidence0 runsNew sandbox evidence appears in the run ledger.Evidence queue
#1 trial priority · skillsdirectory / Coding & Development
Fit
50 / 100
Trust
Verified source
Setup
MCP ready
Before run
0 checks
Top risk

No community evaluationAgentStaffer users have not submitted a review yet.

Full readiness snapshotCandidate summary and risk context stay available here.

Autonomous iteration loop: modify, verify, keep/discard against any metric

Top risk

No community evaluation: AgentStaffer users have not submitted a review yet.

Trial task Run a small code review trial
Input
Give the agent one low-risk issue or one small pull request and ask for defects, tests, and a patch plan.
Expected output
A concise review with reproducible findings, changed-file scope, and test suggestions.
Permissions & setup
  • Sandbox workspace: Run the first trial in a throwaway directory or isolated environment.
  • MCP-capable client: Use Claude Desktop, Cursor, VS Code, or another client that can load MCP server configs.
Promotion gates
  • Clear Install path reviewed
  • Clear Trust evidence reviewed
Guardrails
  • Install asks for production credentials or broad write access.
  • Source or package cannot be verified from profile evidence.

Create evidence with POST /api/actions/run-trial. Keep the card short; open the full checklist in the trial JSON.

Review & run trial Open profile
Review links
Profile JSON Trial JSON Setup JSON Trust JSON
#2 trial priority · mcpservers / Coding & Development
Fit
75 / 100
Trust
High traction
Setup
MCP ready
Before run
0 checks
Top risk

No community evaluationAgentStaffer users have not submitted a review yet.

Full readiness snapshotCandidate summary and risk context stay available here.

Autonomous experiment loop: try ideas, keep what works, discard what doesn't, never stop.

Top risk

No community evaluation: AgentStaffer users have not submitted a review yet.

Trial task Run a small code review trial
Input
Give the agent one low-risk issue or one small pull request and ask for defects, tests, and a patch plan.
Expected output
A concise review with reproducible findings, changed-file scope, and test suggestions.
Permissions & setup
  • Sandbox workspace: Run the first trial in a throwaway directory or isolated environment.
  • MCP-capable client: Use Claude Desktop, Cursor, VS Code, or another client that can load MCP server configs.
Promotion gates
  • Clear Install path reviewed
  • Clear Trust evidence reviewed
Guardrails
  • Install asks for production credentials or broad write access.
  • Source or package cannot be verified from profile evidence.

Create evidence with POST /api/actions/run-trial. Keep the card short; open the full checklist in the trial JSON.

Review & run trial Open profile
Review links
Profile JSON Trial JSON Setup JSON Trust JSON
#3 trial priority · npm / Coding & Development
Fit
55 / 100
Trust
Needs review
Setup
MCP ready
Before run
1 check
Top risk

No community evaluationAgentStaffer users have not submitted a review yet.

Full readiness snapshotCandidate summary and risk context stay available here.

Sneakoscope Codex: fast proof-first Codex trust layer with image-based Voxel TriWiki.

Top risk

No community evaluation: AgentStaffer users have not submitted a review yet.

Trial task Run a small code review trial
Input
Give the agent one low-risk issue or one small pull request and ask for defects, tests, and a patch plan.
Expected output
A concise review with reproducible findings, changed-file scope, and test suggestions.
Permissions & setup
  • Sandbox workspace: Run the first trial in a throwaway directory or isolated environment.
  • Node.js and npm: Required to run sneakoscope.
Promotion gates
  • Clear Install path reviewed
  • Hold Trust evidence reviewed
Guardrails
  • Install asks for production credentials or broad write access.
  • Source or package cannot be verified from profile evidence.

Create evidence with POST /api/actions/run-trial. Keep the card short; open the full checklist in the trial JSON.

Review & run trial Open profile
Review links
Profile JSON Trial JSON Setup JSON Trust JSON
#4 trial priority · playbooks / Coding & Development
Fit
61 / 100
Trust
Needs review
Setup
MCP ready
Before run
1 check
Top risk

No community evaluationAgentStaffer users have not submitted a review yet.

Full readiness snapshotCandidate summary and risk context stay available here.

This skill automates end-to-end AI research projects by managing loops, literature search, experiments, and synthesis to guide direction and produce papers.

Top risk

No community evaluation: AgentStaffer users have not submitted a review yet.

Trial task Run a small code review trial
Input
Give the agent one low-risk issue or one small pull request and ask for defects, tests, and a patch plan.
Expected output
A concise review with reproducible findings, changed-file scope, and test suggestions.
Permissions & setup
  • Sandbox workspace: Run the first trial in a throwaway directory or isolated environment.
  • MCP-capable client: Use Claude Desktop, Cursor, VS Code, or another client that can load MCP server configs.
Promotion gates
  • Clear Install path reviewed
  • Hold Trust evidence reviewed
Guardrails
  • Install asks for production credentials or broad write access.
  • Source or package cannot be verified from profile evidence.

Create evidence with POST /api/actions/run-trial. Keep the card short; open the full checklist in the trial JSON.

Review & run trial Open profile
Review links
Profile JSON Trial JSON Setup JSON Trust JSON
#5 trial priority · deepnlpagents / Coding & Development
Fit
55 / 100
Trust
Needs review
Setup
MCP ready
Before run
1 check
Top risk

No community evaluationAgentStaffer users have not submitted a review yet.

Full readiness snapshotCandidate summary and risk context stay available here.

AIDE: the state-of-the-art machine learning engineer agent, generating machine learning solution code from natural language descriptions.

Top risk

No community evaluation: AgentStaffer users have not submitted a review yet.

Trial task Run a small code review trial
Input
Give the agent one low-risk issue or one small pull request and ask for defects, tests, and a patch plan.
Expected output
A concise review with reproducible findings, changed-file scope, and test suggestions.
Permissions & setup
  • Sandbox workspace: Run the first trial in a throwaway directory or isolated environment.
  • MCP-capable client: Use Claude Desktop, Cursor, VS Code, or another client that can load MCP server configs.
Promotion gates
  • Clear Install path reviewed
  • Hold Trust evidence reviewed
Guardrails
  • Install asks for production credentials or broad write access.
  • Source or package cannot be verified from profile evidence.

Create evidence with POST /api/actions/run-trial. Keep the card short; open the full checklist in the trial JSON.

Review & run trial Open profile
Review links
Profile JSON Trial JSON Setup JSON Trust JSON
#6 trial priority · skillsdirectory / Coding & Development
Fit
55 / 100
Trust
Verified source
Setup
MCP ready
Before run
0 checks
Top risk

No community evaluationAgentStaffer users have not submitted a review yet.

Full readiness snapshotCandidate summary and risk context stay available here.

Universal autonomous experimentation loop inspired by Karpathy's autoresearch. Give it any project with a measurable metric and tunable variables, and it runs experiments autonomously: modify, measure, keep or discard, repeat. Works for landing pages, ad campaigns, prompt engineering, RAG pipelines, checkout flows, SEO, API performance, recommendation engin...

Top risk

No community evaluation: AgentStaffer users have not submitted a review yet.

Trial task Run a small code review trial
Input
Give the agent one low-risk issue or one small pull request and ask for defects, tests, and a patch plan.
Expected output
A concise review with reproducible findings, changed-file scope, and test suggestions.
Permissions & setup
  • Sandbox workspace: Run the first trial in a throwaway directory or isolated environment.
  • MCP-capable client: Use Claude Desktop, Cursor, VS Code, or another client that can load MCP server configs.
Promotion gates
  • Clear Install path reviewed
  • Clear Trust evidence reviewed
Guardrails
  • Install asks for production credentials or broad write access.
  • Source or package cannot be verified from profile evidence.

Create evidence with POST /api/actions/run-trial. Keep the card short; open the full checklist in the trial JSON.

Review & run trial Open profile
Review links
Profile JSON Trial JSON Setup JSON Trust JSON
Show 6 more trial candidatesAdditional candidates stay folded for scanning; trials.json and card resource links keep the full review path.
#7 trial priority · claudemarketplaces / Coding & Development
Fit
59 / 100
Trust
Needs review
Setup
CLI likely
Before run
1 check
Top risk

No community evaluationAgentStaffer users have not submitted a review yet.

Full readiness snapshotCandidate summary and risk context stay available here.

If you're running measured optimization loops with Claude and need the whole workflow in one place, this is the consolidated skill. It handles setup through finalization: spinning up autoresearch.md and .jsonl session files, running benchmarks, logging keep/discard decisions with metric evidence, checking drift, and previewing results. The state machine is...

Top risk

No community evaluation: AgentStaffer users have not submitted a review yet.

Trial task Run a small code review trial
Input
Give the agent one low-risk issue or one small pull request and ask for defects, tests, and a patch plan.
Expected output
A concise review with reproducible findings, changed-file scope, and test suggestions.
Permissions & setup
  • Sandbox workspace: Run the first trial in a throwaway directory or isolated environment.
  • Local terminal: A CLI path is visible, but the exact command must be verified from source.
Promotion gates
  • Clear Install path reviewed
  • Hold Trust evidence reviewed
Guardrails
  • Install asks for production credentials or broad write access.
  • Source or package cannot be verified from profile evidence.

Create evidence with POST /api/actions/run-trial. Keep the card short; open the full checklist in the trial JSON.

Review & run trial Open profile
Review links
Profile JSON Trial JSON Setup JSON Trust JSON
#8 trial priority · remoteopenclaw / Coding & Development
Fit
50 / 100
Trust
Needs review
Setup
Source guide
Before run
1 check
Top risk

No community evaluationAgentStaffer users have not submitted a review yet.

Full readiness snapshotCandidate summary and risk context stay available here.

Start an autonomous experiment loop with user-selected interval (10min, 1h, daily, weekly, monthly). Uses CronCreate for scheduling.

Top risk

No community evaluation: AgentStaffer users have not submitted a review yet.

Trial task Run a small code review trial
Input
Give the agent one low-risk issue or one small pull request and ask for defects, tests, and a patch plan.
Expected output
A concise review with reproducible findings, changed-file scope, and test suggestions.
Permissions & setup
  • Sandbox workspace: Run the first trial in a throwaway directory or isolated environment.
  • License review: License metadata is missing from the current public profile.
Promotion gates
  • Clear Install path reviewed
  • Hold Trust evidence reviewed
Guardrails
  • Install asks for production credentials or broad write access.
  • Source or package cannot be verified from profile evidence.

Create evidence with POST /api/actions/run-trial. Keep the card short; open the full checklist in the trial JSON.

Review & run trial Open profile
Review links
Profile JSON Trial JSON Setup JSON Trust JSON
#9 trial priority · remoteopenclaw / Coding & Development
Fit
50 / 100
Trust
Needs review
Setup
Source guide
Before run
1 check
Top risk

No community evaluationAgentStaffer users have not submitted a review yet.

Full readiness snapshotCandidate summary and risk context stay available here.

Resume a paused experiment. Checkout the experiment branch, read results history, continue iterating. Use when the user runs /ar:resume or asks to pick up a previously started autoresearch experiment.

Top risk

No community evaluation: AgentStaffer users have not submitted a review yet.

Trial task Run a small code review trial
Input
Give the agent one low-risk issue or one small pull request and ask for defects, tests, and a patch plan.
Expected output
A concise review with reproducible findings, changed-file scope, and test suggestions.
Permissions & setup
  • Sandbox workspace: Run the first trial in a throwaway directory or isolated environment.
  • License review: License metadata is missing from the current public profile.
Promotion gates
  • Clear Install path reviewed
  • Hold Trust evidence reviewed
Guardrails
  • Install asks for production credentials or broad write access.
  • Source or package cannot be verified from profile evidence.

Create evidence with POST /api/actions/run-trial. Keep the card short; open the full checklist in the trial JSON.

Review & run trial Open profile
Review links
Profile JSON Trial JSON Setup JSON Trust JSON
#10 trial priority · remoteopenclaw / Coding & Development
Fit
50 / 100
Trust
Needs review
Setup
Source guide
Before run
1 check
Top risk

No community evaluationAgentStaffer users have not submitted a review yet.

Full readiness snapshotCandidate summary and risk context stay available here.

Set up a new autoresearch experiment interactively. Collects domain, target file, eval command, metric, direction, and evaluator.

Top risk

No community evaluation: AgentStaffer users have not submitted a review yet.

Trial task Run a small code review trial
Input
Give the agent one low-risk issue or one small pull request and ask for defects, tests, and a patch plan.
Expected output
A concise review with reproducible findings, changed-file scope, and test suggestions.
Permissions & setup
  • Sandbox workspace: Run the first trial in a throwaway directory or isolated environment.
  • License review: License metadata is missing from the current public profile.
Promotion gates
  • Clear Install path reviewed
  • Hold Trust evidence reviewed
Guardrails
  • Install asks for production credentials or broad write access.
  • Source or package cannot be verified from profile evidence.

Create evidence with POST /api/actions/run-trial. Keep the card short; open the full checklist in the trial JSON.

Review & run trial Open profile
Review links
Profile JSON Trial JSON Setup JSON Trust JSON
#11 trial priority · awesomeclaudetoolkit / Coding & Development
Fit
43 / 100
Trust
Needs review
Setup
Source guide
Before run
1 check
Top risk

No community evaluationAgentStaffer users have not submitted a review yet.

Full readiness snapshotCandidate summary and risk context stay available here.

Automated ML experiment optimization using tree search — designs experiments, generates code, evaluates results, and iterates

Top risk

No community evaluation: AgentStaffer users have not submitted a review yet.

Trial task Run a small code review trial
Input
Give the agent one low-risk issue or one small pull request and ask for defects, tests, and a patch plan.
Expected output
A concise review with reproducible findings, changed-file scope, and test suggestions.
Permissions & setup
  • Sandbox workspace: Run the first trial in a throwaway directory or isolated environment.
  • License review: License metadata is missing from the current public profile.
Promotion gates
  • Clear Install path reviewed
  • Hold Trust evidence reviewed
Guardrails
  • Install asks for production credentials or broad write access.
  • Source or package cannot be verified from profile evidence.

Create evidence with POST /api/actions/run-trial. Keep the card short; open the full checklist in the trial JSON.

Review & run trial Open profile
Review links
Profile JSON Trial JSON Setup JSON Trust JSON
#12 trial priority · aiagentstore / Coding & Development
Fit
43 / 100
Trust
Needs review
Setup
Source guide
Before run
1 check
Top risk

No community evaluationAgentStaffer users have not submitted a review yet.

Full readiness snapshotCandidate summary and risk context stay available here.

An open-source project that lets AI agents autonomously run LLM training experiments and keep the best model changes.

Top risk

No community evaluation: AgentStaffer users have not submitted a review yet.

Trial task Run a small code review trial
Input
Give the agent one low-risk issue or one small pull request and ask for defects, tests, and a patch plan.
Expected output
A concise review with reproducible findings, changed-file scope, and test suggestions.
Permissions & setup
  • Sandbox workspace: Run the first trial in a throwaway directory or isolated environment.
  • License review: License metadata is missing from the current public profile.
Promotion gates
  • Clear Install path reviewed
  • Hold Trust evidence reviewed
Guardrails
  • Install asks for production credentials or broad write access.
  • Source or package cannot be verified from profile evidence.

Create evidence with POST /api/actions/run-trial. Keep the card short; open the full checklist in the trial JSON.

Review & run trial Open profile
Review links
Profile JSON Trial JSON Setup JSON Trust JSON

Recent Trial Runs

RunResultScoreRolePromotionDetails
No public trial runs have been created yet. Pick a candidate above, open its profile, then use Run Trial or POST /api/actions/run-trial with the candidate listingId. New evidence appears here and in the trial guide.
Review support

Review links

Trial candidates and recent runs stay first; complete review records and finalist profile resources stay linked here.

Open Trial queue JSON
Supporting review linksLinks, review order, and page-specific notes remain available here.
Trial queue JSONEvidence requests JSONPromotion queue JSONGEO exposure JSONAgent visibility JSONResource catalog JSONSite context TXTSitemap XMLProfile package JSON
Trial review paths
Trial review path
  1. 01Site contextShared review rules
  2. 02Trial queueOpen the focused review record
  3. 03Profile pageOpen the candidate page
  4. 04Profile resourcesEvidence, setup, trust, trial, and history files

Use the links and review path below for trial queue context, evidence requests, and finalist profile resources before action.

Review route: OpenAI review tools can start with openai.json; otherwise use site context and agent inventory before opening the finalist's complete review materials before install, hire, or promotion.