agent · Agent Skills Sharing Platform
Agentman
24 fields evidenced · 31 with no public information. Every value below links to the document it came from and the date we checked it.
Trust gap
How this is scoredRuntime governance
2/3
Are scope, spend, and authority enforced while the agent runs?
Scored from 2 evidenced field(s): runtime_governance, permission_scopes. Automated score; capped at 2 pending review.
Audit trail
2/3
Is there a tamper-evident record of what it actually did?
Scored from 2 evidenced field(s): audit_trail, explainability. Automated score; capped at 2 pending review.
Compliance
2/3
Are compliance obligations attached per engagement?
Scored from 2 evidenced field(s): compliance_certs, regulatory_alignment. Automated score; capped at 2 pending review.
Outcome settlement
1/3
Does payment depend on a verified result?
Scored from 1 evidenced field(s): outcome_based_pricing. Automated score; capped at 2 pending review.
How this gap gets closed →Insurance & indemnity
unscored
Can the deployment be insured, and is the customer indemnified?
Assurance
- Insurance available
- no public informationagentman.ai · checked Aug 1, 2026 · source did not state this
- Insurance carriers
- no public informationagentman.ai · checked Aug 1, 2026 · source did not state this
- Coverage limits
- no public informationagentman.ai · checked Aug 1, 2026 · source did not state this
- Indemnification
- no public informationagentman.ai · checked Aug 1, 2026 · source did not state this
- Liability cap
- Liability cap 1× fees — below firm floor (2×); escalate to partner
“Liability cap 1× fees — below firm floor (2×); escalate to partner”
agentman.ai · checked Aug 1, 2026 - Audit trail
- Full audit trail Who changed what, when, and which agent used which version on which task. Exportable.
“Full audit trail Who changed what, when, and which agent used which version on which task. Exportable.”
agentman.ai · checked Aug 1, 2026 - Tamper-evident log
- no public informationagentman.ai · checked Aug 1, 2026 · source did not state this
- Explainability
- Same request. One without your context, one with it. Legal Private equity Healthcare Sales Generic AI Contract Review Review contracts carefully for liability, payment terms, and termination clauses. Ensure all parties understand their obligations and consider consulting an attorney before signing. Generic. Textbook. Could be anyone's. AI + your skill Contract Review AI + contract-negotiation-playbook Indemnification Mutual clause confirmed — no unilateral exposure Auto-renewal 60-day window vs. your 90-day standard — redline Liability cap 1× fees — below firm floor (2×); escalate to partner Specific. Actionable. Actually yours.
“Same request. One without your context, one with it. Legal Private equity Healthcare Sales Generic AI Contract Review Review contracts carefully for liability, payment terms, and termination clauses. Ensure all parties understand their obligations and consider consulting an attorney before signing. Generic. Textbook. Could be anyone's. AI + your skill Contract Review AI + contract-negotiation-playbook Indemnification Mutual clause confirmed — no unilateral exposure Auto-renewal 60-day window vs. your 90-day standard — redline Liability cap 1× fees — below firm floor (2×); escalate to partner Specific. Actionable. Actually yours.”
agentman.ai · checked Aug 1, 2026 - Runtime governance
- Permissioned Control who can view, edit, and publish — scoped by workspace, team, or individual, down to a single skill.
“Permissioned Control who can view, edit, and publish — scoped by workspace, team, or individual, down to a single skill.”
agentman.ai · checked Aug 1, 2026 - Permission scopes
- Role-based permissions Four access levels — use, view, edit, admin — granted per skill or across the whole workspace.
“Role-based permissions Four access levels — use, view, edit, admin — granted per skill or across the whole workspace.”
agentman.ai · checked Aug 1, 2026 - Compliance certifications
- SOC 2 Ready ISO 27001 HIPAA
“SOC 2 Ready ISO 27001 HIPAA”
agentman.ai · checked Aug 1, 2026 - Regulatory alignment
- SOC 2 Ready ISO 27001 HIPAA
“SOC 2 Ready ISO 27001 HIPAA”
agentman.ai · checked Aug 1, 2026 - Outcome-based pricing
- $0.50 per eligibility check vs. $6.72 CAQH benchmark
“$0.50 per eligibility check vs. $6.72 CAQH benchmark”
agentman.ai · checked Aug 1, 2026 - Settlement mechanism
- no public informationagentman.ai · checked Aug 1, 2026 · source did not state this
- Dispute process
- no public informationagentman.ai · checked Aug 1, 2026 · source did not state this
- SLA terms
- no public informationagentman.ai · checked Aug 1, 2026 · source did not state this
- Evaluation coverage
- no public informationagentman.ai · checked Aug 1, 2026 · source did not state this
Agency
- Autonomy level
- no public informationagentman.ai · checked Aug 1, 2026 · source did not state this
- Human oversight
- Human in the loop Consequential decisions wait for a person. Always reviewable.
“Human in the loop Consequential decisions wait for a person. Always reviewable.”
agentman.ai · checked Aug 1, 2026 - Goal complexity
- AGENTS Single loops that execute Review one contract. Verify one claim.
“AGENTS Single loops that execute Review one contract. Verify one claim.”
agentman.ai · checked Aug 1, 2026 - Action space
- A skill captures how your best people actually do the work — their procedures, judgment, and standards — so every agent runs it the same way, every time.
“A skill captures how your best people actually do the work — their procedures, judgment, and standards — so every agent runs it the same way, every time.”
agentman.ai · checked Aug 1, 2026 - Operating environment
- Build once, use everywhere Your best skills, shared with the whole team — in Claude and ChatGPT .
“Build once, use everywhere Your best skills, shared with the whole team — in Claude and ChatGPT .”
agentman.ai · checked Aug 1, 2026 - Initiative
- no public informationagentman.ai · checked Aug 1, 2026 · source did not state this
Safety
- Safety evaluations
- no public informationagentman.ai · checked Aug 1, 2026 · source did not state this
- Red teaming
- no public informationagentman.ai · checked Aug 1, 2026 · source did not state this
- Safety policy
- no public informationagentman.ai · checked Aug 1, 2026 · source did not state this
- Usage restrictions
- no public informationagentman.ai · checked Aug 1, 2026 · source did not state this
- Model or system card
- no public informationagentman.ai · checked Aug 1, 2026 · source did not state this
- Incident reporting
- no public informationagentman.ai · checked Aug 1, 2026 · source did not state this
- Third-party evaluations
- no public informationagentman.ai · checked Aug 1, 2026 · source did not state this
- Data handling
- Full audit trail Who changed what, when, and which agent used which version on which task. Exportable.
“Full audit trail Who changed what, when, and which agent used which version on which task. Exportable.”
agentman.ai · checked Aug 1, 2026
Practicality
- Pricing model
- $0.50 per eligibility check vs. $6.72 CAQH benchmark
“$0.50 per eligibility check vs. $6.72 CAQH benchmark”
agentman.ai · checked Aug 1, 2026 - Price point
- $0.50 per eligibility check vs. $6.72 CAQH benchmark
“$0.50 per eligibility check vs. $6.72 CAQH benchmark”
agentman.ai · checked Aug 1, 2026 - Availability
- Start building free
“Start building free”
agentman.ai · checked Aug 1, 2026 - Deployment options
- Run them in any AI tool you already use.
“Run them in any AI tool you already use.”
agentman.ai · checked Aug 1, 2026 - Integrations
- no public informationagentman.ai · checked Aug 1, 2026 · source did not state this
- Supported regions
- no public informationagentman.ai · checked Aug 1, 2026 · source did not state this
- Support model
- no public informationagentman.ai · checked Aug 1, 2026 · source did not state this
Foundation models
- Base models
- no public informationagentman.ai · checked Aug 1, 2026 · source did not state this
- Model provider
- no public informationagentman.ai · checked Aug 1, 2026 · source did not state this
- Model swappable
- no public informationagentman.ai · checked Aug 1, 2026 · source did not state this
- Open weights
- no public informationagentman.ai · checked Aug 1, 2026 · source did not state this
- Fine-tuning
- no public informationagentman.ai · checked Aug 1, 2026 · source did not state this
- Context window
- no public informationagentman.ai · checked Aug 1, 2026 · source did not state this
Ecosystem
- Protocols supported
- Open SKILL.md standard, MCP integrations, and skills you can inspect and customize.
“Open SKILL.md standard, MCP integrations, and skills you can inspect and customize.”
agentman.ai · checked Aug 1, 2026 - Tool use
- A skill captures how your best people actually do the work — their procedures, judgment, and standards — so every agent runs it the same way, every time.
“A skill captures how your best people actually do the work — their procedures, judgment, and standards — so every agent runs it the same way, every time.”
agentman.ai · checked Aug 1, 2026 - Multi-agent
- A harness orchestrates hundreds — all drawing from the same library your team owns and improves.
“A harness orchestrates hundreds — all drawing from the same library your team owns and improves.”
agentman.ai · checked Aug 1, 2026 - API access
- Use-only sharing Share a skill others can run but never read. Instructions stay hidden — and every use is logged.
“Use-only sharing Share a skill others can run but never read. Instructions stay hidden — and every use is logged.”
agentman.ai · checked Aug 1, 2026 - Open source
- no public informationagentman.ai · checked Aug 1, 2026 · source did not state this
- Marketplace presence
- no public informationagentman.ai · checked Aug 1, 2026 · source did not state this
Impact
- User base
- Trusted by Teams at
“Trusted by Teams at”
agentman.ai · checked Aug 1, 2026 - Deployment scale
- Medman is what this looks like fully built. A complete medical back office running on Agentman skills — a production harness coordinating eligibility, inbox triage, and claims loops across 1,300+ payers , with the audit trail to show what every agent did.
“Medman is what this looks like fully built. A complete medical back office running on Agentman skills — a production harness coordinating eligibility, inbox triage, and claims loops across 1,300+ payers , with the audit trail to show what every agent did.”
agentman.ai · checked Aug 1, 2026 - Target sectors
- no public informationagentman.ai · checked Aug 1, 2026 · source did not state this
- High-risk domains
- Governance & permissions Built for firms that can't get this wrong. Permission management and auditing designed for legal, private equity, and healthcare — where every decision needs a paper trail.
“Governance & permissions Built for firms that can't get this wrong. Permission management and auditing designed for legal, private equity, and healthcare — where every decision needs a paper trail.”
agentman.ai · checked Aug 1, 2026 - Documented incidents
- no public informationagentman.ai · checked Aug 1, 2026 · source did not state this