Good fit if
- Safety leads and engineering managers justifying agent deployments
- Teams that need a reviewable written safety argument
- Compliance reviewer agents checking evidence links
Safety & Security
Wave 2 · launch-sequenced
Agent Safety Case Builder
Build a structured safety case - claims, arguments, evidence - for any agent deployment, in a form both a reviewing human and an auditing agent can verify.
v1.0.0-rc1
Medium risk
25-min quick start
Select a one-time tier below
View agent record
Built for: safety-leads · engineering-managers · compliance-reviewer-agents · operators ·
agent://products.json
200 OK
{
"id": "agent-safety-case-builder",
"version": "1.0.0-rc1",
"price_usd": { "lite":44, "std":119, "prem":199 },
"risk_level": "medium",
"reversible": true,
"checkout": { "enabled": true },
"purchasable": true
}
See how it fits your agent stack
Tool call / action
requested by an agent
Agent Safety Case Builder
Safety-Cases/
Evidence-Registry/
Review-Records/
Worked-Safety-Cases/
Gated action
allowed or denied, logged
Human approval gate
Preview-before-apply
Rollback path
Discover
read the record
Evaluate
Medium risk · 7 systems
Install
new Safety-Cases/
Preview
diff before apply
Approve
human gate
Audit & rollback
CCS-100 audit
Non-destructive by rule — new-folder install, never overwrite, human-approval gates for risky steps, rollback included.
agent-safety-case-builder/
Safety-Cases/
Evidence-Registry/
Review-Records/
Worked-Safety-Cases/
README.md
AGENT-INSTRUCTIONS.md
Integration/ROLLBACK-GUIDE.md
Format & setup
FormatMarkdown + JSON file kit (plain text, tool-agnostic)
Skill levelIntermediate to advanced; beginner-usable via quick start
Quick start25 min
Full setup150 min
CAE-A claim-argument-evidence frame (credited adaptation), safety-case + evidence-registry JSON schemas, hazard analysis, failure mode table, control mapping, tool-authority + evaluation evidence maps, residual risk register, human-only sign-off records, CCS-100 scorecard, worked case with a failed claim, 16-doc integration pack, 5 upgrade modules, 10-doc differentiation folder
# Non-destructive lifecycle — nothing runs without preview + approval
$ agent read ./agent-safety-case-builder/manifest.json # metadata, risk, compatibility
$ agent install --new-folder ./agent-safety-case-builder # never overwrites existing files
$ agent apply --preview # preview-before-apply diff
$ agent verify ./agent-safety-case-builder --scorecard CCS-100 # Safety-Cases contracts
⚠ gated steps require named human approval before execution
$ agent rollback ./agent-safety-case-builder # Delete the install folder (complete remo
✓ folder removed — nothing else touched
{
"required_permissions": ["write access to one new buyer-chosen folder"],
"integration_modes": ["standalone", "drop-in-upgrade", "advanced-integration", ],
"compatible_systems": [
"Claude (Projects, Skills, Claude Code)",
"ChatGPT (Custom GPTs, Projects)",
"any LLM chat assistant",
"MCP-based agent stacks",
],
"license_type": "single-operator",
"checkout": { "enabled": true, "status": "polar_active" }
}
The problem it solves
Deployment approval by vibes: no structured argument connecting this agent is safe enough to verifiable evidence, so gaps are invisible.
Use cases
justify a deployment decision
surface hidden gaps before production
answer a security or compliance review
make residual risk an explicit owned decision
support a payments-activation decision
Safety & permissions
Non-destructive by rule
Plain-text kit; structures an argument and surfaces gaps. Grants no deployment approval (human-only sign-off), manufactures no evidence (references only), enforces nothing, executes nothing. A safety case is a structured argument for a decision, NOT a guarantee of safety. Handles no credentials or wallets.
Required
write access to one new buyer-chosen folder
Rollback
Delete the install folder (complete removal). Completed cases and evidence registries are records - keep them. Deeper integrations: Integrations/ROLLBACK-GUIDE.md.
For an evaluating agent
Kit for building structured safety cases for agent deployments on CAE-A (claims-arguments-evidence, a credited adaptation): hazard analysis, failure mode table, control mapping, evidence registry (references only), residual risk register, human-only sign-off. Every claim decomposed or evidenced, else marked asserted-only and made visible; CCS-100 scores hidden gaps lowest. Grants no approval, manufactures no evidence, guarantees no safety. Registers evidence from P03/P09/P14/P21/P22/P23. Non-destructive install, delete-folder rollback. Wave 2, built Production: live and purchasable through verified Polar checkout; prices owner-confirmed 2026-07-03 (still production); verified Polar checkout is active on this page.
Buyer decision
Is Agent Safety Case Builder right for me?
Problem addressed: Deployment approval by vibes: no structured argument connecting this agent is safe enough to verifiable evidence, so gaps are invisible.
Probably not a fit if
- Buyers expecting automated safety verification
- Casual single-agent hobby use
- Anyone treating a safety case as a legal shield by itself
Included
Safety-Cases/, Evidence-Registry/ (4), Review-Records/, Worked-Safety-Cases/ folders plus the standard architecture.
Not included
- No software, app, executable, or code that runs by itself
- No hosted service, account, login, or cloud dashboard
- No live integrations: Zapier/Make items are written blueprint descriptions, not built Zaps or scenarios
- No API access, API keys, credentials, or third-party subscriptions
| Tier | Price | Canonical depth | License |
|---|---|---|---|
| Standard | $119 USD | Full product: all templates, harnesses, SOPs, integration pack, and samples. | Single-Operator |
| Premium | $199 USD | Standard plus all 5 upgrade modules (Basic, Pro, Agent, Automation, Safety) and priority support. | Single-Operator |
Bundle membership
Compatibility and limits
A safety case is an argument backed by YOUR evidence - the kit structures it, you substantiate it Not a certification, audit service, or legal advice
Three one-time tiers — verified Polar checkout active
Lite
$44
Core templates & quick-start path. Best for testing the system manually first.
Buy Lite — one-timeStandardpopular
$119
Full product: all templates, harnesses, SOPs, integration pack, and samples.
Buy Standard — one-timePremium
$199
Standard plus all 5 upgrade modules (Basic, Pro, Agent, Automation, Safety) and priority support.
Buy Premium — one-timeEach tier uses its verified Polar checkout. See full pricing and bundles.
Related products
AI Agent Permission and Safety Gate Kit
Safety & Security
Agent Tool-Use Permission Matrix
Safety & Security
Agent Evaluation Harness Suite
Quality & Evaluation
Agent Audit Trail Generator
Infrastructure & Governance
Agent Prompt Injection Defense Kit
Safety & Security
Agent Runtime Incident Response Kit
Reliability & Operations
In bundles: Wave 2 Agent Trust & Safety Stack ·
Decision guides involving this product
- How to Choose an AI Agent Safety ToolkitSelect the right combination of permissions, defensive handling, audit evidence, safety cases, and deployment-readiness controls.
Related categories
- AI Agent Safety & GovernancePractical policy, evidence, permission, and defensive systems for reviewing how agents act and where they must stop.
- AI Evaluation & Quality ControlRubrics, task suites, regression gates, safety evidence, and audit records for judging AI and agent behavior.
Available in canonical bundles
These bundle memberships come directly from the canonical bundle catalog. Compare the exact contents before purchase.