agentic-scorecard 0.3.0 → 0.4.0

package/benchmark/v0.4/controls/resilience.yaml

@@ -0,0 +1,170 @@
+dimension: resilience
+controls:
+  - id: ADRB-RES-001
+    level: 1
+    title: Changes have a documented recovery path
+    outcome: Contributors can locate actionable rollback, revert, recovery, or incident guidance.
+    risk: A harmful agent change persists because recovery is improvised under pressure.
+    allow_agent_evidence: true
+    agent_evidence_scopes: [repository]
+    evidence:
+      - type: content_terms
+        scope: repository
+        files:
+          [
+            README.md,
+            CONTRIBUTING.md,
+            AGENTS.md,
+            Agents.md,
+            agents.md,
+            .ai/AGENTS.md,
+            .ai/Agents.md,
+            .ai/constitution.md,
+            .ai/instructions/**/*.md,
+            .ai/rules/**/*.md,
+            .ai/skills/**/*.md,
+            .agents/**/*.md,
+            docs/recovery/**,
+            docs/operations/**,
+            docs/agentic/**,
+            runbooks/**,
+          ]
+        terms: [rollback, revert, recovery, incident, restore]
+        min_terms: 2
+        required_any_terms: [change, deployment, release, agent, task, pull request]
+        max_span_lines: 100
+        max_files_per_pattern: 50
+    remediation: Document how to stop work, revert code, recover affected state, and escalate an incident.
+  - id: ADRB-RES-002
+    level: 2
+    title: Failure containment and stop conditions are documented
+    outcome: Agent guidance defines mutation limits, resource budgets, retry bounds, stop triggers, escalation, and recovery ownership.
+    risk: A looping or confused agent continues spending or mutating beyond the intended scope.
+    allow_agent_evidence: true
+    agent_evidence_scopes: [repository]
+    evidence:
+      - type: content_groups
+        scope: repository
+        files:
+          [
+            AGENTS.md,
+            Agents.md,
+            agents.md,
+            SECURITY.md,
+            .ai/AGENTS.md,
+            .ai/Agents.md,
+            .ai/constitution.md,
+            .ai/instructions/**/*.md,
+            .ai/rules/**/*.md,
+            .ai/skills/**/*.md,
+            .agents/**/*.md,
+            docs/agentic/**,
+            docs/recovery/**,
+            runbooks/**,
+            templates/**,
+          ]
+        groups:
+          - id: mutation-scope
+            terms:
+              [
+                mutation limit,
+                allowed mutation,
+                allowed mutations,
+                allowed tools and mutations,
+                permitted mutation,
+                permitted mutations,
+                allowed path,
+                allowed paths,
+                allowed prefix,
+                allowed prefixes,
+                write scope,
+                out of scope,
+                outside scope,
+                edit only,
+                do not edit,
+                do not continue outside allowed paths,
+                do not continue outside the allowed paths,
+              ]
+          - id: resource-bounds
+            terms:
+              [
+                resource budget,
+                token budget,
+                time budget,
+                cost budget,
+                tool call budget,
+                tool-call budget,
+                token limit,
+                time limit,
+                cost limit,
+                tool call limit,
+                tool-call limit,
+                wall clock limit,
+                wall-clock limit,
+              ]
+          - id: retry-bounds
+            terms: [retry limit, retry budget, max retries, bounded retries, maximum attempts]
+          - id: stop-trigger
+            terms:
+              [
+                stop condition,
+                stop and ask,
+                stop and surface,
+                stop safely,
+                must stop,
+                halt work,
+                abort,
+                do not continue,
+                kill switch,
+              ]
+          - id: escalation
+            terms:
+              [
+                escalation,
+                escalate,
+                ask the coordinator,
+                ask coordinator,
+                surface to coordinator,
+                hand back,
+                ask a human,
+                escalate to a human,
+                hand back to a human,
+              ]
+          - id: recovery-ownership
+            terms:
+              [
+                recovery owner,
+                rollback owner,
+                incident owner,
+                responsible for recovery,
+                recovery responsibility,
+                on-call owner,
+              ]
+        min_groups: 6
+        max_span_lines: 120
+        max_files_per_pattern: 50
+    remediation: Add bounded scope, budget, retry, stop, escalation, and recovery requirements to task preflight.
+  - id: ADRB-RES-003
+    level: 3
+    title: Containment and recovery controls are exercised
+    outcome: Cancellation, credential revocation, rollback, timeout, and partial-failure recovery are tested.
+    risk: Recovery mechanisms exist on paper but fail when the harness behaves unexpectedly.
+    allow_attestation: true
+    allow_agent_evidence: true
+    evidence:
+      - type: manual
+        scope: organization
+        prompt: Show recent automated tests or exercises for stop, timeout, revocation, rollback, and partial failure.
+    remediation: Add failure-injection tests and periodic exercises for containment and reversible recovery.
+  - id: ADRB-RES-004
+    level: 4
+    title: Recovery outcomes drive improvement
+    outcome: Time-to-detect, time-to-stop, rollback success, impact, and recurrence trends improve containment.
+    risk: The same failure patterns repeat because recovery performance and residual impact are unknown.
+    allow_attestation: true
+    allow_agent_evidence: true
+    evidence:
+      - type: manual
+        scope: outcome
+        prompt: Provide recovery outcome trends and a recent containment or rollback improvement driven by them.
+    remediation: Trend containment and recovery outcomes and feed them into autonomy and tool design.

package/benchmark/v0.4/controls/security.yaml

@@ -0,0 +1,143 @@
+dimension: security
+controls:
+  - id: ADRB-SEC-001
+    level: 1
+    title: Agent secret and sensitive-data boundaries are documented
+    outcome: Contributors can find agent-specific rules for credentials, secrets, and sensitive data.
+    risk: Agents expose credentials or sensitive data while planning, changing, or reporting work.
+    allow_agent_evidence: true
+    agent_evidence_scopes: [repository]
+    evidence:
+      - type: content_terms
+        scope: repository
+        files:
+          [
+            SECURITY.md,
+            AGENTS.md,
+            Agents.md,
+            agents.md,
+            .ai/AGENTS.md,
+            .ai/Agents.md,
+            .ai/constitution.md,
+            .ai/instructions/**/*.md,
+            .ai/rules/**/*.md,
+            .ai/skills/**/*.md,
+            .agents/**/*.md,
+            docs/security/**,
+            docs/agentic/**,
+          ]
+        terms: [secret, secrets, credential, credentials, sensitive data, personal data, PII]
+        min_terms: 2
+        max_span_lines: 80
+        max_files_per_pattern: 50
+    remediation: Document agent-specific rules for secrets, credentials, sensitive data, logs, prompts, and generated artifacts.
+  - id: ADRB-SEC-002
+    level: 2
+    title: Agent data and autonomy boundaries are explicit
+    outcome: Agent preflight guidance binds permitted data, tools, mutations, approvals, and stop conditions.
+    risk: Operators grant more data or authority than the task requires.
+    allow_agent_evidence: true
+    agent_evidence_scopes: [repository]
+    evidence:
+      - type: content_terms
+        scope: repository
+        files:
+          [
+            SECURITY.md,
+            AGENTS.md,
+            Agents.md,
+            agents.md,
+            .ai/AGENTS.md,
+            .ai/Agents.md,
+            .ai/constitution.md,
+            .ai/instructions/**/*.md,
+            .ai/rules/**/*.md,
+            .ai/skills/**/*.md,
+            .agents/**/*.md,
+            docs/security/**,
+            docs/agentic/**,
+            templates/**,
+          ]
+        terms:
+          [
+            data classification,
+            allowed tools,
+            mutation,
+            budget,
+            human approval,
+            autonomy,
+            stop condition,
+          ]
+        min_terms: 3
+        max_span_lines: 120
+        max_files_per_pattern: 50
+    remediation: Add a task preflight that binds data, tools, write scope, budget, approvals, and stop conditions.
+  - id: ADRB-SEC-006
+    level: 2
+    title: Security reporting and response are documented
+    outcome: Contributors can find a vulnerability-reporting or security-escalation path.
+    risk: Security concerns discovered during agent work lack an accountable response path.
+    allow_agent_evidence: true
+    agent_evidence_scopes: [repository]
+    evidence:
+      - type: content_terms
+        scope: repository
+        files: [SECURITY.md, docs/security/**, docs/contributing/**]
+        terms: [report, vulnerability, security contact, escalation, incident]
+        min_terms: 2
+        max_span_lines: 80
+    remediation: Publish a vulnerability-reporting and security-escalation path with response ownership.
+  - id: ADRB-SEC-003
+    level: 3
+    title: Automated secret-leakage safeguards are enforced
+    outcome: Repository or platform automation scans relevant changes for secrets before integration.
+    risk: Credentials can enter version history because secret safeguards are absent or merely documented.
+    allow_attestation: true
+    allow_agent_evidence: true
+    agent_evidence_scopes: [repository, platform]
+    evidence_mode: any
+    evidence:
+      - type: ci_command
+        scope: repository
+        min_tools: 1
+      - type: manual
+        scope: platform
+        prompt: Show that host-native secret scanning or push protection covers the assessed repository and relevant branches, including current status and controlled exceptions.
+    remediation: Run a secret-leakage safeguard in applicable CI or enable equivalent protected platform scanning with reviewable evidence.
+  - id: ADRB-SEC-007
+    level: 3
+    title: Untrusted agent-input safeguards are enforced
+    outcome: The harness bounds untrusted content and prompt-borne instructions with enforced isolation, validation, or tested handling.
+    risk: Repository, issue, tool, or retrieved content can redirect an agent beyond the authorized task and authority.
+    allow_attestation: true
+    allow_agent_evidence: true
+    agent_evidence_scopes: [repository, platform, organization]
+    evidence:
+      - type: manual
+        scope: organization
+        prompt: Show the untrusted-input boundaries and recent mechanical tests or enforcement evidence for prompt injection, sandbox escape, or unauthorized tool instructions.
+    remediation: Define untrusted-input boundaries and enforce them with sandboxing, validation, allowlists, or adversarial tests appropriate to the harness.
+  - id: ADRB-SEC-005
+    level: 3
+    title: High-impact agent actions are technically gated
+    outcome: External authority controls prevent unapproved high-impact actions and record controlled exceptions.
+    risk: Repository instructions alone cannot prevent credential misuse or irreversible external actions.
+    allow_attestation: true
+    allow_agent_evidence: true
+    evidence:
+      - type: manual
+        scope: platform
+        prompt: Show authorization gates, scoped credentials, approval enforcement, audit records, and controlled bypasses for high-impact agent actions.
+    remediation: Enforce least-privileged credentials, approval gates, auditability, and restricted exception handling.
+  - id: ADRB-SEC-004
+    level: 4
+    title: Agent security outcomes drive improvement
+    outcome: Denials, near misses, incidents, exceptions, and adversarial exercises are trended and improve controls.
+    risk: Controls appear complete while effectiveness against real failure modes remains unknown.
+    allow_attestation: true
+    allow_agent_evidence: true
+    evidence:
+      - type: manual
+        scope: outcome
+        prompt: Provide agent-security outcome trends or exercise results and a recent control change driven by them.
+    remediation: Run adversarial exercises, trend security outcomes, and update boundaries from the results.

package/benchmark/v0.4/controls/specification.yaml

@@ -0,0 +1,65 @@
+dimension: specification
+controls:
+  - id: ADRB-SPC-001
+    level: 1
+    title: Work has a durable objective
+    outcome: Engineering work starts from a tracked issue, request, or specification artifact.
+    risk: Agents optimize an inferred problem and completion cannot be judged consistently.
+    evidence:
+      - type: path_any
+        scope: repository
+        patterns: [docs/requirements/**, docs/spec*.md, docs/specs/**, specs/**, .ai/specs/**]
+    remediation: Adopt a tracked work-request or specification template with objective, owner, and outcome.
+  - id: ADRB-SPC-002
+    level: 2
+    title: Acceptance criteria and constraints are documented
+    outcome: Work artifacts state testable acceptance criteria plus material constraints or exclusions.
+    risk: An implementation can appear plausible without satisfying a shared definition of done.
+    allow_agent_evidence: true
+    agent_evidence_scopes: [repository]
+    evidence:
+      - type: content_terms
+        scope: repository
+        files: [docs/requirements/**, docs/spec*.md, docs/specs/**, specs/**, .ai/specs/**]
+        terms: [acceptance criteria, requirements, constraints, non-goals, verification]
+        min_terms: 2
+        max_span_lines: 160
+    remediation: Add testable outcomes, constraints, exclusions, and verification expectations to work artifacts.
+  - id: ADRB-SPC-003
+    level: 3
+    title: Specification traceability is mechanically checked
+    outcome: Automation checks that applicable changes and verification trace to an approved work artifact.
+    risk: Specifications become optional prose disconnected from implementation and tests.
+    allow_agent_evidence: true
+    agent_evidence_scopes: [repository]
+    evidence:
+      - type: ci_command
+        scope: repository
+        providers: []
+        tools: []
+        min_tools: 1
+    remediation: Add a deterministic traceability check from change to work artifact and verification record.
+  - id: ADRB-SPC-005
+    level: 3
+    title: Specification traceability is required before merge
+    outcome: Repository merge policy requires the applicable traceability check or equivalent review evidence.
+    risk: A configured check can be skipped or bypassed when delivery pressure rises.
+    allow_attestation: true
+    allow_agent_evidence: true
+    evidence:
+      - type: manual
+        scope: platform
+        prompt: Show that the traceability check or equivalent review requirement is an enforced merge gate with controlled exceptions.
+    remediation: Require the traceability check in merge policy and restrict, record, and review bypasses.
+  - id: ADRB-SPC-004
+    level: 4
+    title: Specification effectiveness drives improvement
+    outcome: Rework and escaped ambiguity attributable to specifications are trended and improve the process.
+    risk: Specification ceremony grows without reducing misunderstanding or rework.
+    allow_attestation: true
+    allow_agent_evidence: true
+    evidence:
+      - type: manual
+        scope: outcome
+        prompt: Provide specification-related rework or ambiguity trends and a recent process change driven by them.
+    remediation: Classify rework causes and evolve specification practices using outcome evidence.

package/benchmark/v0.4/controls/testing.yaml

@@ -0,0 +1,82 @@
+dimension: testing
+controls:
+  - id: ADRB-TST-001
+    level: 1
+    title: Automated tests exist
+    outcome: The tracked repository contains executable tests for at least one important behavior.
+    risk: Agent changes rely on plausibility or manual inspection alone.
+    evidence:
+      - type: path_any
+        scope: repository
+        patterns: ['**/*.test.*', '**/*.spec.*', tests/**, test/**]
+    remediation: Add a fast automated test for a critical behavior and document how to run it.
+  - id: ADRB-TST-002
+    level: 2
+    title: Verification layers and canonical commands are documented
+    outcome: Contributors can identify applicable test layers and the canonical verification path.
+    risk: Agents run a convenient subset and overstate confidence in the result.
+    allow_agent_evidence: true
+    agent_evidence_scopes: [repository]
+    evidence:
+      - type: content_terms
+        scope: repository
+        files:
+          [
+            README.md,
+            CONTRIBUTING.md,
+            AGENTS.md,
+            Agents.md,
+            agents.md,
+            .ai/AGENTS.md,
+            .ai/Agents.md,
+            .ai/constitution.md,
+            .ai/instructions/**/*.md,
+            .ai/rules/**/*.md,
+            .ai/skills/**/*.md,
+            .agents/**/*.md,
+            docs/testing/**,
+            package.json,
+            Makefile,
+          ]
+        terms: [unit test, integration test, end-to-end, e2e, typecheck, lint, test]
+        min_terms: 2
+        required_any_terms: [verify, verification, test, check, CI]
+        max_span_lines: 120
+        max_files_per_pattern: 50
+    remediation: Define the test taxonomy and one canonical command that matches CI.
+  - id: ADRB-TST-003
+    level: 3
+    title: CI executes the required verification layers
+    outcome: Repository automation runs appropriate tests and static checks from a clean state.
+    risk: Documented verification can be omitted from automation or run in an unrepresentative environment.
+    allow_agent_evidence: true
+    agent_evidence_scopes: [repository]
+    evidence:
+      - type: ci_command
+        scope: repository
+        min_tools: 2
+    remediation: Configure CI to run the applicable verification layers from a clean environment.
+  - id: ADRB-TST-005
+    level: 3
+    title: Verification is enforced before merge
+    outcome: Merge policy requires the applicable CI checks and restricts bypasses.
+    risk: Healthy CI configuration remains optional under delivery pressure.
+    allow_attestation: true
+    allow_agent_evidence: true
+    evidence:
+      - type: manual
+        scope: platform
+        prompt: Show required status checks or equivalent merge gates, covered branches, bypass actors, and exception controls.
+    remediation: Make appropriate CI checks required merge gates and restrict, record, and review bypasses.
+  - id: ADRB-TST-004
+    level: 4
+    title: Verification effectiveness drives improvement
+    outcome: Escaped defects, flakiness, and other signal-quality outcomes are trended and improve testing.
+    risk: Test count and coverage rise while meaningful defects still escape.
+    allow_attestation: true
+    allow_agent_evidence: true
+    evidence:
+      - type: manual
+        scope: outcome
+        prompt: Provide verification outcome trends by task class and a recent test-strategy improvement driven by them.
+    remediation: Trend escaped defects and signal quality, then invest in the weakest verification layers.

package/benchmark/v0.4/controls/tooling.yaml

@@ -0,0 +1,69 @@
+dimension: tooling
+controls:
+  - id: ADRB-TOL-001
+    level: 1
+    title: Supported agent tools are declared
+    outcome: The tracked repository identifies supported agent interfaces or tool configuration.
+    risk: Agents discover tools opportunistically and use unsupported or unsafe paths.
+    allow_agent_evidence: true
+    agent_evidence_scopes: [repository]
+    evidence:
+      - type: path_any
+        scope: repository
+        patterns: [.ai/agentic.config.*, .ai/skills/**, .agents/**, mcp.json, .mcp.json]
+    remediation: Commit a non-empty declaration of supported agent surfaces and their intended use.
+  - id: ADRB-TOL-002
+    level: 2
+    title: Tool scope and failure behavior are documented
+    outcome: Tool guidance defines authority, validation, success signals, failure handling, and approved fallback.
+    risk: Agents bypass failures, widen scope, or mistake partial results for success.
+    allow_agent_evidence: true
+    agent_evidence_scopes: [repository]
+    evidence:
+      - type: content_terms
+        scope: repository
+        files:
+          [
+            AGENTS.md,
+            Agents.md,
+            agents.md,
+            .ai/AGENTS.md,
+            .ai/Agents.md,
+            .ai/agentic*.md,
+            .ai/instructions/**/*.md,
+            .ai/rules/**/*.md,
+            .ai/skills/**/*.md,
+            .agents/**/*.md,
+            docs/agentic/**,
+            docs/tools/**,
+          ]
+        terms: [authority, permission, read-only, validation, failure, fallback, approval]
+        min_terms: 3
+        required_any_terms: [tool, MCP, connector, skill, command, agent]
+        max_span_lines: 120
+        max_files_per_pattern: 50
+    remediation: Document each high-impact tool's authority, inputs, validation, failure mode, and fallback.
+  - id: ADRB-TOL-003
+    level: 3
+    title: High-impact tool authority is technically bounded and audited
+    outcome: High-impact tools enforce least privilege, authorization, structured validation, and audit records.
+    risk: Prompt instructions become the only barrier between an agent and an irreversible action.
+    allow_attestation: true
+    allow_agent_evidence: true
+    evidence:
+      - type: manual
+        scope: platform
+        prompt: Show technical least-privilege enforcement, authorization tests, validation, audit records, and fail-closed behavior for high-impact tools.
+    remediation: Enforce scoped credentials, authorization, schema validation, audit logging, and deny-by-default behavior.
+  - id: ADRB-TOL-004
+    level: 4
+    title: Tool reliability drives improvement
+    outcome: Tool success, partial failure, denial, latency, and unsafe-fallback attempts are trended and improved.
+    risk: Tooling quality and risky workarounds remain anecdotal until an incident occurs.
+    allow_attestation: true
+    allow_agent_evidence: true
+    evidence:
+      - type: manual
+        scope: outcome
+        prompt: Provide tool reliability trends and a recent tool or fallback improvement driven by them.
+    remediation: Trend tool outcomes by task and risk class and improve weak or bypassed interfaces.

package/benchmark/v0.4/report-schema.json

@@ -0,0 +1,89 @@
+{
+  "$schema": "https://json-schema.org/draft/2020-12/schema",
+  "$id": "https://agentic-readiness.dev/schema/v0.4/report.json",
+  "title": "ADRB v0.4 assessment report",
+  "type": "object",
+  "required": [
+    "schema_version",
+    "benchmark",
+    "target",
+    "assessed_at",
+    "warnings",
+    "score",
+    "evidence_summary",
+    "dimensions",
+    "controls",
+    "profiles",
+    "readiness",
+    "limitations"
+  ],
+  "properties": {
+    "schema_version": { "const": "0.4.0" },
+    "benchmark": {
+      "type": "object",
+      "required": ["id", "version"],
+      "properties": { "version": { "const": "0.4.0" } }
+    },
+    "target": {
+      "type": "object",
+      "required": [
+        "repository",
+        "profile",
+        "scope",
+        "git_head",
+        "git_remote",
+        "working_tree_dirty"
+      ],
+      "properties": { "scope": { "enum": ["tracked", "workspace"] } }
+    },
+    "assessed_at": { "type": "string", "format": "date-time" },
+    "warnings": { "type": "array", "items": { "type": "string" } },
+    "score": {
+      "type": "object",
+      "additionalProperties": false,
+      "required": ["total", "maximum", "percentage", "repository"],
+      "properties": {
+        "total": { "type": "integer", "minimum": 0, "maximum": 40 },
+        "maximum": { "const": 40 },
+        "percentage": { "type": "integer", "minimum": 0, "maximum": 100 },
+        "repository": {
+          "type": "object",
+          "additionalProperties": false,
+          "required": ["achieved", "ceiling", "percentage"],
+          "properties": {
+            "achieved": { "type": "integer", "minimum": 0, "maximum": 40 },
+            "ceiling": { "type": "integer", "minimum": 0, "maximum": 40 },
+            "percentage": { "type": "integer", "minimum": 0, "maximum": 100 }
+          }
+        }
+      }
+    },
+    "evidence_summary": {
+      "type": "object",
+      "additionalProperties": false,
+      "required": [
+        "repository_detected",
+        "agent_collected",
+        "attested",
+        "unmet",
+        "unknown",
+        "resolved",
+        "total"
+      ],
+      "properties": {
+        "repository_detected": { "type": "integer", "minimum": 0 },
+        "agent_collected": { "type": "integer", "minimum": 0 },
+        "attested": { "type": "integer", "minimum": 0 },
+        "unmet": { "type": "integer", "minimum": 0 },
+        "unknown": { "type": "integer", "minimum": 0 },
+        "resolved": { "type": "integer", "minimum": 0 },
+        "total": { "type": "integer", "minimum": 0 }
+      }
+    },
+    "dimensions": { "type": "array", "minItems": 10, "maxItems": 10 },
+    "controls": { "type": "array" },
+    "profiles": { "type": "array" },
+    "readiness": { "type": "object" },
+    "limitations": { "type": "array", "items": { "type": "string" } }
+  }
+}