@martinloop/mcp 0.2.5 → 0.3.0

package/README.md

@@ -1,55 +1,63 @@
 # @martinloop/mcp
 
-Governed execution cockpit for AI coding agents over MCP stdio.
+Governed MCP server for AI coding agents over local stdio.
 
-The standalone `@martinloop/mcp` release train is documented through `0.1.4`, `0.2.0`, and the later `0.2.5` stable cockpit line. It gives hosts one bounded execution entrypoint, rich read-only inspection tools, discoverable resources, run triage, and operator prompts on top of Martin Loop’s persisted run records.
+`@martinloop/mcp@0.2.7` is the current public baseline. It gives hosts one bounded execution entrypoint, strong read-only inspection, clear next-step guidance, and a safer default MartinLoop workflow.
 
-This package stays local-first and stdio-first in public packaging today.
+This package stays local-first and stdio-first in the public OSS lane.
 
-For host-facing guidance, see [MCP for AI Agents](https://github.com/Keesan12/martin-loop/blob/main/docs/oss/MCP-FOR-AI-AGENTS.md).
+## Public release train
 
-## Public Release Train
+- `0.2.7` made the guided MCP workflow easier to adopt and harder to misuse.
+- `0.3.0` is the next adoption release.
+- `0.3.1` is planned for review and handoff controls.
+- `0.3.2` is planned for opt-in execution controls.
 
-- 0.1.4 operator foundation.
-- 0.2.0 cockpit expansion. 0.2.0 adds resources, resource templates, prompts, and read-only cockpit inspection.
-- 0.2.5 stable cockpit line with local triage and degraded run-store hardening.
-
-## What Ships
+## What ships today
 
 ### Tools
 
 - `martin_doctor`
+- `martin_plan`
 - `martin_preflight`
 - `martin_run`
 - `martin_inspect`
 - `martin_status`
+- `martin_logs`
+- `martin_pause`
+- `martin_cancel`
+- `martin_continue`
 - `martin_list_runs`
 - `martin_triage_runs`
 - `martin_get_run`
 - `martin_get_attempt`
 - `martin_get_verification_results`
 - `martin_run_dossier`
+- `martin_dossier`
+- `martin_eval`
+- `martin_pr_summary`
+- `martin_create_pr`
+- `martin_review_pr`
 
 ### Resources
 
 - `martin://server/health`
 - `martin://runs/recent`
 - `martin://runs/triage`
+- `martin://runs/latest`
 - `martin://runs/latest/summary`
 - `martin://runs/latest/proof-card`
 - `martin://runs/latest/budget-status`
 - `martin://runs/latest/verifier-evidence`
 - `martin://runs/latest/rollback-evidence`
+- `martin://policies/current`
+- `martin://repo/risk-map`
+- `martin://verifiers/results`
 - `martin://agent/next-step`
 - `martin://guides/mcp-usage`
+- `martin://guides/agent-start`
 - `martin://guides/publish-readiness`
 
-### Resource templates
-
-- `martin://runs/{loopId}`
-- `martin://runs/{loopId}/attempts/{attemptIndex}`
-- `martin://runs/{loopId}/verification`
-
 ### Prompts
 
 - `martin_start`
@@ -63,31 +71,29 @@ For host-facing guidance, see [MCP for AI Agents](https://github.com/Keesan12/ma
 - `martin_publish_readiness_review`
 - `martin_triage_run_store`
 
-## Recommended Flow
+## Recommended flow
 
 1. `martin_doctor`
-2. `martin_preflight`
-3. `martin_run`
-4. `martin_triage_runs`
-5. `martin://agent/next-step` or `martin://runs/latest/summary`
-6. `martin_run_dossier` or `martin_get_*` when compact evidence says the full record is needed
-7. `martin://runs/latest/proof-card` or `martin_prove` for a shareable receipt
+2. `martin_plan`
+3. `martin_preflight`
+4. `martin_run`
+5. `martin_status` or `martin_logs`
+6. `martin_dossier`
+7. `martin_eval`
 
 ## Install
 
-Run the packaged server directly:
-
 ```sh
 npx -y @martinloop/mcp
 ```
 
-Add it to Codex:
+Codex:
 
 ```sh
 codex mcp add martin-loop -- npx -y @martinloop/mcp
 ```
 
-Add it to Claude Code:
+Claude Code:
 
 ```sh
 # macOS/Linux
@@ -97,103 +103,24 @@ claude mcp add --transport stdio --scope user martin-loop -- npx -y @martinloop/
 claude mcp add --transport stdio --scope user martin-loop -- cmd /c npx -y @martinloop/mcp
 ```
 
-Generate host config from the CLI when you want minimal, diagnostic, or full-local profiles:
+If you want generated host config, use the MartinLoop CLI:
 
 ```sh
 martin mcp print-config --host codex --transport stdio --profile minimal
 martin mcp print-config --host claude --transport stdio --profile diagnostic
 martin mcp print-config --host gemini --transport stdio --profile full-local
+martin mcp print-config --host generic --transport stdio --profile github-review
 ```
 
-`martin mcp install` supports the same host set and only writes when the target file is absent or already contains a Martin Loop block.
-
-Codex also supports `~/.codex/config.toml` and project-scoped `.codex/config.toml`:
-
-```toml
-[mcp_servers."martin-loop"]
-command = "npx"
-args = ["-y", "@martinloop/mcp"]
-cwd = "C:\\path\\to\\repo"
-startup_timeout_sec = 20
-tool_timeout_sec = 180
-enabled_tools = [
-  "martin_doctor",
-  "martin_preflight",
-  "martin_list_runs",
-  "martin_triage_runs",
-  "martin_run_dossier",
-]
-env = { MARTIN_RUNS_DIR = "C:\\path\\to\\runs" }
-```
-
-If you use `martin mcp install`, it will only write a starter host config when the target file is absent, or when it detects an existing Martin Loop block and can remain idempotent. Otherwise it refuses to overwrite mixed host config so you can merge safely.
-
-When `CODEX_HOME` is set, Codex user-scope installs target `CODEX_HOME\\config.toml` instead of the default user path.
-
-Registry/server identifier: `io.github.Keesan12/martin-loop`
-
-## Host coverage
-
-- `codex`: local stdio profiles
-- `claude`: local, user, and project scopes
-- `gemini`: local `settings.json` snippets with `includeTools`
-- `generic`: JSON config for MCP-aware wrappers
-
-Operating-system launcher behavior is explicit:
-
-- Windows: `cmd /c npx -y @martinloop/mcp`
-- macOS/Linux: `npx -y @martinloop/mcp`
-
-Claude `--scope local` remains CLI-managed. `martin mcp install --host claude --scope local` shells out to Claude Code directly instead of fabricating a repo config file for that scope.
-
-## Discovery metadata
-
-- JSON resources now carry `metadata.serverVersion` and `metadata.discoveryRevision`.
-- Environment-specific path details stay in `martin://server/health` instead of low-context discovery metadata.
-- Compact resources expose low-token latest-run summaries, proof cards, budget status, verifier evidence, rollback evidence, and a single recommended next step.
-- Prompts stamp the current server version and discovery revision into their descriptions so hosts can confirm which surface they discovered.
-- The server does **not** advertise `listChanged` yet. That is deliberate: the current discovery surface is stable and versioned, but it does not yet emit authoritative change notifications.
-
-## Runtime Model
-
-- `martin_run` is the only execution entrypoint.
-- All other Martin MCP tools are read-only.
-- Live runs require `claude` or `codex` on `PATH`.
-- Stub or smoke flows use `MARTIN_LIVE=false`.
-- Paths stay bounded to the configured workspace root and runs root.
-- Direct raw-model compatibility is not the target. Martin Loop supports hosts and wrappers that speak MCP; open-source model families such as Gemma or Nemotron should use the `generic` host path through an MCP-capable shell or runtime.
-
-## Operator Notes
+## Compatibility posture
 
-- `martin_get_verification_results` only reports persisted verification evidence. If evidence is missing, it returns `unavailable` with warnings.
-- `martin_triage_runs` is the fastest way to decide which persisted run deserves attention first.
-- `martin://agent/next-step`, `martin://runs/latest/summary`, and `martin://runs/latest/proof-card` are the best default follow-ups for context-constrained agents.
-- `martin_run_dossier` is the richest single-run inspection surface and is best when a compact receipt says deeper evidence is needed.
-- Resources and prompts reuse the same run-store selectors as the tools; they are discovery surfaces, not a second data model.
-- The recommended host default is the `minimal` profile: `martin_doctor`, `martin_preflight`, `martin_list_runs`, `martin_triage_runs`, and `martin_run_dossier`. Use `diagnostic` for read-only archaeology and `full-local` only when the host should execute runs.
-
-## Debugging
-
-Use the live handshake inspector before you blame the host:
-
-```sh
-pnpm --filter @martinloop/mcp inspect:live
-```
-
-If you want the official MCP Inspector UI, point it at the same stdio launch command:
-
-```sh
-npx @modelcontextprotocol/inspector --command npx --args "-y,@martinloop/mcp"
-```
-
-The stdio server keeps protocol output on stdout and diagnostic logging on stderr. When a host integration goes sideways, confirm the live discovery surface first, then move on to the host config.
-
-For WSL or Linux validation, do a native install on that platform before you smoke the package. Reusing Windows-installed `node_modules` across WSL will fail on native dependencies such as `esbuild`, which looks like a transport failure but is really a cross-platform install mismatch.
+- `martin_run` remains the single execution entrypoint.
+- Read-only inspection stays available without execution-capable profiles.
+- The OSS package stays focused on local stdio workflows. Hosted and team features live on a separate product track.
+- Later `0.3.x` releases should widen adoption and guidance without blurring those boundaries.
 
 ## Verification
 
-From the repository root:
-
 ```sh
 pnpm --filter @martinloop/mcp lint
 pnpm --filter @martinloop/mcp test
@@ -201,23 +128,4 @@ pnpm --filter @martinloop/mcp build
 pnpm --filter @martinloop/mcp smoke:pack
 pnpm --filter @martinloop/mcp smoke:published:pack
 pnpm --filter @martinloop/mcp verify:release
-pnpm --filter @martin/cli verify:hosts:live
-pnpm --filter @martinloop/mcp smoke:published
-pnpm --filter @martinloop/mcp inspect:live
 ```
-
-- `smoke:pack` verifies the packed tarball and stdio launch path.
-- `smoke:published:pack` verifies install-and-run behavior from a freshly packed local tarball through the installed `mcp` bin before npm publish.
-- `verify:release` checks metadata parity, release-note presence, install docs, and discovery-surface claims.
-- `@martin/cli verify:hosts:live` proves the generated host config against the real Codex, Claude, and Gemini CLIs on this machine.
-- `smoke:published` remains a post-publish npm gate.
-
-## Compatibility
-
-`0.2.5` is the current integrated governed execution cockpit line:
-
-- `martin_run`, `martin_inspect`, `martin_status`, `martin_doctor`, and `martin_preflight` remain backward-compatible.
-- New read-only surfaces are additive.
-- No new write-capable MCP tools are introduced in `0.2.5`.
-
-See `docs/release/MCP-COMPATIBILITY.md`, `docs/release/MCP-0.2.0-RELEASE-NOTES.md`, and `docs/release/MCP-0.2.5-RELEASE-NOTES.md` for the public release contract and delivery sequence.

package/dist/discovery-metadata.d.ts

@@ -1,8 +1,12 @@
-export declare const MARTIN_TOOL_NAMES: readonly ["martin_run", "martin_inspect", "martin_status", "martin_doctor", "martin_preflight", "martin_list_runs", "martin_triage_runs", "martin_get_run", "martin_get_attempt", "martin_get_verification_results", "martin_run_dossier"];
-export declare const MARTIN_STARTER_TOOL_NAMES: readonly ["martin_doctor", "martin_preflight", "martin_run", "martin_triage_runs", "martin_run_dossier"];
-export declare const MARTIN_RESOURCE_URIS: readonly ["martin://server/health", "martin://runs/recent", "martin://runs/triage", "martin://guides/mcp-usage", "martin://guides/publish-readiness"];
-export declare const MARTIN_RESOURCE_TEMPLATE_URIS: readonly ["martin://runs/{loopId}", "martin://runs/{loopId}/attempts/{attemptIndex}", "martin://runs/{loopId}/verification"];
-export declare const MARTIN_PROMPT_NAMES: readonly ["martin_governed_coding_kickoff", "martin_debug_failed_run", "martin_publish_readiness_review", "martin_triage_run_store"];
+export declare const MARTIN_TOOL_NAMES: readonly ["martin_run", "martin_inspect", "martin_status", "martin_doctor", "martin_plan", "martin_preflight", "martin_logs", "martin_pause", "martin_cancel", "martin_continue", "martin_list_runs", "martin_triage_runs", "martin_get_run", "martin_get_attempt", "martin_get_verification_results", "martin_run_dossier", "martin_dossier", "martin_eval", "martin_pr_summary", "martin_create_pr", "martin_review_pr"];
+export declare const MARTIN_STARTER_TOOL_NAMES: readonly ["martin_doctor", "martin_plan", "martin_preflight", "martin_run", "martin_triage_runs", "martin_dossier"];
+export declare const MARTIN_MINIMAL_TOOL_NAMES: readonly ["martin_doctor", "martin_plan", "martin_preflight", "martin_list_runs", "martin_triage_runs", "martin_dossier"];
+export declare const MARTIN_DIAGNOSTIC_TOOL_NAMES: readonly ["martin_doctor", "martin_plan", "martin_preflight", "martin_logs", "martin_list_runs", "martin_triage_runs", "martin_get_run", "martin_get_attempt", "martin_get_verification_results", "martin_dossier", "martin_eval"];
+export declare const MARTIN_GITHUB_REVIEW_TOOL_NAMES: readonly ["martin_doctor", "martin_plan", "martin_preflight", "martin_dossier", "martin_eval", "martin_pr_summary", "martin_create_pr", "martin_review_pr"];
+export declare const MARTIN_PAID_REMOTE_TOOL_NAMES: readonly ["martin_doctor", "martin_plan", "martin_preflight", "martin_run", "martin_list_runs", "martin_triage_runs", "martin_get_run", "martin_get_verification_results", "martin_dossier", "martin_eval"];
+export declare const MARTIN_RESOURCE_URIS: readonly ["martin://server/health", "martin://runs/recent", "martin://runs/triage", "martin://runs/latest", "martin://runs/latest/summary", "martin://runs/latest/proof-card", "martin://runs/latest/budget-status", "martin://runs/latest/verifier-evidence", "martin://runs/latest/rollback-evidence", "martin://policies/current", "martin://repo/risk-map", "martin://verifiers/results", "martin://agent/next-step", "martin://guides/mcp-usage", "martin://guides/agent-start", "martin://guides/command-map", "martin://guides/ide-onboarding", "martin://guides/operating-rules", "martin://guides/publish-readiness"];
+export declare const MARTIN_RESOURCE_TEMPLATE_URIS: readonly ["martin://runs/{loopId}", "martin://runs/{loopId}/dossier", "martin://runs/{loopId}/attempts/{attemptIndex}", "martin://runs/{loopId}/verification"];
+export declare const MARTIN_PROMPT_NAMES: readonly ["martin_start", "martin_preflight", "martin_triage", "martin_resume", "martin_prove", "martin_release_check", "martin_governed_coding_kickoff", "martin_debug_failed_run", "martin_publish_readiness_review", "martin_triage_run_store", "safe_bug_fix", "write_tests_first", "small_refactor", "security_review", "pr_review", "release_check"];
 export interface MartinDiscoveryMetadata {
     serverVersion: string;
     discoveryRevision: string;
@@ -12,5 +16,6 @@ export interface MartinDiscoveryMetadata {
     resourceTemplateCount: number;
     promptCount: number;
     starterTools: string[];
+    profiles: Record<string, string[]>;
 }
 export declare function buildMartinDiscoveryMetadata(serverVersion: string): MartinDiscoveryMetadata;

package/dist/discovery-metadata.js

@@ -4,38 +4,119 @@ export const MARTIN_TOOL_NAMES = [
     "martin_inspect",
     "martin_status",
     "martin_doctor",
+    "martin_plan",
     "martin_preflight",
+    "martin_logs",
+    "martin_pause",
+    "martin_cancel",
+    "martin_continue",
     "martin_list_runs",
     "martin_triage_runs",
     "martin_get_run",
     "martin_get_attempt",
     "martin_get_verification_results",
-    "martin_run_dossier"
+    "martin_run_dossier",
+    "martin_dossier",
+    "martin_eval",
+    "martin_pr_summary",
+    "martin_create_pr",
+    "martin_review_pr"
 ];
 export const MARTIN_STARTER_TOOL_NAMES = [
     "martin_doctor",
+    "martin_plan",
     "martin_preflight",
     "martin_run",
     "martin_triage_runs",
-    "martin_run_dossier"
+    "martin_dossier"
+];
+export const MARTIN_MINIMAL_TOOL_NAMES = [
+    "martin_doctor",
+    "martin_plan",
+    "martin_preflight",
+    "martin_list_runs",
+    "martin_triage_runs",
+    "martin_dossier"
+];
+export const MARTIN_DIAGNOSTIC_TOOL_NAMES = [
+    "martin_doctor",
+    "martin_plan",
+    "martin_preflight",
+    "martin_logs",
+    "martin_list_runs",
+    "martin_triage_runs",
+    "martin_get_run",
+    "martin_get_attempt",
+    "martin_get_verification_results",
+    "martin_dossier",
+    "martin_eval"
+];
+export const MARTIN_GITHUB_REVIEW_TOOL_NAMES = [
+    "martin_doctor",
+    "martin_plan",
+    "martin_preflight",
+    "martin_dossier",
+    "martin_eval",
+    "martin_pr_summary",
+    "martin_create_pr",
+    "martin_review_pr"
+];
+export const MARTIN_PAID_REMOTE_TOOL_NAMES = [
+    "martin_doctor",
+    "martin_plan",
+    "martin_preflight",
+    "martin_run",
+    "martin_list_runs",
+    "martin_triage_runs",
+    "martin_get_run",
+    "martin_get_verification_results",
+    "martin_dossier",
+    "martin_eval"
 ];
 export const MARTIN_RESOURCE_URIS = [
     "martin://server/health",
     "martin://runs/recent",
     "martin://runs/triage",
+    "martin://runs/latest",
+    "martin://runs/latest/summary",
+    "martin://runs/latest/proof-card",
+    "martin://runs/latest/budget-status",
+    "martin://runs/latest/verifier-evidence",
+    "martin://runs/latest/rollback-evidence",
+    "martin://policies/current",
+    "martin://repo/risk-map",
+    "martin://verifiers/results",
+    "martin://agent/next-step",
     "martin://guides/mcp-usage",
+    "martin://guides/agent-start",
+    "martin://guides/command-map",
+    "martin://guides/ide-onboarding",
+    "martin://guides/operating-rules",
     "martin://guides/publish-readiness"
 ];
 export const MARTIN_RESOURCE_TEMPLATE_URIS = [
     "martin://runs/{loopId}",
+    "martin://runs/{loopId}/dossier",
     "martin://runs/{loopId}/attempts/{attemptIndex}",
     "martin://runs/{loopId}/verification"
 ];
 export const MARTIN_PROMPT_NAMES = [
+    "martin_start",
+    "martin_preflight",
+    "martin_triage",
+    "martin_resume",
+    "martin_prove",
+    "martin_release_check",
     "martin_governed_coding_kickoff",
     "martin_debug_failed_run",
     "martin_publish_readiness_review",
-    "martin_triage_run_store"
+    "martin_triage_run_store",
+    "safe_bug_fix",
+    "write_tests_first",
+    "small_refactor",
+    "security_review",
+    "pr_review",
+    "release_check"
 ];
 export function buildMartinDiscoveryMetadata(serverVersion) {
     const surface = {
@@ -43,7 +124,15 @@ export function buildMartinDiscoveryMetadata(serverVersion) {
         resources: [...MARTIN_RESOURCE_URIS],
         resourceTemplates: [...MARTIN_RESOURCE_TEMPLATE_URIS],
         prompts: [...MARTIN_PROMPT_NAMES],
-        starterTools: [...MARTIN_STARTER_TOOL_NAMES]
+        starterTools: [...MARTIN_STARTER_TOOL_NAMES],
+        profiles: {
+            minimal: [...MARTIN_MINIMAL_TOOL_NAMES],
+            diagnostic: [...MARTIN_DIAGNOSTIC_TOOL_NAMES],
+            "github-review": [...MARTIN_GITHUB_REVIEW_TOOL_NAMES],
+            "full-local": [...MARTIN_TOOL_NAMES],
+            starter: [...MARTIN_STARTER_TOOL_NAMES],
+            full: [...MARTIN_TOOL_NAMES]
+        }
     };
     const discoveryRevision = createHash("sha256")
         .update(JSON.stringify({ serverVersion, surface }))
@@ -57,6 +146,7 @@ export function buildMartinDiscoveryMetadata(serverVersion) {
         resourceCount: surface.resources.length,
         resourceTemplateCount: surface.resourceTemplates.length,
         promptCount: surface.prompts.length,
-        starterTools: [...surface.starterTools]
+        starterTools: [...surface.starterTools],
+        profiles: surface.profiles
     };
 }

package/dist/package-version.d.ts

@@ -1 +1 @@
-export declare const MARTIN_MCP_PACKAGE_VERSION = "0.2.5";
+export declare const MARTIN_MCP_PACKAGE_VERSION = "0.3.0";

package/dist/package-version.js

@@ -1,3 +1,3 @@
 // Keep this aligned with packages/mcp/package.json during version bumps so the
 // runtime does not depend on package.json being present in every hosted bundle.
-export const MARTIN_MCP_PACKAGE_VERSION = "0.2.5";
+export const MARTIN_MCP_PACKAGE_VERSION = "0.3.0";

package/dist/prompts.d.ts

@@ -5,7 +5,7 @@ export interface MartinGetPromptInput {
     arguments?: Record<string, string>;
     runsDir?: string;
     workingDirectory?: string;
-    engine?: "claude" | "codex";
+    engine?: "claude" | "codex" | "gemini";
 }
 export declare function listMartinPrompts(): {
     prompts: Prompt[];

package/dist/prompts.js

@@ -108,6 +108,56 @@ export const MARTIN_PROMPTS = [
         arguments: [
             { name: "focus", description: "Optional triage focus, such as verification failures, budget pressure, or publish blockers." }
         ]
+    },
+    {
+        name: "safe_bug_fix",
+        title: "Safe Bug Fix",
+        description: appendPromptMetadata("Plan a small scoped bug fix through doctor, plan, preflight, run, and dossier."),
+        arguments: [
+            { name: "objective", description: "Bug fix objective.", required: true }
+        ]
+    },
+    {
+        name: "write_tests_first",
+        title: "Write Tests First",
+        description: appendPromptMetadata("Constrain the plan around failing tests first, then a small fix."),
+        arguments: [
+            { name: "objective", description: "Objective to satisfy with tests-first discipline.", required: true }
+        ]
+    },
+    {
+        name: "small_refactor",
+        title: "Small Refactor",
+        description: appendPromptMetadata("Keep a refactor small, verifier-backed, and path-scoped."),
+        arguments: [
+            { name: "objective", description: "Refactor objective.", required: true }
+        ]
+    },
+    {
+        name: "security_review",
+        title: "Security Review",
+        description: appendPromptMetadata("Review a risky change with Martin risk, scope, and verifier evidence first."),
+        arguments: [
+            { name: "objective", description: "Security review focus.", required: true }
+        ]
+    },
+    {
+        name: "pr_review",
+        title: "PR Review",
+        description: appendPromptMetadata("Generate a Martin-aware PR review checklist with dossier and eval evidence."),
+        arguments: [
+            { name: "objective", description: "Review objective.", required: true },
+            { name: "loopId", description: "Optional loop identifier to review." }
+        ]
+    },
+    {
+        name: "release_check",
+        title: "Release Check",
+        description: appendPromptMetadata("Run a release-readiness check grounded in Martin evidence."),
+        arguments: [
+            { name: "objective", description: "Release check objective.", required: true },
+            { name: "loopId", description: "Optional loop identifier for concrete evidence." }
+        ]
     }
 ];
 export function listMartinPrompts() {
@@ -141,6 +191,7 @@ export async function getMartinPrompt(input) {
             });
         case "martin_release_check":
         case "martin_publish_readiness_review":
+        case "release_check":
             return buildPublishReadinessPrompt({
                 args,
                 runsDir: context.runsRoot
@@ -161,6 +212,16 @@ export async function getMartinPrompt(input) {
                 args,
                 runsDir: context.runsRoot
             });
+        case "safe_bug_fix":
+            return buildWorkflowPrompt(args, "safe bug fix", "Keep the file scope narrow and verifier-backed.");
+        case "write_tests_first":
+            return buildWorkflowPrompt(args, "tests-first change", "Write or update the targeted verifier before widening the implementation.");
+        case "small_refactor":
+            return buildWorkflowPrompt(args, "small refactor", "Preserve behavior and keep the diff easy to review.");
+        case "security_review":
+            return buildWorkflowPrompt(args, "security-sensitive change", "Escalate if auth, secrets, payments, or infra paths are involved.");
+        case "pr_review":
+            return buildWorkflowPrompt(args, "PR review", "Use martin_dossier and martin_eval before any approval decision.");
         default:
             throw invalidArgumentsError(`Unknown prompt '${input.name}'.`, "Use prompts/list to discover the available Martin prompt names.");
     }
@@ -172,12 +233,24 @@ async function buildKickoffPrompt(input) {
         runsDir: input.runsDir,
         workingDirectory: input.workingDirectory
     });
+    const commandMapGuide = await readMartinResource({
+        uri: MARTIN_STATIC_RESOURCE_URIS.commandMapGuide,
+        runsDir: input.runsDir,
+        workingDirectory: input.workingDirectory
+    });
+    const operatingRulesGuide = await readMartinResource({
+        uri: MARTIN_STATIC_RESOURCE_URIS.operatingRulesGuide,
+        runsDir: input.runsDir,
+        workingDirectory: input.workingDirectory
+    });
     const healthResource = MARTIN_STATIC_RESOURCES.find((resource) => resource.uri === MARTIN_STATIC_RESOURCE_URIS.serverHealth);
     return {
         description: appendPromptMetadata("Kick off a Martin-governed coding session with explicit scope, budgets, and verification expectations."),
         messages: [
-            textMessage("assistant", "You are helping prepare a Martin Loop coding run. Keep the plan governed: validate the environment first, preflight non-trivial work, preserve scope discipline, and make verification requirements explicit."),
+            textMessage("assistant", "You are helping prepare a Martin Loop coding run. Keep the plan governed: validate the environment first, plan before spend, preflight non-trivial work, preserve scope discipline, and make verification requirements explicit. Do not skip Martin commands and do not treat Martin as optional."),
             embeddedResourceMessage("assistant", firstResourceContent(usageGuide)),
+            embeddedResourceMessage("assistant", firstResourceContent(commandMapGuide)),
+            embeddedResourceMessage("assistant", firstResourceContent(operatingRulesGuide)),
             ...(healthResource ? [resourceLinkMessage("assistant", healthResource)] : []),
             textMessage("user", joinSections([
                 "Prepare a Martin Loop kickoff plan and a ready-to-send `martin_preflight` payload for this task.",
@@ -193,6 +266,7 @@ async function buildKickoffPrompt(input) {
                 optionalLine("Workspace ID", input.args["workspaceId"]),
                 optionalLine("Project ID", input.args["projectId"]),
                 "Return:",
+                "- the required Martin command order before actual coding work begins,",
                 "- a concise governed execution plan,",
                 "- the exact `martin_preflight` arguments,",
                 "- the main risks or blockers to resolve before `martin_run`."
@@ -304,6 +378,24 @@ async function buildTriageRunStorePrompt(input) {
         ]
     };
 }
+async function buildWorkflowPrompt(args, label, guardrail) {
+    const objective = requirePromptArgument(args, "objective");
+    return {
+        description: appendPromptMetadata(`Guide an agent through a ${label} with Martin governance.`),
+        messages: [
+            textMessage("assistant", "Use Martin as the command center: doctor first, then plan, preflight, run, dossier, and eval. Do not jump directly to execution."),
+            textMessage("user", joinSections([
+                `Objective: ${objective}`,
+                `Guardrail: ${guardrail}`,
+                "Return:",
+                "- the first Martin tool to call,",
+                "- the proposed file scope,",
+                "- the verifier plan,",
+                "- the conditions that should block or escalate the run."
+            ]))
+        ]
+    };
+}
 async function buildResumePrompt(input) {
     const loopId = input.args["loopId"]?.trim();
     const messages = [

package/dist/resources.d.ts

@@ -3,13 +3,21 @@ export declare const MARTIN_STATIC_RESOURCE_URIS: {
     readonly serverHealth: "martin://server/health";
     readonly recentRuns: "martin://runs/recent";
     readonly triage: "martin://runs/triage";
+    readonly latestRun: "martin://runs/latest";
     readonly latestSummary: "martin://runs/latest/summary";
     readonly latestProofCard: "martin://runs/latest/proof-card";
     readonly latestBudgetStatus: "martin://runs/latest/budget-status";
     readonly latestVerifierEvidence: "martin://runs/latest/verifier-evidence";
     readonly latestRollbackEvidence: "martin://runs/latest/rollback-evidence";
+    readonly currentPolicies: "martin://policies/current";
+    readonly repoRiskMap: "martin://repo/risk-map";
+    readonly verifierResults: "martin://verifiers/results";
     readonly agentNextStep: "martin://agent/next-step";
     readonly mcpUsageGuide: "martin://guides/mcp-usage";
+    readonly agentStartGuide: "martin://guides/agent-start";
+    readonly commandMapGuide: "martin://guides/command-map";
+    readonly ideOnboardingGuide: "martin://guides/ide-onboarding";
+    readonly operatingRulesGuide: "martin://guides/operating-rules";
     readonly publishReadinessGuide: "martin://guides/publish-readiness";
 };
 export declare const MARTIN_RESOURCE_TEMPLATES: ResourceTemplate[];
@@ -18,7 +26,7 @@ export interface MartinReadResourceInput {
     uri: string;
     runsDir?: string;
     workingDirectory?: string;
-    engine?: "claude" | "codex";
+    engine?: "claude" | "codex" | "gemini";
 }
 export declare function listMartinResources(): {
     resources: Resource[];