diff --git a/apps/api/src/modules/activity-registry/__tests__/acceptance-predicate.test.ts b/apps/api/src/modules/activity-registry/__tests__/acceptance-predicate.test.ts
index 6fafd06..ad9facd 100644
--- a/apps/api/src/modules/activity-registry/__tests__/acceptance-predicate.test.ts
+++ b/apps/api/src/modules/activity-registry/__tests__/acceptance-predicate.test.ts
@@ -348,3 +348,116 @@ describe('refersTo 目标要在本活动的声明里 —— 写错的地址会
     expect(found.map((f) => f.code)).toEqual(['reference-target-unbound']);
   });
 });
+
+/**
+ * ── 配方静态审(2026-08-29)──────────────────────────────────────────
+ *
+ * `autoRecipeFindings` 读的是**整份** `ActivityManifest`(不像本文件其余审读只收窄到
+ * 字段级),所以这里不能再用局部的 `manifest()` / `table()` 这类窄类型 helper ——
+ * 借 `activityManifestSchema.parse()` 把六区的默认值一次性填满,只手写真正必填的那几处。
+ */
+import { activityManifestSchema } from '@contracts';
+import { autoRecipeFindings } from '../internal/domain/static-audit.ts';
+
+/** 台账地址与列名全部真实声明过 —— `demo.record` 只有 `case_ref` / `note` 两列 */
+function manifestFixture(): ActivityManifest {
+  return activityManifestSchema.parse({
+    identity: {
+      activityId: 'demo-activity',
+      name: '演示活动',
+      packageVersion: '1.0.0',
+      category: '演示',
+      sdkVersion: '1.0.0',
+      checksum: 'chk',
+    },
+    contract: {
+      activityId: 'demo-activity',
+      version: '1.0.0',
+      input: { data: { type: 'object', properties: {} } },
+      output: {},
+      authorization: { humanCallBudget: 0 },
+      resources: { budget: { steps: 10, tokens: 10000, activeMinutes: 10, humanCalls: 0 } },
+    },
+    declarations: {
+      models: ['m'],
+      ledger: [
+        {
+          domain: 'demo',
+          object: 'record',
+          kind: 'record',
+          caseKey: 'case_ref',
+          label: '演示记录',
+          fields: [
+            { name: 'case_ref', type: 'text', primaryKey: true },
+            { name: 'note', type: 'text' },
+          ],
+        },
+      ],
+      harness: {},
+    },
+    assets: {
+      businessModel: {
+        cmmnXml: '<caseFileItem id="S1" name="x"/>',
+        narrative: '演示说明书',
+        dmn: { drd: [], tables: [] },
+        steps: [],
+      },
+    },
+    samples: [{ name: '样例', input: {}, expect: { ports: ['done'] } }],
+    entry: { file: 'index.js', checksum: 'chk' },
+  });
+}
+
+describe('配方静态审:写错地址 = 每一单都错,装的时候就拒', () => {
+  const withRecipe = (auto: unknown) => {
+    const base = manifestFixture();
+    return {
+      ...base,
+      assets: {
+        ...base.assets,
+        businessModel: {
+          ...base.assets.businessModel,
+          steps: [{ item: 'S1', guide: '', writes: [], reads: [], tools: [], auto }],
+        },
+      },
+    } as never;
+  };
+
+  it('台账地址不在 declarations.ledger 里 → error', () => {
+    const findings = autoRecipeFindings(withRecipe({ do: [{ kind: 'project', into: 'nope.nope', from: { once: true }, fields: { a: 'b' } }] }));
+    expect(findings.some((f) => f.severity === 'error' && f.message.includes('nope.nope'))).toBe(true);
+  });
+
+  it('列名不在该对象的声明里 → error(列名写错 = 那一格永远是空的)', () => {
+    const findings = autoRecipeFindings(
+      withRecipe({ do: [{ kind: 'project', into: 'demo.record', from: { once: true }, fields: { 不存在的列: 'x' } }] }),
+    );
+    expect(findings.some((f) => f.severity === 'error' && f.message.includes('不存在的列'))).toBe(true);
+  });
+
+  it('each / lookup 的地址同样要在声明里', () => {
+    const findings = autoRecipeFindings(
+      withRecipe({ do: [{ kind: 'project', into: 'demo.record', from: { each: 'mine:nope.nope' }, fields: {} }] }),
+    );
+    expect(findings.some((f) => f.message.includes('nope.nope'))).toBe(true);
+  });
+
+  it('in: 与 result: 不是台账地址,不该被当成台账来审', () => {
+    const findings = autoRecipeFindings(
+      withRecipe({ do: [{ kind: 'project', into: 'demo.record', from: { each: 'in:pns' }, fields: {} }] }),
+    );
+    expect(findings).toEqual([]);
+  });
+
+  it('analyze 的出参没人消费 → warning(白烧一次模型调用)', () => {
+    const findings = autoRecipeFindings(
+      withRecipe({ do: [{ kind: 'analyze', model: 'm', into: 'items', instruction: 'x', input: { from: { once: true }, fields: {} }, output: { type: 'object' } }] }),
+    );
+    expect(findings.some((f) => f.severity === 'warn' && f.message.includes('items'))).toBe(true);
+  });
+
+  it('submit 那一笔所在的步没有人工验收清单 → error(系统提交不比模型提交宽松)', () => {
+    const findings = autoRecipeFindings(withRecipe({ do: [{ kind: 'submit', rationale: 'x' }] }));
+    expect(findings.some((f) => f.severity === 'error' && f.message.includes('验收清单'))).toBe(true);
+  });
+});
diff --git a/apps/api/src/modules/activity-registry/internal/domain/static-audit.ts b/apps/api/src/modules/activity-registry/internal/domain/static-audit.ts
index a4cfe3a..c56862d 100644
--- a/apps/api/src/modules/activity-registry/internal/domain/static-audit.ts
+++ b/apps/api/src/modules/activity-registry/internal/domain/static-audit.ts
@@ -376,6 +376,125 @@ export function loopFindings(manifest: ActivityManifest): StaticAuditFinding[] {
   return out;
 }
 
+/**
+ * **配方静态审**(2026-08-29)—— 与 `refersTo` 目标检查同款:**写错地址 = 每一单都错**。
+ *
+ * 代码错是必然的错,模型错是概率的错。必然的错好查 —— 前提是它在装包那一刻就被拦下,
+ * 而不是等到第一单跑起来才现形。
+ */
+export function autoRecipeFindings(manifest: ActivityManifest): StaticAuditFinding[] {
+  const out: StaticAuditFinding[] = [];
+  const ledgers = new Map(
+    manifest.declarations.ledger.map((l) => [`${l.domain}.${l.object}`, new Set(l.fields.map((f) => f.name))]),
+  );
+  const templates = new Set(manifest.assets.viewTemplates.map((t) => t.name));
+
+  /** 台账地址:剥掉 `mine:` 前缀;`in:` / `result:` 不是台账,跳过 */
+  const checkAddress = (raw: string, at: string): void => {
+    if (raw.startsWith('in:') || raw.startsWith('result:')) return;
+    const address = raw.startsWith('mine:') ? raw.slice('mine:'.length) : raw;
+    if (!ledgers.has(address)) {
+      out.push({
+        code: 'schema-invalid',
+        severity: 'error',
+        message: `配方引的台账地址不在声明里:${address}(写的授权面是台账声明)`,
+        at,
+      });
+    }
+  };
+
+  /** 表达式里也可能藏着 lookup 地址,递归找一遍 */
+  const walkExpr = (expr: unknown, at: string): void => {
+    if (typeof expr !== 'object' || expr === null) return;
+    const node = expr as Record<string, unknown>;
+    if (typeof node['lookup'] === 'string') {
+      checkAddress(node['lookup'], at);
+      for (const value of Object.values((node['by'] ?? {}) as Record<string, unknown>)) walkExpr(value, at);
+      if (node['else'] !== undefined) walkExpr(node['else'], at);
+    }
+    if (Array.isArray(node['cat'])) for (const part of node['cat'] as unknown[]) walkExpr(part, at);
+    if (node['fmt'] !== undefined) walkExpr(node['fmt'], at);
+    if (node['then'] !== undefined) walkExpr(node['then'], at);
+    if (typeof node['when'] === 'string' && node['else'] !== undefined) walkExpr(node['else'], at);
+  };
+
+  const walkSource = (source: unknown, at: string): void => {
+    if (typeof source !== 'object' || source === null) return;
+    const node = source as Record<string, unknown>;
+    if (typeof node['each'] === 'string') checkAddress(node['each'], at);
+    for (const value of Object.values((node['where'] ?? {}) as Record<string, unknown>)) walkExpr(value, at);
+    if (typeof node['then'] === 'object' && node['then'] !== null) walkSource(node['then'], at);
+    if (Array.isArray(node['rows'])) {
+      for (const row of node['rows'] as unknown[]) {
+        for (const value of Object.values(row as Record<string, unknown>)) walkExpr(value, at);
+      }
+    }
+  };
+
+  for (const step of manifest.assets.businessModel.steps ?? []) {
+    const recipe = step.auto;
+    if (recipe === undefined) continue;
+    const at = `assets.businessModel.steps[${step.item}].auto`;
+    const consumed = new Set<string>();
+
+    for (const [index, action] of recipe.do.entries()) {
+      const where = `${at}.do[${index}]`;
+      if (action.kind === 'project') {
+        checkAddress(action.into, where);
+        walkSource(action.from, where);
+        const columns = ledgers.get(action.into);
+        for (const [name, expr] of Object.entries(action.fields)) {
+          walkExpr(expr, where);
+          if (columns !== undefined && !columns.has(name)) {
+            out.push({ code: 'schema-invalid', severity: 'error', message: `配方写的列不在 ${action.into} 的声明里:${name}`, at: where });
+          }
+        }
+      }
+      if (action.kind === 'analyze') {
+        walkSource(action.input.from, where);
+        for (const expr of Object.values(action.input.fields)) walkExpr(expr, where);
+        if (!manifest.declarations.models.includes(action.model)) {
+          out.push({ code: 'schema-invalid', severity: 'error', message: `配方用的模型没在 declarations.models 里声明:${action.model}`, at: where });
+        }
+      }
+      if (action.kind === 'card') {
+        for (const address of action.gateLedgers ?? []) checkAddress(address, where);
+        if (action.as === 'decide' && (action.options ?? []).length === 0) {
+          out.push({ code: 'schema-invalid', severity: 'error', message: '决策卡一个选项都没有', at: where });
+        }
+      }
+      if (action.kind === 'submit' && (step.acceptanceChecklist ?? []).length === 0) {
+        out.push({
+          code: 'schema-invalid',
+          severity: 'error',
+          message: 'submit 那一步必须声明人工验收清单(acceptanceChecklist)—— 系统提交不比模型提交宽松',
+          at: where,
+        });
+      }
+      /* 找出 `result:xxx` 被谁消费了 —— analyze 的出参没人用,就是白烧一次模型调用 */
+      const text = JSON.stringify(action);
+      for (const hit of text.matchAll(/"result:([A-Za-z0-9_]+)"/g)) consumed.add(hit[1] ?? '');
+    }
+
+    for (const action of recipe.do) {
+      if (action.kind !== 'analyze') continue;
+      if (!consumed.has(action.into)) {
+        out.push({
+          code: 'schema-invalid',
+          severity: 'warn',
+          message: `analyze 的出参 result:${action.into} 没有任何一笔消费它 —— 白烧一次模型调用`,
+          at,
+        });
+      }
+    }
+
+    if (step.view !== undefined && step.view !== '' && !templates.has(step.view)) {
+      out.push({ code: 'schema-invalid', severity: 'error', message: `剧本引的视图模版不存在:${step.view}`, at });
+    }
+  }
+  return out;
+}
+
 export function staticAudit(manifest: ActivityManifest, external: ExternalChecks): StaticAuditFinding[] {
   const out: StaticAuditFinding[] = [];
 
@@ -425,6 +544,7 @@ export function staticAudit(manifest: ActivityManifest, external: ExternalChecks
   out.push(...ledgerKindFindings(manifest));
   out.push(...acceptanceLevelFindings(manifest));
   out.push(...loopFindings(manifest));
+  out.push(...autoRecipeFindings(manifest));
 
   return out;
 }
diff --git a/packages/contracts/src/__tests__/auto-recipe.test.ts b/packages/contracts/src/__tests__/auto-recipe.test.ts
index 223f135..4d070f7 100644
--- a/packages/contracts/src/__tests__/auto-recipe.test.ts
+++ b/packages/contracts/src/__tests__/auto-recipe.test.ts
@@ -33,3 +33,32 @@ describe('auto 配方契约', () => {
     expect(parsed.success).toBe(false);
   });
 });
+
+import { planStepSchema } from '../manifest.ts';
+
+describe('全 auto 的步可以没有 guide', () => {
+  /* brief 原样缺了 intent(required,非空)—— 缺了它 safeParse 恒失败,前两条测试就都验不到「guide 允不允许空」这件事本身 */
+  const base = { item: 'S1', intent: '这一步交出什么', guide: '', writes: [], reads: [], tools: [] };
+
+  it('声明了 auto 就允许 guide 为空 —— 那一步压根不问模型', () => {
+    const parsed = planStepSchema.safeParse({
+      ...base,
+      auto: { do: [{ kind: 'say', text: '办完了' }] },
+    });
+    expect(parsed.success).toBe(true);
+  });
+
+  it('没有 auto 又不写 guide → 拒 —— 「作者忘了写做法」这个老错照旧要拦', () => {
+    const parsed = planStepSchema.safeParse(base);
+    expect(parsed.success).toBe(false);
+  });
+
+  it('有 auto 但 guide 写了内容 → 照收(半 auto:确定的先做完,剩下的仍问模型)', () => {
+    const parsed = planStepSchema.safeParse({
+      ...base,
+      guide: '把结论写实',
+      auto: { do: [{ kind: 'say', text: 'x' }] },
+    });
+    expect(parsed.success).toBe(true);
+  });
+});
diff --git a/packages/contracts/src/manifest.ts b/packages/contracts/src/manifest.ts
index 16f3fa5..3c368f5 100644
--- a/packages/contracts/src/manifest.ts
+++ b/packages/contracts/src/manifest.ts
@@ -119,7 +119,7 @@ export const planStepSchema = z.object({
   /** 一句话:这一步交出什么 */
   intent: z.string().min(1),
   /** 这一步的做法(从说明书里搬过来的那一段)—— 只在轮到它时进上下文 */
-  guide: z.string().min(1),
+  guide: z.string(),
   /** 这一步可写哪几个台账地址「域.对象」;空 = 这一步不写台账 */
   writes: z.array(z.string()).default([]),
   /**
@@ -200,7 +200,22 @@ export const planStepSchema = z.object({
    * **老活动一个字不用改** —— 不写就是不写,不是缺件。
    */
   auto: autoRecipeSchema.optional(),
-});
+})
+  .superRefine((step, ctx) => {
+    /*
+     * **全 auto 的步没有 guide 是正常形态**(2026-08-29):引擎按 `guide.trim() === ''`
+     * 分「半 auto(确定的先做完,剩下的仍问模型)」与「全 auto(这一步一次都不问模型)」。
+     * 而 `.min(1)` 让后者压根写不出来 —— 四步全 auto 的活动会在装包那一刻被拒。
+     * 非空这条要求仍留给没有 auto 的步:**「作者忘了写做法」是个老错,照旧要拦**。
+     */
+    if (step.auto === undefined && step.guide.trim() === '') {
+      ctx.addIssue({
+        code: 'custom',
+        path: ['guide'],
+        message: '这一步的做法不能为空 —— 只有声明了 auto 配方的步才允许没有 guide',
+      });
+    }
+  });
 export type PlanStep = z.infer<typeof planStepSchema>;
 
 /**