god-prompt-mcp 1.2.0 → 1.2.1

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
package/README.md CHANGED
@@ -38,7 +38,7 @@ To buy the review, use the [US$49 one-time GitHub Sponsors tier](https://github.
38
38
 
39
39
  > **Version 1.1.1:** `create_work_contract` and `review_work_evidence` expand the seven original MCP tools to nine. Older hosted or version-pinned installations may still expose only the original seven until separately updated. Both tools remain stateless and read-only, and neither independently authenticates caller-supplied evidence. See the [task-contract workflow and security limitations](docs/task-contracts.md).
40
40
 
41
- **Version 1.2.0:** Eight additional read-only engineering-quality tools expand the public MCP surface from nine to seventeen. The Codexify checkpoint remains an optional **stdio-only** eighteenth tool. Install a versioned MCP package or inspect the hosted `tools/list` response to determine which functions your client actually receives. None of the tools independently execute tests, inspect external repositories or authorize deployment. See the [toolkit QA and limitations](docs/qa/godprompt-public-toolkit-20261120.md). The OpenAI marketplace distribution remains a separate, Skill-only integration until its eventual dedicated upgrade.
41
+ **Version 1.2.1:** All seventeen public MCP tools are available, including the eight engineering-quality functions introduced in v1.2.0. This patch refines code-review signal precision, requirement-conflict detection and duplicate CI-check blocking without adding permissions or storage. The Codexify checkpoint remains an optional **stdio-only** eighteenth tool. Install a versioned MCP package or inspect the hosted `tools/list` response to determine which functions your client actually receives. None of the tools independently execute tests, inspect external repositories or authorize deployment. See the [toolkit QA and limitations](docs/qa/godprompt-public-toolkit-20261120.md). The OpenAI marketplace distribution remains a separate, Skill-only integration until its eventual dedicated upgrade.
42
42
 
43
43
  ### Optional local proof bridge (from v1.1.1)
44
44
 
@@ -299,7 +299,7 @@ npx -y skills@latest add AKzar1el/god-prompt-mcp --skill god-prompt --agent droi
299
299
  Droid discovers compatible project skills under `.agents/skills/`. To add the callable GodPrompt tools as a local stdio MCP server, use Droid's native MCP command with the published version pinned:
300
300
 
301
301
  ```bash
302
- droid mcp add god-prompt "npx -y god-prompt-mcp@1.2.0"
302
+ droid mcp add god-prompt "npx -y god-prompt-mcp@1.2.1"
303
303
  ```
304
304
 
305
305
  Open `/mcp` in Droid to verify the server and available tools. The Agent Skill supplies the reusable workflow while MCP exposes GodPrompt's read-only task and protocol tools. Node.js 22+ is required for the MCP server.
@@ -312,7 +312,7 @@ Warp can use GodPrompt as both an Agent Skill and a local MCP server. Install th
312
312
  npx -y skills@latest add AKzar1el/god-prompt-mcp --skill god-prompt --agent warp --copy -y
313
313
  ```
314
314
 
315
- Warp discovers project skills from `.agents/skills/` and `.warp/skills/`. For MCP tools, add a CLI-based MCP server in Warp with command `npx` and arguments `-y`, `god-prompt-mcp`; Warp's Oz CLI can also receive MCP configuration through `oz agent run --mcp`. The skill supplies the reusable workflow while MCP exposes GodPrompt's seventeen public tools in v1.2.0. Node.js 22+ is required for the MCP server.
315
+ Warp discovers project skills from `.agents/skills/` and `.warp/skills/`. For MCP tools, add a CLI-based MCP server in Warp with command `npx` and arguments `-y`, `god-prompt-mcp`; Warp's Oz CLI can also receive MCP configuration through `oz agent run --mcp`. The skill supplies the reusable workflow while MCP exposes GodPrompt's seventeen public tools in v1.2.1. Node.js 22+ is required for the MCP server.
316
316
 
317
317
  ### Goose
318
318
 
@@ -325,10 +325,10 @@ npx -y skills@latest add AKzar1el/god-prompt-mcp --skill god-prompt --agent goos
325
325
  Goose discovers the copied skill under `.goose/skills/god-prompt/`. To expose GodPrompt's callable tools for a session, start Goose with the published MCP package as an external stdio extension:
326
326
 
327
327
  ```bash
328
- goose session --with-extension "npx -y god-prompt-mcp@1.2.0"
328
+ goose session --with-extension "npx -y god-prompt-mcp@1.2.1"
329
329
  ```
330
330
 
331
- Goose currently treats Agent Skills and MCP extensions as separate native surfaces, so this path does not depend on Agent Plugins support. The skill supplies the reusable workflow while MCP exposes GodPrompt's seventeen public tools in v1.2.0. Node.js 22+ is required for the MCP server.
331
+ Goose currently treats Agent Skills and MCP extensions as separate native surfaces, so this path does not depend on Agent Plugins support. The skill supplies the reusable workflow while MCP exposes GodPrompt's seventeen public tools in v1.2.1. Node.js 22+ is required for the MCP server.
332
332
 
333
333
  ### Zed
334
334
 
@@ -390,13 +390,13 @@ The Trae target installs the skill under `.trae/skills/god-prompt/`, where TraeC
390
390
  "mcpServers": {
391
391
  "god-prompt": {
392
392
  "command": "npx",
393
- "args": ["-y", "god-prompt-mcp@1.2.0"]
393
+ "args": ["-y", "god-prompt-mcp@1.2.1"]
394
394
  }
395
395
  }
396
396
  }
397
397
  ```
398
398
 
399
- TraeCode also supports the portable `.agents/skills/` convention when **Enable .agents Skills Directory** is turned on in its import settings. Treat project MCP configuration as executable workspace configuration and enable it only in repositories you trust. The Agent Skill supplies the reusable workflow while MCP exposes GodPrompt's seventeen public tools in v1.2.0. Node.js 22+ is required for the MCP server.
399
+ TraeCode also supports the portable `.agents/skills/` convention when **Enable .agents Skills Directory** is turned on in its import settings. Treat project MCP configuration as executable workspace configuration and enable it only in repositories you trust. The Agent Skill supplies the reusable workflow while MCP exposes GodPrompt's seventeen public tools in v1.2.1. Node.js 22+ is required for the MCP server.
400
400
 
401
401
  ### OpenClaw
402
402
 
@@ -409,11 +409,11 @@ npx -y skills@latest add AKzar1el/god-prompt-mcp --skill god-prompt --agent open
409
409
  The copied skill lands under `.agents/skills/god-prompt/`, one of OpenClaw's documented project skill roots. To expose GodPrompt's callable tools to OpenClaw-managed agent runtimes as well, register the published stdio server:
410
410
 
411
411
  ```bash
412
- openclaw mcp add god-prompt --command npx --arg -y --arg god-prompt-mcp@1.2.0
412
+ openclaw mcp add god-prompt --command npx --arg -y --arg god-prompt-mcp@1.2.1
413
413
  openclaw mcp probe god-prompt
414
414
  ```
415
415
 
416
- `mcp probe` opens a live MCP connection and reports the discovered capabilities, making it a direct verification step after registration. The Agent Skill supplies the reusable workflow while MCP exposes GodPrompt's seventeen public tools in v1.2.0. Node.js 22+ is required for the MCP server.
416
+ `mcp probe` opens a live MCP connection and reports the discovered capabilities, making it a direct verification step after registration. The Agent Skill supplies the reusable workflow while MCP exposes GodPrompt's seventeen public tools in v1.2.1. Node.js 22+ is required for the MCP server.
417
417
 
418
418
  ### Qoder
419
419
 
@@ -430,13 +430,13 @@ The Qoder target installs the skill under `.qoder/skills/god-prompt/`, where Qod
430
430
  "mcpServers": {
431
431
  "god-prompt": {
432
432
  "command": "npx",
433
- "args": ["-y", "god-prompt-mcp@1.2.0"]
433
+ "args": ["-y", "god-prompt-mcp@1.2.1"]
434
434
  }
435
435
  }
436
436
  }
437
437
  ```
438
438
 
439
- Qoder requires approval before using project-level MCP servers by default. After adding or changing the server, start a new session or run `/mcp reload`, then use `/mcp` to verify the connection. The Agent Skill supplies the reusable workflow while MCP exposes GodPrompt's seventeen public tools in v1.2.0. Node.js 22+ is required for the MCP server.
439
+ Qoder requires approval before using project-level MCP servers by default. After adding or changing the server, start a new session or run `/mcp reload`, then use `/mcp` to verify the connection. The Agent Skill supplies the reusable workflow while MCP exposes GodPrompt's seventeen public tools in v1.2.1. Node.js 22+ is required for the MCP server.
440
440
 
441
441
  ### Qwen Code
442
442
 
@@ -459,7 +459,7 @@ This installs GodPrompt under `.qwen/skills/god-prompt/`, where Qwen Code can di
459
459
  }
460
460
  ```
461
461
 
462
- Restart Qwen Code after changing MCP configuration, then open `/mcp` to verify the server. The Agent Skill provides the reusable workflow while MCP exposes GodPrompt's seventeen public tools in v1.2.0. Node.js 22+ is required for the MCP server.
462
+ Restart Qwen Code after changing MCP configuration, then open `/mcp` to verify the server. The Agent Skill provides the reusable workflow while MCP exposes GodPrompt's seventeen public tools in v1.2.1. Node.js 22+ is required for the MCP server.
463
463
 
464
464
  ### Kimi Code
465
465
 
@@ -470,7 +470,7 @@ Kimi Code CLI can install GodPrompt as one native custom plugin containing the e
470
470
  /reload
471
471
  ```
472
472
 
473
- The Kimi manifest points at `skills/`, so the `god-prompt` skill remains available through Kimi's normal relevance-based skill loading instead of being forced into every session. The same manifest exposes `god-prompt-mcp@1.2.0` as a local stdio MCP server, including the seventeen public tools available in v1.2.0. The explicit `tree/main` URL matters because Kimi's bare GitHub-repository install form prefers the latest GitHub release; using `main` makes the current plugin manifest available without forcing a documentation-only npm/MCP Registry release. Node.js 22+ is required for the MCP server.
473
+ The Kimi manifest points at `skills/`, so the `god-prompt` skill remains available through Kimi's normal relevance-based skill loading instead of being forced into every session. The same manifest exposes `god-prompt-mcp@1.2.1` as a local stdio MCP server, including the seventeen public tools available in v1.2.0. The explicit `tree/main` URL matters because Kimi's bare GitHub-repository install form prefers the latest GitHub release; using `main` makes the current plugin manifest available without forcing a documentation-only npm/MCP Registry release. Node.js 22+ is required for the MCP server.
474
474
 
475
475
  ### JetBrains AI Assistant
476
476
 
@@ -508,7 +508,7 @@ If you only want the portable skill, place the complete skill directory at `.age
508
508
  devin mcp add god-prompt -- npx -y god-prompt-mcp
509
509
  ```
510
510
 
511
- Run `devin mcp list` to verify the direct server registration. The Agent Skill provides the reusable workflow while MCP exposes GodPrompt's seventeen public tools in v1.2.0. Node.js 22+ is required for the MCP server.
511
+ Run `devin mcp list` to verify the direct server registration. The Agent Skill provides the reusable workflow while MCP exposes GodPrompt's seventeen public tools in v1.2.1. Node.js 22+ is required for the MCP server.
512
512
 
513
513
  ### Cursor
514
514
 
@@ -48,7 +48,15 @@ export function diagnoseFailure(symptoms, logs = "") {
48
48
  }
49
49
  export function assessReleaseReadiness(input) {
50
50
  const blockers = [];
51
+ const seenChecks = new Set();
51
52
  for (const check of input.checks) {
53
+ const name = check.name.trim().toLowerCase();
54
+ if (seenChecks.has(name))
55
+ blockers.push({
56
+ code: "DUPLICATE_CHECK_NAME",
57
+ message: "Repeated check names do not count as independent verification evidence.",
58
+ });
59
+ seenChecks.add(name);
52
60
  if (check.status !== "passed")
53
61
  blockers.push({
54
62
  code: check.status === "failed" ? "FAILED_CHECK" : "UNRUN_CHECK",
@@ -115,8 +115,19 @@ export function reviewCodeChange(diff) {
115
115
  reviewedLines++;
116
116
  if (findings.length >= MAX_FINDINGS)
117
117
  continue;
118
+ const added = change.content.slice(1).trimStart();
119
+ const commentOnly = /^(?:\/\/|\/\*|\*|#|<!--)/.test(added);
120
+ if (/^\.github\/workflows\/(?:publish|release|deploy)[^/]*\.ya?ml$/i.test(path)
121
+ && /github\.event_name\s*!=\s*[\x27\x22]pull_request[\x27\x22]/i.test(added)) {
122
+ findings.push({ code: "WEAKENED_RELEASE_GATE", severity: "high",
123
+ message: "A release workflow gate appears broadened beyond manual dispatch; inspect publication permissions and intended triggers.",
124
+ file: path, line: change.ln });
125
+ continue;
126
+ }
118
127
  for (const signal of PATCH_SIGNALS) {
119
- if (signal.matcher.test(change.content.slice(1))) {
128
+ if (commentOnly && signal.code !== "UNFINISHED_MARKER")
129
+ continue;
130
+ if (signal.matcher.test(added)) {
120
131
  findings.push({ code: signal.code, severity: signal.severity, message: signal.message, file: path, line: change.ln });
121
132
  break;
122
133
  }
@@ -128,7 +139,7 @@ export function reviewCodeChange(diff) {
128
139
  if (changeOverflow)
129
140
  break;
130
141
  }
131
- if (productionPatch && !testPatch && findings.length < MAX_FINDINGS) {
142
+ if (productionPatch && !testPatch && changedLines > 1 && findings.length < MAX_FINDINGS) {
132
143
  findings.push({
133
144
  code: "NO_TEST_CHANGES_IN_PATCH",
134
145
  severity: "low",
@@ -219,6 +230,7 @@ export function auditRequirements(specification) {
219
230
  const { requirements, truncated } = normalizeRequirements(specification);
220
231
  const findings = [];
221
232
  const exact = new Map();
233
+ const quantified = new Map();
222
234
  for (const req of requirements) {
223
235
  const key = req.text.replace(/\s+/g, " ").toLowerCase();
224
236
  const prior = exact.get(key);
@@ -226,6 +238,19 @@ export function auditRequirements(specification) {
226
238
  findings.push({ code: "DUPLICATE_REQUIREMENT", severity: "medium", message: `Same text also appears in ${prior}.`, requirement_id: req.id });
227
239
  else
228
240
  exact.set(key, req.id);
241
+ const quantifiedClause = /^(every|all|no)\s+(.+)$/i.exec(key.replace(/[.!?]+$/, ""));
242
+ if (quantifiedClause) {
243
+ const polarity = quantifiedClause[1] === "no" ? -1 : 1;
244
+ const previous = quantified.get(quantifiedClause[2]);
245
+ if (previous && previous.polarity !== polarity)
246
+ findings.push({
247
+ code: "CONTRADICTORY_REQUIREMENTS", severity: "medium",
248
+ message: "Obvious universal-versus-none obligations conflict with " + previous.id + "; clarify which behavior applies.",
249
+ requirement_id: req.id,
250
+ });
251
+ else if (!previous)
252
+ quantified.set(quantifiedClause[2], { polarity, id: req.id });
253
+ }
229
254
  if (!req.acceptance.length && !req.scenarios.length)
230
255
  findings.push({
231
256
  code: "MISSING_ACCEPTANCE_EVIDENCE",
@@ -240,7 +265,7 @@ export function auditRequirements(specification) {
240
265
  message: "Qualitative language needs a concrete, observable acceptance threshold.",
241
266
  requirement_id: req.id,
242
267
  });
243
- if (/\b(?:shall|must|should)\b/i.test(req.text) && /\b(?:may|maybe|optional|if possible)\b/i.test(req.text))
268
+ if (/\b(?:shall|must|should)\b/i.test(req.text) && /\b(?:may|maybe|optional|optionally|if possible)\b/i.test(req.text))
244
269
  findings.push({
245
270
  code: "MIXED_OBLIGATION",
246
271
  severity: "low",
package/dist/server.js CHANGED
@@ -3,7 +3,7 @@ import { CONTENT, VERSION } from "./content.js";
3
3
  import { CORE_SKILL } from "./skill-content.js";
4
4
  export const SERVER_INFO = {
5
5
  name: "god-prompt-mcp",
6
- version: "1.2.0",
6
+ version: "1.2.1",
7
7
  };
8
8
  export const SERVER_INSTRUCTIONS = "For scoped engineering tasks, use classify_task to route the work and get_tailored_guidance to load only the needed phase. Use get_core_skill if the entire core protocol is needed, not on every request. Use review_code_change, audit_requirements and build_test_matrix for bounded caller-supplied evidence and draft test planning. Use diagnose_failure, assess_release_readiness, create_context_handoff and compare_evaluation_runs only for their respective supplied-evidence workflows. None of these tools run external checks, authenticate evidence, authorize release or independently verify work. Load get_protocols, get_gates, or get_anti_patterns only when focused guidance is insufficient. Use get_god_prompt only when the full single-file payload is preferable; request bounded start/maxChars chunks if an MCP bridge truncates large responses. All GodPrompt tools are read-only.";
9
9
  const READ_ONLY_ANNOTATIONS = {
package/package.json CHANGED
@@ -1,6 +1,6 @@
1
1
  {
2
2
  "name": "god-prompt-mcp",
3
- "version": "1.2.0",
3
+ "version": "1.2.1",
4
4
  "mcpName": "io.github.AKzar1el/god-prompt-mcp",
5
5
  "description": "GodPrompt MCP server + portable Agent Skill for coding agents — TDD, debugging, verification gates, task routing, and progressive disclosure.",
6
6
  "private": false,