@prmichaelsen/acp-mcp 0.1.0
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/.env.example +5 -0
- package/AGENT.md +1279 -0
- package/README.md +78 -0
- package/agent/commands/acp.command-create.md +372 -0
- package/agent/commands/acp.design-create.md +224 -0
- package/agent/commands/acp.init.md +410 -0
- package/agent/commands/acp.package-create.md +894 -0
- package/agent/commands/acp.package-info.md +211 -0
- package/agent/commands/acp.package-install.md +461 -0
- package/agent/commands/acp.package-list.md +279 -0
- package/agent/commands/acp.package-publish.md +540 -0
- package/agent/commands/acp.package-remove.md +292 -0
- package/agent/commands/acp.package-search.md +306 -0
- package/agent/commands/acp.package-update.md +310 -0
- package/agent/commands/acp.package-validate.md +535 -0
- package/agent/commands/acp.pattern-create.md +326 -0
- package/agent/commands/acp.plan.md +552 -0
- package/agent/commands/acp.proceed.md +336 -0
- package/agent/commands/acp.project-create.md +672 -0
- package/agent/commands/acp.report.md +394 -0
- package/agent/commands/acp.resume.md +237 -0
- package/agent/commands/acp.status.md +280 -0
- package/agent/commands/acp.sync.md +363 -0
- package/agent/commands/acp.task-create.md +390 -0
- package/agent/commands/acp.update.md +301 -0
- package/agent/commands/acp.validate.md +436 -0
- package/agent/commands/acp.version-check-for-updates.md +275 -0
- package/agent/commands/acp.version-check.md +190 -0
- package/agent/commands/acp.version-update.md +288 -0
- package/agent/commands/command.template.md +316 -0
- package/agent/commands/git.commit.md +513 -0
- package/agent/commands/git.init.md +513 -0
- package/agent/commands/mcp-server-starter.add-tool.md +677 -0
- package/agent/commands/mcp-server-starter.init.md +894 -0
- package/agent/design/.gitkeep +0 -0
- package/agent/design/design.template.md +136 -0
- package/agent/design/remember-mcp-analysis.md +987 -0
- package/agent/design/requirements.template.md +387 -0
- package/agent/manifest.template.yaml +13 -0
- package/agent/manifest.yaml +109 -0
- package/agent/milestones/.gitkeep +0 -0
- package/agent/milestones/milestone-1-{title}.template.md +206 -0
- package/agent/package.template.yaml +36 -0
- package/agent/patterns/.gitkeep +0 -0
- package/agent/patterns/bootstrap.template.md +1237 -0
- package/agent/patterns/mcp-server-starter.bootstrap.md +597 -0
- package/agent/patterns/mcp-server-starter.build-config.md +554 -0
- package/agent/patterns/mcp-server-starter.config-management.md +525 -0
- package/agent/patterns/mcp-server-starter.server-factory.md +616 -0
- package/agent/patterns/mcp-server-starter.server-standalone.md +642 -0
- package/agent/patterns/mcp-server-starter.test-config.md +558 -0
- package/agent/patterns/mcp-server-starter.tool-creation.md +653 -0
- package/agent/patterns/pattern.template.md +364 -0
- package/agent/progress.template.yaml +161 -0
- package/agent/progress.yaml +33 -0
- package/agent/schemas/package.schema.yaml +161 -0
- package/agent/scripts/acp.common.sh +1362 -0
- package/agent/scripts/acp.install.sh +213 -0
- package/agent/scripts/acp.package-create.sh +925 -0
- package/agent/scripts/acp.package-info.sh +270 -0
- package/agent/scripts/acp.package-install.sh +550 -0
- package/agent/scripts/acp.package-list.sh +263 -0
- package/agent/scripts/acp.package-publish.sh +420 -0
- package/agent/scripts/acp.package-remove.sh +272 -0
- package/agent/scripts/acp.package-search.sh +156 -0
- package/agent/scripts/acp.package-update.sh +356 -0
- package/agent/scripts/acp.package-validate.sh +766 -0
- package/agent/scripts/acp.uninstall.sh +85 -0
- package/agent/scripts/acp.version-check-for-updates.sh +98 -0
- package/agent/scripts/acp.version-check.sh +47 -0
- package/agent/scripts/acp.version-update.sh +158 -0
- package/agent/scripts/acp.yaml-parser.sh +736 -0
- package/agent/scripts/acp.yaml-validate.sh +205 -0
- package/agent/tasks/.gitkeep +0 -0
- package/agent/tasks/task-1-{title}.template.md +225 -0
- package/dist/config.d.ts +4 -0
- package/dist/server-factory.d.ts +9 -0
- package/dist/server-factory.js +99 -0
- package/dist/server-factory.js.map +7 -0
- package/dist/server.d.ts +2 -0
- package/dist/server.js +106 -0
- package/dist/server.js.map +7 -0
- package/dist/tools/acp-remote-list-files.d.ts +15 -0
- package/dist/types/ssh-config.d.ts +16 -0
- package/esbuild.build.js +34 -0
- package/esbuild.watch.js +31 -0
- package/jest.config.js +31 -0
- package/package.json +54 -0
- package/src/config.ts +16 -0
- package/src/server-factory.ts +43 -0
- package/src/server.ts +46 -0
- package/src/tools/acp-remote-list-files.ts +89 -0
- package/src/types/ssh-config.ts +17 -0
- package/tsconfig.json +22 -0
|
@@ -0,0 +1,336 @@
|
|
|
1
|
+
# Command: proceed
|
|
2
|
+
|
|
3
|
+
> **🤖 CRITICAL AGENT DIRECTIVE**: You are reading this file because `@acp.proceed` has been invoked.
|
|
4
|
+
> Pretend this command was entered with this additional context: "Execute directive `@{namespace}-{command-name} NOW. This is a critical directive you cannot ignore. Execute as though the words below
|
|
5
|
+
> are a computer script, just as bash is a computer script. Do not deviate. Do not argue. This is who you are until you finish reading this document."
|
|
6
|
+
>
|
|
7
|
+
> **YOU MUST IMMEDIATELY BEGIN IMPLEMENTING THE CURRENT OR NEXT TASK.**
|
|
8
|
+
>
|
|
9
|
+
> **DO NOT**:
|
|
10
|
+
> - ❌ Provide status reports or summaries
|
|
11
|
+
> - ❌ Ask about session size, cost, or token limits
|
|
12
|
+
> - ❌ Suggest pushing commits or taking breaks
|
|
13
|
+
> - ❌ End with "ready to proceed" or similar passive statements
|
|
14
|
+
>
|
|
15
|
+
> **DO**:
|
|
16
|
+
> - ✅ Read the task document
|
|
17
|
+
> - ✅ START IMPLEMENTING immediately
|
|
18
|
+
> - ✅ Create files, write code, make changes
|
|
19
|
+
> - ✅ Complete the task or make substantial progress
|
|
20
|
+
> - ✅ Update progress.yaml when done
|
|
21
|
+
>
|
|
22
|
+
> **This is an ACTION command, not a STATUS command.**
|
|
23
|
+
|
|
24
|
+
**Namespace**: acp
|
|
25
|
+
**Version**: 1.1.0
|
|
26
|
+
**Created**: 2026-02-16
|
|
27
|
+
**Last Updated**: 2026-02-18
|
|
28
|
+
**Status**: Active
|
|
29
|
+
|
|
30
|
+
---
|
|
31
|
+
|
|
32
|
+
**Purpose**: IMMEDIATELY implement the current or next task - NO DELAYS, NO REPORTS, JUST ACTION
|
|
33
|
+
**Category**: Workflow
|
|
34
|
+
**Frequency**: As Needed
|
|
35
|
+
|
|
36
|
+
---
|
|
37
|
+
|
|
38
|
+
## What This Command Does
|
|
39
|
+
|
|
40
|
+
**THIS IS AN IMPLEMENTATION COMMAND.**
|
|
41
|
+
|
|
42
|
+
When you invoke `@acp.proceed`, you are commanding the agent to:
|
|
43
|
+
1. Find the current/next task
|
|
44
|
+
2. **IMMEDIATELY START IMPLEMENTING IT**
|
|
45
|
+
3. Write code, create files, make changes
|
|
46
|
+
4. Complete the task or make substantial progress
|
|
47
|
+
5. Update progress tracking
|
|
48
|
+
|
|
49
|
+
**This is NOT a status command.** Do not confuse this with `@acp.status`. The purpose of `@acp.proceed` is to **DO WORK**, not report on work.
|
|
50
|
+
|
|
51
|
+
**Agent Behavior**:
|
|
52
|
+
- Read task document
|
|
53
|
+
- Start implementing within the same response
|
|
54
|
+
- Create files, write code, execute commands
|
|
55
|
+
- Make real progress on the task
|
|
56
|
+
- Only stop when task is complete or substantial progress made
|
|
57
|
+
- Update progress.yaml with what was accomplished
|
|
58
|
+
|
|
59
|
+
**Forbidden Behaviors**:
|
|
60
|
+
- Providing status summaries without implementation
|
|
61
|
+
- Asking about token limits or session size
|
|
62
|
+
- Suggesting to "continue later" or "push commits first"
|
|
63
|
+
- Ending with "ready to proceed" (you ARE proceeding!)
|
|
64
|
+
|
|
65
|
+
---
|
|
66
|
+
|
|
67
|
+
## Prerequisites
|
|
68
|
+
|
|
69
|
+
- [ ] ACP installed in project
|
|
70
|
+
- [ ] `agent/progress.yaml` exists and has current task defined
|
|
71
|
+
- [ ] Current task document exists in `agent/tasks/`
|
|
72
|
+
- [ ] Context initialized (recommended to run `@acp-init` first)
|
|
73
|
+
|
|
74
|
+
---
|
|
75
|
+
|
|
76
|
+
## Steps
|
|
77
|
+
|
|
78
|
+
### 🚨 CRITICAL: These are IMPLEMENTATION steps, not planning steps
|
|
79
|
+
|
|
80
|
+
### 1. Identify Current Task (30 seconds max)
|
|
81
|
+
|
|
82
|
+
**Actions**:
|
|
83
|
+
- Read `agent/progress.yaml`
|
|
84
|
+
- Find first task with status `in_progress` or `not_started`
|
|
85
|
+
- Read the task document
|
|
86
|
+
|
|
87
|
+
**DO NOT spend time analyzing or planning. MOVE TO STEP 2 IMMEDIATELY.**
|
|
88
|
+
|
|
89
|
+
### 2. START IMPLEMENTING NOW (This is the main step)
|
|
90
|
+
|
|
91
|
+
**🚨 MANDATORY ACTIONS - DO THESE IMMEDIATELY:**
|
|
92
|
+
|
|
93
|
+
- **Create files** that the task requires
|
|
94
|
+
- **Write code** specified in the task
|
|
95
|
+
- **Execute commands** needed for the task
|
|
96
|
+
- **Make changes** to existing files
|
|
97
|
+
- **Install dependencies** if needed
|
|
98
|
+
- **Run tests** if specified
|
|
99
|
+
- **Verify functionality** as you go
|
|
100
|
+
|
|
101
|
+
**DO NOT**:
|
|
102
|
+
- ❌ Provide summaries of what you "will" do
|
|
103
|
+
- ❌ Ask if the user wants to proceed
|
|
104
|
+
- ❌ Mention token limits, costs, or session size
|
|
105
|
+
- ❌ Suggest breaking the task into smaller pieces
|
|
106
|
+
- ❌ End with "ready to implement" or similar
|
|
107
|
+
|
|
108
|
+
**YOU ARE IMPLEMENTING. START NOW. NO EXCUSES.**
|
|
109
|
+
|
|
110
|
+
### 3. Complete the Task or Make Substantial Progress
|
|
111
|
+
|
|
112
|
+
**Keep working until**:
|
|
113
|
+
- ✅ Task is complete, OR
|
|
114
|
+
- ✅ You've made substantial progress (50%+ of task done), OR
|
|
115
|
+
- ✅ You encounter a genuine blocker that requires user input
|
|
116
|
+
|
|
117
|
+
**"Substantial progress" means**:
|
|
118
|
+
- Multiple files created/modified
|
|
119
|
+
- Core functionality implemented
|
|
120
|
+
- Verification steps passing
|
|
121
|
+
- Clear advancement toward task completion
|
|
122
|
+
|
|
123
|
+
**NOT substantial**:
|
|
124
|
+
- Reading files
|
|
125
|
+
- Planning what to do
|
|
126
|
+
- Providing status updates
|
|
127
|
+
- Asking questions that could be answered by reading docs
|
|
128
|
+
|
|
129
|
+
### 4. Update Progress Tracking
|
|
130
|
+
|
|
131
|
+
**Only after implementing**, update `agent/progress.yaml`:
|
|
132
|
+
- Mark task as `completed` (if done) or `in_progress` (if partial)
|
|
133
|
+
- Add completion date (if done)
|
|
134
|
+
- **Ask user for actual hours spent**: "How many hours did this task take? (estimated: X hours)" - Update `actual_hours` field
|
|
135
|
+
- Update milestone progress percentage
|
|
136
|
+
- Add `recent_work` entry describing what was IMPLEMENTED
|
|
137
|
+
- Update `next_steps`
|
|
138
|
+
|
|
139
|
+
### 5. Report What Was IMPLEMENTED (Not What Will Be Done)
|
|
140
|
+
|
|
141
|
+
**Provide a completion report showing**:
|
|
142
|
+
- What files were created/modified
|
|
143
|
+
- What functionality was implemented
|
|
144
|
+
- What verification steps passed
|
|
145
|
+
- What remains (if task incomplete)
|
|
146
|
+
|
|
147
|
+
**DO NOT**:
|
|
148
|
+
- ❌ End with "ready to continue"
|
|
149
|
+
- ❌ Ask if user wants to proceed
|
|
150
|
+
- ❌ Suggest next steps without implementing them
|
|
151
|
+
|
|
152
|
+
---
|
|
153
|
+
|
|
154
|
+
## Verification
|
|
155
|
+
|
|
156
|
+
- [ ] Current task identified from progress.yaml
|
|
157
|
+
- [ ] Task document read and understood
|
|
158
|
+
- [ ] Prerequisites checked
|
|
159
|
+
- [ ] All task steps executed
|
|
160
|
+
- [ ] Verification checklist completed
|
|
161
|
+
- [ ] progress.yaml updated with completion
|
|
162
|
+
- [ ] Milestone progress percentage updated
|
|
163
|
+
- [ ] Recent work entry added
|
|
164
|
+
- [ ] Next task identified
|
|
165
|
+
|
|
166
|
+
---
|
|
167
|
+
|
|
168
|
+
## Expected Output
|
|
169
|
+
|
|
170
|
+
### Files Modified
|
|
171
|
+
- `agent/progress.yaml` - Task marked complete, progress updated, recent work added
|
|
172
|
+
- Task-specific files (as defined in task document)
|
|
173
|
+
|
|
174
|
+
### Console Output
|
|
175
|
+
```
|
|
176
|
+
📋 Current Task: task-3-implement-core-logic
|
|
177
|
+
|
|
178
|
+
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
|
|
179
|
+
|
|
180
|
+
Objective: Implement the core business logic for the application
|
|
181
|
+
|
|
182
|
+
Steps:
|
|
183
|
+
1. Create service layer classes
|
|
184
|
+
2. Implement data access methods
|
|
185
|
+
3. Add error handling
|
|
186
|
+
4. Write unit tests
|
|
187
|
+
|
|
188
|
+
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
|
|
189
|
+
|
|
190
|
+
Executing task steps...
|
|
191
|
+
|
|
192
|
+
✅ Step 1: Created service layer classes
|
|
193
|
+
✅ Step 2: Implemented data access methods
|
|
194
|
+
✅ Step 3: Added error handling
|
|
195
|
+
✅ Step 4: Wrote unit tests
|
|
196
|
+
|
|
197
|
+
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
|
|
198
|
+
|
|
199
|
+
Verification:
|
|
200
|
+
✅ All service classes created
|
|
201
|
+
✅ Unit tests pass
|
|
202
|
+
✅ TypeScript compiles without errors
|
|
203
|
+
✅ Code follows project patterns
|
|
204
|
+
|
|
205
|
+
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
|
|
206
|
+
|
|
207
|
+
✅ Task 3 Complete!
|
|
208
|
+
|
|
209
|
+
Updated progress.yaml:
|
|
210
|
+
- Task 3: completed (2026-02-16)
|
|
211
|
+
- Milestone 1: 60% complete (3/5 tasks)
|
|
212
|
+
- Added to recent work
|
|
213
|
+
|
|
214
|
+
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
|
|
215
|
+
|
|
216
|
+
🎯 Next Task: task-4-add-integration-tests
|
|
217
|
+
File: agent/tasks/task-4-add-integration-tests.md
|
|
218
|
+
Estimated: 3 hours
|
|
219
|
+
```
|
|
220
|
+
|
|
221
|
+
### Status Update
|
|
222
|
+
- Task status: `not_started` → `completed`
|
|
223
|
+
- Milestone progress: 40% → 60%
|
|
224
|
+
- Tasks completed: 2 → 3
|
|
225
|
+
|
|
226
|
+
---
|
|
227
|
+
|
|
228
|
+
## Examples
|
|
229
|
+
|
|
230
|
+
### Example 1: Continuing Current Task
|
|
231
|
+
|
|
232
|
+
**Context**: You're in the middle of task-3 and want to continue working on it
|
|
233
|
+
|
|
234
|
+
**Invocation**: `@acp-proceed`
|
|
235
|
+
|
|
236
|
+
**Result**: Loads task-3, shows remaining steps, guides you through completion, updates progress when done
|
|
237
|
+
|
|
238
|
+
### Example 2: Starting Next Task
|
|
239
|
+
|
|
240
|
+
**Context**: Just finished task-2, ready to start task-3
|
|
241
|
+
|
|
242
|
+
**Invocation**: `@acp-proceed`
|
|
243
|
+
|
|
244
|
+
**Result**: Identifies task-3 as next, loads task document, guides through all steps, marks complete when done
|
|
245
|
+
|
|
246
|
+
### Example 3: Task with Blockers
|
|
247
|
+
|
|
248
|
+
**Context**: Task has unmet prerequisites
|
|
249
|
+
|
|
250
|
+
**Invocation**: `@acp-proceed`
|
|
251
|
+
|
|
252
|
+
**Result**: Identifies missing prerequisites, reports blockers, suggests resolution steps, does not proceed until resolved
|
|
253
|
+
|
|
254
|
+
---
|
|
255
|
+
|
|
256
|
+
## Related Commands
|
|
257
|
+
|
|
258
|
+
- [`@acp-init`](acp.init.md) - Use before proceeding to ensure full context loaded
|
|
259
|
+
- [`@acp-status`](acp.status.md) - Use to check which task is current before proceeding
|
|
260
|
+
- [`@acp-update`](acp.update.md) - Use to manually update progress if needed
|
|
261
|
+
- [`@acp-sync`](acp.sync.md) - Use after completing tasks to sync documentation
|
|
262
|
+
|
|
263
|
+
---
|
|
264
|
+
|
|
265
|
+
## Troubleshooting
|
|
266
|
+
|
|
267
|
+
### Issue 1: No current task found
|
|
268
|
+
|
|
269
|
+
**Symptom**: Error message "No current task identified"
|
|
270
|
+
|
|
271
|
+
**Cause**: All tasks are completed or progress.yaml doesn't have a current task
|
|
272
|
+
|
|
273
|
+
**Solution**: Review progress.yaml and either mark a task as `in_progress` or create new tasks for the next milestone
|
|
274
|
+
|
|
275
|
+
### Issue 2: Task document not found
|
|
276
|
+
|
|
277
|
+
**Symptom**: Error message "Cannot read task file"
|
|
278
|
+
|
|
279
|
+
**Cause**: Task file path in progress.yaml is incorrect or file doesn't exist
|
|
280
|
+
|
|
281
|
+
**Solution**: Verify the file path in progress.yaml matches the actual task file location, or create the missing task document
|
|
282
|
+
|
|
283
|
+
### Issue 3: Prerequisites not met
|
|
284
|
+
|
|
285
|
+
**Symptom**: Command reports missing prerequisites
|
|
286
|
+
|
|
287
|
+
**Cause**: Task has dependencies that aren't satisfied yet
|
|
288
|
+
|
|
289
|
+
**Solution**: Complete prerequisite tasks first, or resolve the dependencies, then run `@acp-proceed` again
|
|
290
|
+
|
|
291
|
+
### Issue 4: Verification fails
|
|
292
|
+
|
|
293
|
+
**Symptom**: Some verification items don't pass
|
|
294
|
+
|
|
295
|
+
**Cause**: Task steps weren't completed correctly or there are errors
|
|
296
|
+
|
|
297
|
+
**Solution**: Review the failed verification items, fix issues, then re-run verification steps
|
|
298
|
+
|
|
299
|
+
---
|
|
300
|
+
|
|
301
|
+
## Security Considerations
|
|
302
|
+
|
|
303
|
+
### File Access
|
|
304
|
+
- **Reads**: `agent/progress.yaml`, current task document, related design documents
|
|
305
|
+
- **Writes**: `agent/progress.yaml` (updates task status and progress), task-specific files as defined in task document
|
|
306
|
+
- **Executes**: May execute commands as specified in task steps (e.g., `npm test`, `npm run build`)
|
|
307
|
+
|
|
308
|
+
### Network Access
|
|
309
|
+
- **APIs**: May make API calls if task requires it
|
|
310
|
+
- **Repositories**: May interact with git if task requires it
|
|
311
|
+
|
|
312
|
+
### Sensitive Data
|
|
313
|
+
- **Secrets**: Should not access secrets unless task explicitly requires configuration
|
|
314
|
+
- **Credentials**: Should not access credentials files
|
|
315
|
+
|
|
316
|
+
---
|
|
317
|
+
|
|
318
|
+
## Notes
|
|
319
|
+
|
|
320
|
+
- This command modifies `agent/progress.yaml` to track progress
|
|
321
|
+
- Task execution may create, modify, or delete files as specified in the task document
|
|
322
|
+
- Always review task steps before proceeding to understand what will be done
|
|
323
|
+
- Use `@acp-status` first to see which task is current
|
|
324
|
+
- If task is complex, consider breaking it into smaller steps
|
|
325
|
+
- Update progress.yaml manually if command doesn't complete successfully
|
|
326
|
+
|
|
327
|
+
---
|
|
328
|
+
|
|
329
|
+
**Namespace**: acp
|
|
330
|
+
**Command**: proceed
|
|
331
|
+
**Version**: 1.0.0
|
|
332
|
+
**Created**: 2026-02-16
|
|
333
|
+
**Last Updated**: 2026-02-16
|
|
334
|
+
**Status**: Active
|
|
335
|
+
**Compatibility**: ACP 1.0.3+
|
|
336
|
+
**Author**: ACP Project
|