ptbk 0.112.0-121 → 0.112.0-124

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.
Files changed (2) hide show
  1. package/README.md +14 -14
  2. package/package.json +3 -3
package/README.md CHANGED
@@ -396,7 +396,7 @@ Prompts marked with `[-]` are not ready yet, prompts containing `@@@` are treate
396
396
  #### Features
397
397
 
398
398
  - **Multi-runner execution:** `openai-codex`, `github-copilot`, `cline`, `claude-code`, `opencode`, `gemini`
399
- - **Context injection:** `--context AGENTS.md` or inline extra instructions
399
+ - **Context injection:** `--agent agents/coding/developer.book --context AGENTS.md` or inline extra instructions
400
400
  - **Reasoning control:** `--thinking-level low|medium|high|xhigh` for supported runners
401
401
  - **Interactive or unattended runs:** default wait mode, or `--no-wait` for batch execution
402
402
  - **Git safety:** clean working tree check by default, optional `--ignore-git-changes`
@@ -416,11 +416,11 @@ npx ts-node ./src/cli/test/ptbk.ts coder generate-boilerplates --template prompt
416
416
 
417
417
  npx ts-node ./src/cli/test/ptbk.ts coder generate-boilerplates --template prompts/templates/agents-server.md
418
418
 
419
- npx ts-node ./src/cli/test/ptbk.ts coder run --harness github-copilot --model gpt-5.4 --thinking-level xhigh --context AGENTS.md
419
+ npx ts-node ./src/cli/test/ptbk.ts coder run --harness github-copilot --model gpt-5.4 --thinking-level xhigh --agent agents/coding/developer.book --context AGENTS.md
420
420
 
421
- npx ts-node ./src/cli/test/ptbk.ts coder run --harness github-copilot --model gpt-5.4 --thinking-level xhigh --context AGENTS.md --auto-push
421
+ npx ts-node ./src/cli/test/ptbk.ts coder run --harness github-copilot --model gpt-5.4 --thinking-level xhigh --agent agents/coding/developer.book --context AGENTS.md --auto-push
422
422
 
423
- npx ts-node ./src/cli/test/ptbk.ts coder run --harness github-copilot --model gpt-5.4 --thinking-level xhigh --context AGENTS.md --ignore-git-changes --no-wait
423
+ npx ts-node ./src/cli/test/ptbk.ts coder run --harness github-copilot --model gpt-5.4 --thinking-level xhigh --agent agents/coding/developer.book --context AGENTS.md --ignore-git-changes --no-wait
424
424
 
425
425
  npx ts-node ./src/cli/test/ptbk.ts coder find-refactor-candidates
426
426
 
@@ -442,11 +442,11 @@ ptbk coder generate-boilerplates
442
442
 
443
443
  ptbk coder generate-boilerplates --template prompts/templates/common.md
444
444
 
445
- ptbk coder run --harness github-copilot --model gpt-5.4 --thinking-level xhigh --context AGENTS.md --test npm run test
445
+ ptbk coder run --harness github-copilot --model gpt-5.4 --thinking-level xhigh --agent agents/coding/developer.book --context AGENTS.md --test npm run test
446
446
 
447
- ptbk coder run --harness github-copilot --model gpt-5.4 --thinking-level xhigh --context AGENTS.md --auto-push
447
+ ptbk coder run --harness github-copilot --model gpt-5.4 --thinking-level xhigh --agent agents/coding/developer.book --context AGENTS.md --auto-push
448
448
 
449
- ptbk coder run --harness github-copilot --model gpt-5.4 --thinking-level xhigh --context AGENTS.md --test npm run test --ignore-git-changes --no-wait
449
+ ptbk coder run --harness github-copilot --model gpt-5.4 --thinking-level xhigh --agent agents/coding/developer.book --context AGENTS.md --test npm run test --ignore-git-changes --no-wait
450
450
 
451
451
  ptbk coder find-refactor-candidates
452
452
 
@@ -459,13 +459,13 @@ ptbk coder verify
459
459
 
460
460
  #### What each command does
461
461
 
462
- | Command | What it does |
463
- | ------------------------------------- | -------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | --- | ------ | ---- | ----- | ------------------------------------------------------------------------ |
462
+ | Command | What it does |
463
+ | ------------------------------------- | --------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | --- | ------ | ---- | ----- | ------------------------------------------------------------------------ |
464
464
  | `ptbk coder init` | Creates `prompts/`, `prompts/done/`, the project-generic template files materialized in `prompts/templates/` (currently `common.md`), and a starter `AGENTS.md`; ensures `.env` contains `CODING_AGENT_GIT_NAME`, `CODING_AGENT_GIT_EMAIL`, and `CODING_AGENT_GIT_SIGNING_KEY`; adds helper coder scripts to `package.json`; ensures `.gitignore` contains `/.promptbook`; and configures `.vscode/settings.json` to save pasted prompt images into `prompts/screenshots/`. |
465
- | `ptbk coder generate-boilerplates` | Creates new prompt markdown files with fresh emoji tags so you can quickly fill in coding tasks; `--template` accepts either a built-in alias or a markdown file path relative to the project root. |
466
- | `ptbk coder run` | Picks the next ready prompt, appends optional context, runs it through the selected coding agent, can optionally verify each attempt with a shell test command and feed failing output back for retries, then marks success or failure, commits the result, and pushes only when `--auto-push` is enabled. |
467
- | `ptbk coder find-refactor-candidates` | Scans the repository for oversized or overpacked files and writes prompt files for likely refactors; `--level <xlow | low | medium | high | xhigh | extreme>` ranges from a very benevolent scan to a very aggressive sweep. |
468
- | `ptbk coder verify` | Walks through completed prompts, archives truly finished work, and adds follow-up repair prompts for unfinished results. |
465
+ | `ptbk coder generate-boilerplates` | Creates new prompt markdown files with fresh emoji tags so you can quickly fill in coding tasks; `--template` accepts either a built-in alias or a markdown file path relative to the project root. |
466
+ | `ptbk coder run` | Picks the next ready prompt, appends optional context, runs it through the selected coding agent, can optionally verify each attempt with a shell test command and feed failing output back for retries, then marks success or failure, commits the result, and pushes only when `--auto-push` is enabled. |
467
+ | `ptbk coder find-refactor-candidates` | Scans the repository for oversized or overpacked files and writes prompt files for likely refactors; `--level <xlow | low | medium | high | xhigh | extreme>` ranges from a very benevolent scan to a very aggressive sweep. |
468
+ | `ptbk coder verify` | Walks through completed prompts, archives truly finished work, and adds follow-up repair prompts for unfinished results. |
469
469
 
470
470
  #### Most useful `ptbk coder run` flags
471
471
 
@@ -488,7 +488,7 @@ ptbk coder verify
488
488
 
489
489
  1. Initialize once with `ptbk coder init`.
490
490
  2. Customize `prompts/templates/*.md` if needed, then create or write prompt files in `prompts/`.
491
- 3. Customize the starter `AGENTS.md` with repository-specific instructions, then pass `--context AGENTS.md`.
491
+ 3. Customize the starter `AGENTS.md` with repository-specific instructions, then pass `--agent agents/coding/developer.book --context AGENTS.md`.
492
492
  4. Run one prompt at a time interactively, or use `--no-wait` for unattended batches.
493
493
  5. Finish with `ptbk coder verify` so resolved prompts are archived and broken ones get explicit repair follow-ups.
494
494
 
package/package.json CHANGED
@@ -1,6 +1,6 @@
1
1
  {
2
2
  "name": "ptbk",
3
- "version": "0.112.0-121",
3
+ "version": "0.112.0-124",
4
4
  "description": "Promptbook: Create persistent AI agents that turn your company's scattered knowledge into action",
5
5
  "private": false,
6
6
  "sideEffects": false,
@@ -91,10 +91,10 @@
91
91
  "zod": "$zod"
92
92
  },
93
93
  "peerDependencies": {
94
- "@promptbook/core": "0.112.0-121"
94
+ "@promptbook/core": "0.112.0-124"
95
95
  },
96
96
  "dependencies": {
97
- "promptbook": "0.112.0-121"
97
+ "promptbook": "0.112.0-124"
98
98
  },
99
99
  "bin": {
100
100
  "ptbk": "bin/promptbook-cli-proxy.js"