anycrew 0.1.0 → 0.1.1

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.
Files changed (4) hide show
  1. package/README.md +39 -226
  2. package/README.npm.md +80 -0
  3. package/README.pypi.md +82 -0
  4. package/package.json +8 -4
package/README.md CHANGED
@@ -1,267 +1,80 @@
1
1
  <p align="center">
2
- <img src="assets/logo.svg" alt="anycrew" width="620">
2
+ <img src="https://raw.githubusercontent.com/fadlytanjung/anycrew/main/assets/logo.svg" alt="anycrew" width="560">
3
3
  </p>
4
4
 
5
- <p align="center">
6
- <strong>One crew of specialist AI agents for any coding assistant.</strong><br>
7
- Spec-driven · test-first · security-reviewed · model-tiered
8
- </p>
5
+ **One crew of specialist AI agents for any coding assistant.**
6
+ Spec-driven · test-first · security-reviewed · model-tiered
9
7
 
10
- <p align="center">
11
- <a href="https://github.com/fadlytanjung/anycrew/actions/workflows/ci.yml"><img alt="CI" src="https://img.shields.io/github/actions/workflow/status/fadlytanjung/anycrew/ci.yml?branch=main&label=ci"></a>
12
- <a href="https://www.npmjs.com/package/anycrew"><img alt="npm" src="https://img.shields.io/npm/v/anycrew?color=0284c7"></a>
13
- <a href="https://pypi.org/project/anycrew/"><img alt="PyPI" src="https://img.shields.io/pypi/v/anycrew?color=3776ab&logo=python&logoColor=white"></a>
14
- <img alt="python" src="https://img.shields.io/badge/python-%E2%89%A53.9-3776ab">
15
- <img alt="node" src="https://img.shields.io/badge/node-%E2%89%A518-339933?logo=node.js&logoColor=white">
16
- <img alt="dependencies" src="https://img.shields.io/badge/dependencies-0-0284c7">
17
- <a href="LICENSE"><img alt="MIT" src="https://img.shields.io/badge/license-MIT-blue"></a>
18
- <br>
19
- <img alt="Claude Code" src="https://img.shields.io/badge/Claude_Code-000?logo=anthropic&logoColor=white">
20
- <img alt="Codex" src="https://img.shields.io/badge/OpenAI_Codex-412991?logo=openai&logoColor=white">
21
- <img alt="Antigravity" src="https://img.shields.io/badge/Antigravity-4285F4?logo=google&logoColor=white">
22
- <img alt="Cursor" src="https://img.shields.io/badge/Cursor-111827">
23
- <img alt="OpenCode" src="https://img.shields.io/badge/OpenCode-1f2937">
24
- <img alt="Copilot" src="https://img.shields.io/badge/GitHub_Copilot-24292e?logo=github&logoColor=white">
25
- </p>
8
+ `anycrew` installs a ready-made engineering team into the coding assistant you already use:
9
+ Claude Code, OpenAI Codex, Google Antigravity, Cursor, OpenCode or GitHub Copilot. Sixteen agents
10
+ (brainstormer, product manager, architect, designer, spec writer, implementer, tester, reviewer,
11
+ security reviewer, debugger, AI engineer, release engineer, doc writer, scout, crew lead) follow one
12
+ spec-driven method from idea to a deployed MVP, and each declares how much model it needs so cheap
13
+ work runs on cheap models.
26
14
 
27
- ---
15
+ This package is the Node CLI. It has no dependencies and needs Node 18 or newer.
28
16
 
29
- anycrew installs a ready-made engineering team into the coding assistant you already use. Sixteen
30
- agents (brainstormer, product manager, architect, designer, spec writer, implementer, tester,
31
- reviewer, security reviewer, debugger, AI engineer, release engineer, doc writer, scout, crew lead)
32
- follow one method from idea to a deployed MVP, and leave behind the documents a team can review: a
33
- constitution, a PRD, ADRs, specs with acceptance criteria, and a status page that says what is
34
- really built. Each agent declares how much model it needs, so cheap work runs on cheap models.
17
+ ## Install and run
35
18
 
36
19
  ```bash
37
- uvx anycrew init # Python: uv (or `pipx run anycrew init`, or `pip install anycrew`)
38
- npx anycrew init # Node: npm (or `npx github:fadlytanjung/anycrew init` straight from this repo)
20
+ npx anycrew init # run without installing
21
+ npm install -g anycrew # or install the `anycrew` command
39
22
  ```
40
23
 
41
- Both CLIs are the same tool: one canonical pack, two zero-dependency ports that generate
42
- byte-identical projects (the CI proves it on every commit). Use whichever runtime you already have.
43
-
44
- > **Status: 0.1.0, early.** Claude Code and Antigravity outputs are verified end to end; Codex,
45
- > Cursor, OpenCode and Copilot outputs follow their documentation and are being exercised next.
46
- > See the [tool matrix](docs/04-tool-matrix.md). Feedback and PRs welcome.
47
-
48
- ## Contents
49
-
50
- - [Why anycrew](#why-anycrew)
51
- - [Concepts in two minutes](#concepts-in-two-minutes)
52
- - [What you get](#what-you-get)
53
- - [Quick start](#quick-start)
54
- - [Install the pack globally](#install-the-pack-globally)
55
- - [How it works](#how-it-works)
56
- - [The crew](#the-crew)
57
- - [Model tiers](#model-tiers)
58
- - [What `init` writes](#what-init-writes)
59
- - [Documentation and wiki](#documentation-and-wiki)
60
- - [FAQ](#faq)
61
- - [Roadmap](#roadmap)
62
- - [Contributing](#contributing)
63
- - [Acknowledgements](#acknowledgements)
64
- - [Licence](#licence)
65
-
66
- ## Why anycrew
67
-
68
- Every new project with a coding assistant repeats the same setup: an agent guide, rules, a handful
69
- of slash commands, a constitution, a docs skeleton, a spec loop, quality gates, a status page. Each
70
- assistant wants those in a different folder with a different front matter. The packs that exist are
71
- tied to one assistant, or ship skills without a team, or ship a method without the security,
72
- testing, docs and release roles an MVP needs. None of them says which model each role needs.
73
-
74
- anycrew is the boilerplate for the **team**, not for the stack. A preset describes your stack's
75
- commands and conventions; anycrew never forces a framework, a cloud or a language.
76
-
77
- ## Concepts in two minutes
78
-
79
- Every term has a page in the [wiki](wiki/Home.md). The short version:
80
-
81
- | Term | Means | In anycrew |
82
- |---|---|---|
83
- | **SDD** (spec-driven development) | write and approve the spec first, implement from it, change both together | the whole method; `rules/00-sdd-process.md` |
84
- | **Constitution** | the short list of principles every change is checked against | `docs/00-constitution.md`, created by `init` |
85
- | **PRD** (product requirements document) | who it is for, what they need, scope by priority, requirements with IDs | `docs/03`, written by `/crew-prd` |
86
- | **ADR** (architecture decision record) | one decision that is expensive to reverse: context, options, decision, consequences | `docs/adr/ADR-NNN-*.md`, written by `/crew-adr` |
87
- | **AC** (acceptance criterion) | one testable Given/When/Then statement, `AC-NNN-n` | in every spec; test names and commits cite them |
88
- | **Spec · plan · tasks** | what and why · how and which files · ordered test-first checklist | `docs/specs/NNN-name/`, the unit of work |
89
- | **Implementation status** | the only doc that says what is actually built, with the test that proves it | `docs/20`, kept true by `/crew-checkpoint` |
90
- | **Gate** | a point where a person decides before the next phase | decision, P0 scope, ADRs, spec Ready, production deploy |
91
- | **Agent** | a specialist with its own prompt, tools and model the assistant delegates to | 16 in `agents/` |
92
- | **Skill** | a procedure loaded on demand, typed as `/name` | 22 `/crew-*` in `skills/` |
93
- | **Rule** | always-on or path-scoped guidance | 6 in `rules/`, plus stack rules from your preset |
94
- | **Tier** | how much model an agent needs: `fast`, `balanced`, `strong` | mapped per assistant in `models.json` |
95
- | **Preset** | a JSON description of a stack: commands, layout, conventions | `presets/`, or your own file |
96
- | **Hook** | a command the assistant runs at an event, e.g. after a file edit | lint-after-edit, wired into each assistant |
97
-
98
- ## What you get
99
-
100
- | | |
101
- |---|---|
102
- | **16 agents** | each with a job, inputs, outputs, a procedure, rules, stop conditions and a **model tier** |
103
- | **22 skills** (`/crew-*`) | the workflow as slash commands: status, brainstorm, research, prd, architecture, adr, design, spec, plan, tasks, implement, test, review, security, verify, debug, checkpoint, deploy-check, docs, llm, sync, init |
104
- | **6 rules** | spec-driven process, architecture boundaries, security and data, LLM features, testing, docs and status; plus backend and frontend rules generated from your preset |
105
- | **Docs skeleton** | constitution, brainstorm, research, PRD, traceability, architecture, data model, API, frontend, design system, conventions, security, testing, infra, observability, delivery plan, status, ADRs, specs |
106
- | **Presets** | `python-fastapi-react`, `node-typescript-next`, `go-service`, `generic`; write your own in one JSON file |
107
- | **Hook** | a tool-agnostic lint-after-edit hook wired into each assistant |
108
- | **One CLI, two runtimes** | `uvx anycrew init` (Python) or `npx anycrew init` (Node) generates every assistant's native files from one source; `sync` keeps them current without touching your edits; zero dependencies in both |
109
-
110
24
  ## Quick start
111
25
 
112
26
  ```bash
113
27
  cd your-project
114
- uvx anycrew init --preset python-fastapi-react --tools claude,codex,antigravity
115
- # or just: uvx anycrew init (detects the assistants on your machine)
116
- # Node users: replace `uvx anycrew` with `npx anycrew` in every command below
28
+ anycrew init --preset python-fastapi-react --tools claude,codex,antigravity
29
+ # or just: anycrew init (detects the assistants on your machine)
117
30
 
118
- uvx anycrew doctor # what each assistant will read
119
- uvx anycrew list # agents, tiers and the model each assistant will use
31
+ anycrew doctor # what each assistant will read
32
+ anycrew list # agents, tiers and the model each assistant will use
33
+ anycrew sync # regenerate after editing .anycrew/config.json or upgrading
120
34
  ```
121
35
 
122
36
  Then open your assistant in the folder and type `/crew-status`. For a new idea, `/crew-brainstorm`;
123
37
  for an existing codebase, `/crew-spec`.
124
38
 
125
- ## Install the pack globally
126
-
127
- | Assistant | Command |
128
- |---|---|
129
- | Claude Code | `claude plugin marketplace add fadlytanjung/anycrew && claude plugin install anycrew@anycrew` |
130
- | Antigravity | `agy plugin install https://github.com/fadlytanjung/anycrew` |
131
- | Codex | `codex plugin marketplace add fadlytanjung/anycrew` then `/plugins` |
132
- | Copilot CLI | `copilot plugin install fadlytanjung/anycrew` |
133
- | Cursor | Customize → Install, point at the repository (Agent Plugins manifest) |
134
- | Skills only, any assistant | `npx skills add fadlytanjung/anycrew` |
135
- | Python environment | `pip install anycrew` or `uv tool install anycrew` gives you the `anycrew` command |
136
-
137
- A global install gives you the agents and skills everywhere. `npx anycrew init` in a project adds
138
- the docs skeleton, the stack rules, the hooks and the per-project model overrides.
139
-
140
- ## How it works
141
-
142
- ```mermaid
143
- flowchart LR
144
- idea["Idea"] --> b["/crew-brainstorm<br/>docs/01 decision"]
145
- b --> p["/crew-prd<br/>docs/03 PRD, FR/NFR"]
146
- p --> a["/crew-architecture<br/>docs/05, 09, 10, ADRs"]
147
- a --> s["/crew-spec<br/>spec · plan · tasks"]
148
- s --> i["/crew-implement<br/>TDD, one task, one commit"]
149
- i --> r["/crew-review · /crew-security<br/>findings with evidence"]
150
- r --> d["/crew-deploy-check<br/>checklist, rollback"]
151
- d --> c["/crew-checkpoint · /crew-docs<br/>status that is true"]
152
- i -. "/crew-debug · /crew-test" .-> i
153
- ```
154
-
155
- Each skill delegates to one agent at its tier. The crew lead sequences the phases and keeps a
156
- person at every gate. Agents never approve their own work.
157
-
158
- ## The crew
159
-
160
- | Agent | Tier | Does |
161
- |---|---|---|
162
- | crew-lead | strong | routes a request through the phases; never codes |
163
- | scout | fast | finds what exists, read-only, before anyone guesses |
164
- | brainstormer | strong | idea → problem scan → scored options → decision (`docs/01`) |
165
- | researcher | balanced | facts with sources and confidence (`docs/02`) |
166
- | product-manager | strong | personas, journeys, P0/P1/P2, FR/NFR (`docs/03`, `04`) |
167
- | architect | strong | containers, boundaries, data model, API contract, ADRs |
168
- | designer | balanced | screens, states, tokens, responsive and accessibility rules |
169
- | ai-engineer | strong | model/code boundary, prompts as files, schemas, grounding, evals |
170
- | spec-writer | strong | spec, plan, tasks with acceptance criteria |
171
- | implementer | balanced | one task, test first, smallest change, one commit |
172
- | tester | balanced | AC → test map, fixtures, boundary and property tests, evals |
173
- | debugger | strong | reproduce, isolate, root cause, regression test |
174
- | reviewer | strong | findings with file:line and a failure scenario; drift audit |
175
- | security-reviewer | strong | threat model, OWASP and LLM top-10 audit, test per fix |
176
- | release-engineer | balanced | build, pipeline, deploy, rollback, observability, cost guardrails |
177
- | doc-writer | fast | README, docs index, changelog, the status page |
178
-
179
- ## Model tiers
180
-
181
- | Tier | Claude Code | Antigravity | Codex | OpenCode | Used by |
182
- |---|---|---|---|---|---|
183
- | fast | haiku, low effort | flash | low effort | claude-haiku | scout, doc-writer |
184
- | balanced | sonnet, medium | flash | medium | claude-sonnet | implementer, tester, researcher, designer, release-engineer |
185
- | strong | opus, high | pro | high | claude-opus | brainstormer, product-manager, architect, spec-writer, reviewer, security-reviewer, debugger, ai-engineer, crew-lead |
186
-
187
- Override any cell per project in `.anycrew/config.json` under `models`. Cursor and Copilot default
188
- to `inherit` until you set model IDs. Details: [docs/03-model-tiers.md](docs/03-model-tiers.md).
189
-
190
39
  ## What `init` writes
191
40
 
192
41
  ```
193
42
  your-project/
194
43
  ├── AGENTS.md agent guide, read by every assistant (yours to edit)
195
- ├── CLAUDE.md @AGENTS.md
196
44
  ├── docs/ constitution, status, specs index, ADR and spec templates (yours)
197
45
  ├── .anycrew/config.json preset, tools, model overrides
198
- ├── .anycrew/hooks/ lint-after-edit.sh
199
46
  ├── .agents/rules|skills|agents universal layer: Codex, Antigravity, Cursor, Copilot, OpenCode
200
- ├── .claude/agents|skills|rules + settings.json hooks
201
- ├── .codex/agents/*.toml
202
- ├── .cursor/rules/*.mdc, agents/, hooks.json
203
- ├── .opencode/agents/
204
- └── .github/copilot-instructions.md, instructions/, agents/, hooks/
47
+ ├── .claude/ .codex/ .cursor/ .opencode/ .github/ native files per assistant
48
+ └── .anycrew/hooks/ lint-after-edit hook
205
49
  ```
206
50
 
207
- Generated files carry an `anycrew:generated` marker; `sync` rewrites only those and reports the
208
- rest. `AGENTS.md` and everything under `docs/` are created once and then belong to you.
209
-
210
- ## Documentation and wiki
211
-
212
- | Where | What |
213
- |---|---|
214
- | [wiki/](wiki/Home.md) | every term and concept, one page each: SDD, constitution, PRD, ACs, ADRs, spec loop, status, gates, agents vs skills vs rules, tiers, hooks, presets, standards, glossary, FAQ |
215
- | [docs/00-vision.md](docs/00-vision.md) | what anycrew is and is not |
216
- | [docs/01-method.md](docs/01-method.md) | the lifecycle, artifacts, gates, who does what |
217
- | [docs/02-agents.md](docs/02-agents.md) | the roster and how to customise it |
218
- | [docs/03-model-tiers.md](docs/03-model-tiers.md) | tiers and the mapping per assistant |
219
- | [docs/04-tool-matrix.md](docs/04-tool-matrix.md) | what each assistant reads, install, verification status |
220
- | [docs/05-landscape.md](docs/05-landscape.md) | comparison with BMAD, superpowers, spec-kit, wshobson/agents and others |
221
- | [docs/06-project-layout.md](docs/06-project-layout.md) | the docs skeleton and the spec loop in a project |
222
- | [docs/07-presets.md](docs/07-presets.md) | stack presets and writing your own |
223
- | [docs/08-roadmap.md](docs/08-roadmap.md) | what is next |
224
- | [docs/adr/](docs/adr/README.md) | decisions about anycrew itself |
225
-
226
- The `wiki/` folder is published to the GitHub wiki on every push to `main`.
227
-
228
- ## FAQ
51
+ Generated files carry an `anycrew:generated` marker; `sync` rewrites only those. `AGENTS.md` and
52
+ everything under `docs/` are created once and then belong to you.
229
53
 
230
- **Is this a framework like CrewAI or LangGraph?** No. Those run agents inside your product. anycrew
231
- is a crew that helps you build your product inside your coding assistant.
54
+ ## Presets
232
55
 
233
- **Will it overwrite my CLAUDE.md, rules or agents?** No. `init` never touches `AGENTS.md`, `docs/`
234
- or any file without the `anycrew:generated` marker; it reports them instead.
56
+ `python-fastapi-react`, `node-typescript-next`, `go-service`, `generic`, or your own JSON file:
57
+ `anycrew init --preset ./my-stack.json`. A preset carries commands and conventions, never code.
235
58
 
236
- **Do I have to use the whole method?** No. Each skill works alone; the gates and IDs pay off most
237
- when the loop is used end to end.
238
-
239
- **Can I use cheaper models everywhere?** Yes: override the tier mapping per project.
240
-
241
- More in the [wiki FAQ](wiki/FAQ.md).
242
-
243
- ## Roadmap
59
+ ## Model tiers
244
60
 
245
- 0.2: exercise Codex, Cursor, OpenCode and Copilot outputs for real; eval cases per agent; a shared
246
- MCP server list; Gemini CLI extension. 0.3: Windsurf/Devin, Cline, Kiro, Amp, Augment; `upgrade`;
247
- an example project built end to end. Full list: [docs/08-roadmap.md](docs/08-roadmap.md).
61
+ | Tier | Claude Code | Antigravity | Codex | Used by |
62
+ |---|---|---|---|---|
63
+ | fast | haiku, low effort | flash | low effort | scout, doc-writer |
64
+ | balanced | sonnet, medium | flash | medium | implementer, tester, researcher, designer, release-engineer |
65
+ | strong | opus, high | pro | high | brainstormer, product-manager, architect, spec-writer, reviewer, security-reviewer, debugger, ai-engineer, crew-lead |
248
66
 
249
- ## Contributing
67
+ Override per project in `.anycrew/config.json` under `models`.
250
68
 
251
- `npm test` validates the pack (front matter, tier consistency, Agent Skills spec fields, size
252
- budgets) and runs the smoke test (init for every preset and tool, idempotent sync, protection of
253
- hand-written files). See [CONTRIBUTING.md](CONTRIBUTING.md), [SECURITY.md](SECURITY.md) and the
254
- [code of conduct](CODE_OF_CONDUCT.md).
69
+ ## Documentation
255
70
 
256
- ## Acknowledgements
71
+ - Repository and full README: https://github.com/fadlytanjung/anycrew
72
+ - Wiki (every concept explained: SDD, ADR, PRD, acceptance criteria, gates, tiers): https://github.com/fadlytanjung/anycrew/wiki
73
+ - Changelog: https://github.com/fadlytanjung/anycrew/blob/main/CHANGELOG.md
257
74
 
258
- anycrew stands on the work of others: the spec loop and constitution from
259
- [spec-kit](https://github.com/github/spec-kit) and Kiro; brainstorm-first skills from
260
- [superpowers](https://github.com/obra/superpowers) and Compound Engineering; per-agent model
261
- selection from [wshobson/agents](https://github.com/wshobson/agents) and oh-my-claudecode; the
262
- open formats [AGENTS.md](https://agents.md), [Agent Skills](https://agentskills.io) and
263
- [Agent Plugins](https://agent-plugins.org); and the ADR format from Michael Nygard.
75
+ A Python build of the same CLI exists on PyPI (`uvx anycrew`) for teams without Node; both generate byte-identical
76
+ projects.
264
77
 
265
78
  ## Licence
266
79
 
267
- [MIT](LICENSE).
80
+ MIT.
package/README.npm.md ADDED
@@ -0,0 +1,80 @@
1
+ <p align="center">
2
+ <img src="https://raw.githubusercontent.com/fadlytanjung/anycrew/main/assets/logo.svg" alt="anycrew" width="560">
3
+ </p>
4
+
5
+ **One crew of specialist AI agents for any coding assistant.**
6
+ Spec-driven · test-first · security-reviewed · model-tiered
7
+
8
+ `anycrew` installs a ready-made engineering team into the coding assistant you already use:
9
+ Claude Code, OpenAI Codex, Google Antigravity, Cursor, OpenCode or GitHub Copilot. Sixteen agents
10
+ (brainstormer, product manager, architect, designer, spec writer, implementer, tester, reviewer,
11
+ security reviewer, debugger, AI engineer, release engineer, doc writer, scout, crew lead) follow one
12
+ spec-driven method from idea to a deployed MVP, and each declares how much model it needs so cheap
13
+ work runs on cheap models.
14
+
15
+ This package is the Node CLI. It has no dependencies and needs Node 18 or newer.
16
+
17
+ ## Install and run
18
+
19
+ ```bash
20
+ npx anycrew init # run without installing
21
+ npm install -g anycrew # or install the `anycrew` command
22
+ ```
23
+
24
+ ## Quick start
25
+
26
+ ```bash
27
+ cd your-project
28
+ anycrew init --preset python-fastapi-react --tools claude,codex,antigravity
29
+ # or just: anycrew init (detects the assistants on your machine)
30
+
31
+ anycrew doctor # what each assistant will read
32
+ anycrew list # agents, tiers and the model each assistant will use
33
+ anycrew sync # regenerate after editing .anycrew/config.json or upgrading
34
+ ```
35
+
36
+ Then open your assistant in the folder and type `/crew-status`. For a new idea, `/crew-brainstorm`;
37
+ for an existing codebase, `/crew-spec`.
38
+
39
+ ## What `init` writes
40
+
41
+ ```
42
+ your-project/
43
+ ├── AGENTS.md agent guide, read by every assistant (yours to edit)
44
+ ├── docs/ constitution, status, specs index, ADR and spec templates (yours)
45
+ ├── .anycrew/config.json preset, tools, model overrides
46
+ ├── .agents/rules|skills|agents universal layer: Codex, Antigravity, Cursor, Copilot, OpenCode
47
+ ├── .claude/ .codex/ .cursor/ .opencode/ .github/ native files per assistant
48
+ └── .anycrew/hooks/ lint-after-edit hook
49
+ ```
50
+
51
+ Generated files carry an `anycrew:generated` marker; `sync` rewrites only those. `AGENTS.md` and
52
+ everything under `docs/` are created once and then belong to you.
53
+
54
+ ## Presets
55
+
56
+ `python-fastapi-react`, `node-typescript-next`, `go-service`, `generic`, or your own JSON file:
57
+ `anycrew init --preset ./my-stack.json`. A preset carries commands and conventions, never code.
58
+
59
+ ## Model tiers
60
+
61
+ | Tier | Claude Code | Antigravity | Codex | Used by |
62
+ |---|---|---|---|---|
63
+ | fast | haiku, low effort | flash | low effort | scout, doc-writer |
64
+ | balanced | sonnet, medium | flash | medium | implementer, tester, researcher, designer, release-engineer |
65
+ | strong | opus, high | pro | high | brainstormer, product-manager, architect, spec-writer, reviewer, security-reviewer, debugger, ai-engineer, crew-lead |
66
+
67
+ Override per project in `.anycrew/config.json` under `models`.
68
+
69
+ ## Documentation
70
+
71
+ - Repository and full README: https://github.com/fadlytanjung/anycrew
72
+ - Wiki (every concept explained: SDD, ADR, PRD, acceptance criteria, gates, tiers): https://github.com/fadlytanjung/anycrew/wiki
73
+ - Changelog: https://github.com/fadlytanjung/anycrew/blob/main/CHANGELOG.md
74
+
75
+ A Python build of the same CLI exists on PyPI (`uvx anycrew`) for teams without Node; both generate byte-identical
76
+ projects.
77
+
78
+ ## Licence
79
+
80
+ MIT.
package/README.pypi.md ADDED
@@ -0,0 +1,82 @@
1
+ <p align="center">
2
+ <img src="https://raw.githubusercontent.com/fadlytanjung/anycrew/main/assets/logo.svg" alt="anycrew" width="560">
3
+ </p>
4
+
5
+ **One crew of specialist AI agents for any coding assistant.**
6
+ Spec-driven · test-first · security-reviewed · model-tiered
7
+
8
+ `anycrew` installs a ready-made engineering team into the coding assistant you already use:
9
+ Claude Code, OpenAI Codex, Google Antigravity, Cursor, OpenCode or GitHub Copilot. Sixteen agents
10
+ (brainstormer, product manager, architect, designer, spec writer, implementer, tester, reviewer,
11
+ security reviewer, debugger, AI engineer, release engineer, doc writer, scout, crew lead) follow one
12
+ spec-driven method from idea to a deployed MVP, and each declares how much model it needs so cheap
13
+ work runs on cheap models.
14
+
15
+ This package is the Python CLI. It has no dependencies and needs Python 3.9 or newer.
16
+
17
+ ## Install and run
18
+
19
+ ```bash
20
+ uvx anycrew init # run without installing (uv)
21
+ pipx run anycrew init # run without installing (pipx)
22
+ pip install anycrew # or install the `anycrew` command
23
+ uv tool install anycrew
24
+ ```
25
+
26
+ ## Quick start
27
+
28
+ ```bash
29
+ cd your-project
30
+ anycrew init --preset python-fastapi-react --tools claude,codex,antigravity
31
+ # or just: anycrew init (detects the assistants on your machine)
32
+
33
+ anycrew doctor # what each assistant will read
34
+ anycrew list # agents, tiers and the model each assistant will use
35
+ anycrew sync # regenerate after editing .anycrew/config.json or upgrading
36
+ ```
37
+
38
+ Then open your assistant in the folder and type `/crew-status`. For a new idea, `/crew-brainstorm`;
39
+ for an existing codebase, `/crew-spec`.
40
+
41
+ ## What `init` writes
42
+
43
+ ```
44
+ your-project/
45
+ ├── AGENTS.md agent guide, read by every assistant (yours to edit)
46
+ ├── docs/ constitution, status, specs index, ADR and spec templates (yours)
47
+ ├── .anycrew/config.json preset, tools, model overrides
48
+ ├── .agents/rules|skills|agents universal layer: Codex, Antigravity, Cursor, Copilot, OpenCode
49
+ ├── .claude/ .codex/ .cursor/ .opencode/ .github/ native files per assistant
50
+ └── .anycrew/hooks/ lint-after-edit hook
51
+ ```
52
+
53
+ Generated files carry an `anycrew:generated` marker; `sync` rewrites only those. `AGENTS.md` and
54
+ everything under `docs/` are created once and then belong to you.
55
+
56
+ ## Presets
57
+
58
+ `python-fastapi-react`, `node-typescript-next`, `go-service`, `generic`, or your own JSON file:
59
+ `anycrew init --preset ./my-stack.json`. A preset carries commands and conventions, never code.
60
+
61
+ ## Model tiers
62
+
63
+ | Tier | Claude Code | Antigravity | Codex | Used by |
64
+ |---|---|---|---|---|
65
+ | fast | haiku, low effort | flash | low effort | scout, doc-writer |
66
+ | balanced | sonnet, medium | flash | medium | implementer, tester, researcher, designer, release-engineer |
67
+ | strong | opus, high | pro | high | brainstormer, product-manager, architect, spec-writer, reviewer, security-reviewer, debugger, ai-engineer, crew-lead |
68
+
69
+ Override per project in `.anycrew/config.json` under `models`.
70
+
71
+ ## Documentation
72
+
73
+ - Repository and full README: https://github.com/fadlytanjung/anycrew
74
+ - Wiki (every concept explained: SDD, ADR, PRD, acceptance criteria, gates, tiers): https://github.com/fadlytanjung/anycrew/wiki
75
+ - Changelog: https://github.com/fadlytanjung/anycrew/blob/main/CHANGELOG.md
76
+
77
+ A Node build of the same CLI exists on npm for teams without Python; both generate byte-identical
78
+ projects.
79
+
80
+ ## Licence
81
+
82
+ MIT.
package/package.json CHANGED
@@ -1,6 +1,6 @@
1
1
  {
2
2
  "name": "anycrew",
3
- "version": "0.1.0",
3
+ "version": "0.1.1",
4
4
  "description": "One crew of specialist AI agents for any coding assistant. Spec-driven, test-first, security-reviewed, and model-tiered. Installs into Claude Code, OpenAI Codex, Google Antigravity, Gemini CLI, Cursor, OpenCode and GitHub Copilot.",
5
5
  "license": "MIT",
6
6
  "type": "module",
@@ -17,14 +17,18 @@
17
17
  "presets",
18
18
  "hooks",
19
19
  "models.json",
20
- "README.md",
21
- "LICENSE"
20
+ "LICENSE",
21
+ "README.md"
22
22
  ],
23
23
  "scripts": {
24
24
  "validate": "node scripts/validate.mjs",
25
25
  "test": "node scripts/validate.mjs && node scripts/smoke.mjs",
26
26
  "list": "node bin/anycrew.mjs list",
27
- "test:parity": "python3 tests/test_parity.py"
27
+ "test:parity": "python3 tests/test_parity.py",
28
+ "bump": "node scripts/bump.mjs",
29
+ "release:check": "node scripts/release-check.mjs",
30
+ "prepack": "cp README.md .README.repo.md && cp README.npm.md README.md",
31
+ "postpack": "mv .README.repo.md README.md"
28
32
  },
29
33
  "engines": {
30
34
  "node": ">=18"