@shadowclone/cli 0.0.33 → 0.0.34
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 +33 -16
- package/dist/shadowclone.js +1058 -362
- package/package.json +1 -1
- package/plugins/shadowclone/.claude-plugin/plugin.json +1 -1
- package/plugins/shadowclone/.codex-plugin/plugin.json +1 -1
- package/plugins/shadowclone/plugin.json +1 -1
- package/plugins/shadowclone/skills/setup-cloud-sessions/SKILL.md +59 -0
- package/plugins/shadowclone/skills/setup-shadowclone/SKILL.md +3 -3
package/README.md
CHANGED
|
@@ -7,17 +7,17 @@
|
|
|
7
7
|
[](LICENSE)
|
|
8
8
|
[](https://hol.org/registry/plugins/theonly1me%2Fshadowclone)
|
|
9
9
|
|
|
10
|
-
[Quick start](#quick-start) · [What shadowclone offers](#what-shadowclone-offers) · [Compare](#how-shadowclone-compares-to-other-tools) · [How it works](#how-it-works) · [Eval and Results](#eval-and-results) · [Docs](#docs)
|
|
10
|
+
[Quick start](#quick-start) · [Cloud sessions](#your-clone-works-while-you-are-away) · [What shadowclone offers](#what-shadowclone-offers) · [Compare](#how-shadowclone-compares-to-other-tools) · [How it works](#how-it-works) · [Eval and Results](#eval-and-results) · [Docs](#docs)
|
|
11
11
|
|
|
12
12
|
</div>
|
|
13
13
|
|
|
14
|
-
**shadowclone keeps your engineering preferences the same in every coding agent.** It maintains one set of skills and instructions for Claude Code, Codex, Cursor, Pi, and
|
|
14
|
+
**shadowclone keeps your engineering preferences the same in every coding agent.** It maintains one set of skills and instructions for Claude Code, Codex, Cursor, Pi, Antigravity, and OpenCode. You do not copy rules from one tool to the next. shadowclone can also learn new preferences from the sessions that you allow.
|
|
15
15
|
|
|
16
|
-
**
|
|
16
|
+
**It works as you while you are away.** Comment `/shadowclone <task>` on a GitHub issue. Claude Code or Codex works with your skills, on your own subscription, in your own cloud account. It opens a draft pull request as you. shadowclone is not a separate agent. It equips the agent that you already use. See [how it compares to other tools](#how-shadowclone-compares-to-other-tools).
|
|
17
17
|
|
|
18
18
|
## Quick start
|
|
19
19
|
|
|
20
|
-
Paste this into Claude Code, Codex, Cursor, Pi, or
|
|
20
|
+
Paste this into Claude Code, Codex, Cursor, Pi, Antigravity, or OpenCode:
|
|
21
21
|
|
|
22
22
|
```text
|
|
23
23
|
Set up shadowclone: https://raw.githubusercontent.com/theonly1me/shadowclone/main/plugins/shadowclone/skills/setup-shadowclone/SKILL.md
|
|
@@ -45,6 +45,20 @@ To add the plugin, run `/plugin install shadowclone@shadowclone` after `/plugin
|
|
|
45
45
|
|
|
46
46
|
## What shadowclone offers
|
|
47
47
|
|
|
48
|
+
### Your clone works while you are away
|
|
49
|
+
|
|
50
|
+
**Comment, and it works as you.** `/shadowclone fix the flaky date parser test` on an issue starts Claude Code or Codex with your skills, on your Claude or ChatGPT plan or a key. It opens a draft pull request with your name on it. Only your own comment starts it.
|
|
51
|
+
|
|
52
|
+
```text
|
|
53
|
+
you /shadowclone fix the flaky date parser test
|
|
54
|
+
session shadowclone session is working on this. Branch shadowclone/issue-42 | Claude Code
|
|
55
|
+
session shadowclone session finished. Pull request #43
|
|
56
|
+
```
|
|
57
|
+
|
|
58
|
+
**Runs in your account.** Sessions run on Cloudflare, Vercel, Modal, Daytona, E2B, or a spare machine. There is no shadowclone server, and your tokens stay with the host that you choose. Sessions never push to the default branch, and each commit names the agent.
|
|
59
|
+
|
|
60
|
+
**Set it up with one sentence.** Ask your agent to "set up shadowclone cloud sessions on Cloudflare." You approve your skills and a default branch ruleset, and paste two tokens. See the [cloud sessions guide](docs/guides/cloud-sessions.md).
|
|
61
|
+
|
|
48
62
|
### Preferences that evolve with your work
|
|
49
63
|
|
|
50
64
|
**Learn from corrections.** shadowclone reads the sessions you allow and turns reusable instructions into skills and short native guidance. It keeps repository-specific rules in their scope. Rules remain readable, editable, and reversible.
|
|
@@ -55,7 +69,7 @@ To add the plugin, run `/plugin install shadowclone@shadowclone` after `/plugin
|
|
|
55
69
|
|
|
56
70
|
**Start with a build.** shadowclone includes 15 workflow skills for planning, debugging, implementation, verification, and review. New users can pick skills immediately. Learning from past sessions is optional. Browse the skills in [`skills/`](skills/), or [install them without the CLI](docs/guides/skills.md#install-skills-without-shadowclone).
|
|
57
71
|
|
|
58
|
-
**Choose where skills apply.** The browser wizard supports a personal build, a private build for one repository, or a shared build that a team commits. The same skills reach all
|
|
72
|
+
**Choose where skills apply.** The browser wizard supports a personal build, a private build for one repository, or a shared build that a team commits. The same skills reach all six agents. Pi can use any model it supports. See [Agent builds](docs/guides/agent-builds.md).
|
|
59
73
|
|
|
60
74
|
|
|
61
75
|
|
|
@@ -79,9 +93,9 @@ The agent creates an HTML guide with actual diffs, behavior traces, and a readin
|
|
|
79
93
|
|
|
80
94
|
**Review in the cloud.** Comment `@<bot> review` on a pull request, also on one from a fork. The cloud bot posts its findings on GitHub under its own identity. See [cloud review](docs/guides/reviews.md#review-in-the-cloud).
|
|
81
95
|
|
|
82
|
-
### A cloud bot
|
|
96
|
+
### A cloud bot for your team
|
|
83
97
|
|
|
84
|
-
**
|
|
98
|
+
**Share an agent with your team.** A bot runs in GitHub Actions with your selected skills and one provider API key: Anthropic, OpenAI, an OpenAI-compatible endpoint, or Cursor. Anyone with write access can tag it. It works on issues, opens pull requests, and follows checks and review feedback. You decide when to merge.
|
|
85
99
|
|
|
86
100
|
**Ask the agent to configure it.** After local setup, ask:
|
|
87
101
|
|
|
@@ -97,14 +111,14 @@ The agent prepares the skills repository and workflows. Then it gives you one li
|
|
|
97
111
|
|
|
98
112
|
shadowclone gives one set of skills to the agents that you already use, on your machine and on GitHub. The table uses each project's own pages, checked on 12 October 2026. "Not stated" means that those pages do not answer the question.
|
|
99
113
|
|
|
100
|
-
| Tool | What it is | Agents
|
|
101
|
-
| ---------------------------------------------------------------------- | ------------------------------------------------------------------------------------------ |
|
|
102
|
-
| shadowclone | Skills, instructions, learning, and a GitHub cloud bot for the agents that you already use | Claude Code, Codex, Cursor, Pi, Antigravity | Yes, from the sessions that you allow | Yes,
|
|
103
|
-
| [pstack](https://github.com/cursor/plugins/tree/main/pstack) | A skill and principle pack | Cursor
|
|
104
|
-
| [Hermes Agent](https://github.com/NousResearch/hermes-agent) | Its own agent with a learning loop | Hermes only
|
|
105
|
-
| [Claude Code auto memory](https://code.claude.com/docs/en/memory) | Built-in notes from corrections | Claude Code
|
|
106
|
-
| [Claude Subconscious](https://github.com/letta-ai/claude-subconscious) | A background Letta agent | Claude Code
|
|
107
|
-
| [imprint](https://github.com/n33kos/imprint) | A plugin that trains one profile | Claude Code
|
|
114
|
+
| Tool | What it is | Agents | Learns from your sessions | Same guidance in the cloud | Reviews pull requests |
|
|
115
|
+
| ---------------------------------------------------------------------- | ------------------------------------------------------------------------------------------ | ----------------------------------------------------- | -------------------------------------- | ------------------------------- | ------------------------------------- |
|
|
116
|
+
| shadowclone | Skills, instructions, learning, and a GitHub cloud bot for the agents that you already use | Claude Code, Codex, Cursor, Pi, Antigravity, OpenCode | Yes, from the sessions that you allow | Yes, cloud sessions and a bot | Yes, locally, guided, and on GitHub |
|
|
117
|
+
| [pstack](https://github.com/cursor/plugins/tree/main/pstack) | A skill and principle pack | Cursor | No. You run `/reflect` to edit a skill | Not stated | Yes, `/interrogate` and Comment Sicko |
|
|
118
|
+
| [Hermes Agent](https://github.com/NousResearch/hermes-agent) | Its own agent with a learning loop | Hermes only | Yes, it writes skills after tasks | Yes, on a server with chat apps | Not stated |
|
|
119
|
+
| [Claude Code auto memory](https://code.claude.com/docs/en/memory) | Built-in notes from corrections | Claude Code | Yes, notes from your corrections | No. Memory stays on one machine | No |
|
|
120
|
+
| [Claude Subconscious](https://github.com/letta-ai/claude-subconscious) | A background Letta agent | Claude Code | Yes, through a Letta agent | Not stated | No |
|
|
121
|
+
| [imprint](https://github.com/n33kos/imprint) | A plugin that trains one profile | Claude Code | Yes, when you run `/imprint:train` | Not stated | No |
|
|
108
122
|
|
|
109
123
|
Claude Code loads its auto memory beside shadowclone skills, so you can use both. See the [comparison guide](docs/guides/comparison.md) for each tool and its sources.
|
|
110
124
|
|
|
@@ -115,7 +129,8 @@ flowchart LR
|
|
|
115
129
|
A[Consented sessions] --> B[Learning]
|
|
116
130
|
B --> C[Skills and native instructions]
|
|
117
131
|
C --> D[Agents on your machine]
|
|
118
|
-
C --> E[Cloud
|
|
132
|
+
C --> E[Cloud sessions that work as you]
|
|
133
|
+
C --> F[Cloud bot on GitHub]
|
|
119
134
|
```
|
|
120
135
|
|
|
121
136
|
shadowclone indexes references to enabled sessions and copies no transcript. It redacts text and learns rules. One session can give an explicit rule, and an inferred pattern needs three independent sessions. Rules become skills that you can read, edit, and undo. shadowclone changes the guidance, not the model. See the [architecture](docs/architecture/README.md).
|
|
@@ -148,8 +163,10 @@ Read the [privacy policy](PRIVACY.md) and [data handling](docs/data-handling.md)
|
|
|
148
163
|
| [Skill maintenance](docs/guides/skills.md) | Review updates, undo |
|
|
149
164
|
| [Repository setup](docs/guides/repositories.md) | Share checks |
|
|
150
165
|
| [Pi setup](docs/guides/pi.md) | Use Pi models |
|
|
166
|
+
| [OpenCode setup](docs/guides/opencode.md) | Use OpenCode |
|
|
151
167
|
| [Delegated work](docs/guides/delegated-work.md) | Ready a pull request |
|
|
152
168
|
| [Cloud bot](docs/guides/cloud-bot.md) | Set up the GitHub bot |
|
|
169
|
+
| [Cloud sessions](docs/guides/cloud-sessions.md) | Work as you, anywhere |
|
|
153
170
|
| [Reviews](docs/guides/reviews.md) | Review a pull request |
|
|
154
171
|
| [MCP server](docs/guides/mcp.md) | Give agents the tools |
|
|
155
172
|
| [Command reference](docs/guides/commands.md) | Find every command |
|