openclaw-code-agent 4.1.2 → 4.2.1
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 +98 -160
- package/dist/index.js +142 -146
- package/openclaw.plugin.json +4 -4
- package/package.json +4 -5
package/README.md
CHANGED
|
@@ -4,114 +4,60 @@
|
|
|
4
4
|
[](https://www.npmjs.com/package/openclaw-code-agent)
|
|
5
5
|
[](LICENSE)
|
|
6
6
|
|
|
7
|
-
`openclaw-code-agent`
|
|
7
|
+
`openclaw-code-agent` runs Claude Code and Codex as managed background coding sessions from OpenClaw chat. It adds plan approval, session lifecycle, wake routing, worktree isolation, merge/PR follow-through, and explicit goal loops on top of the agent backends.
|
|
8
|
+
|
|
9
|
+
Use it when you want to start coding work from Telegram, Discord, or another OpenClaw-supported channel and keep the job observable after the first message.
|
|
10
|
+
|
|
11
|
+
## Highlights
|
|
8
12
|
|
|
9
13
|
- **Plan -> Review -> Execute**. `plan` is the default launch mode, and plan approval defaults to `delegate` so the orchestrator reviews the full plan before approving or escalating to the user.
|
|
10
14
|
- **Delegated worktree isolation**. New sessions default to `delegate`; opt into `ask`, `off`, `manual`, `auto-merge`, or `auto-pr` when you want a different branch follow-through policy.
|
|
11
|
-
- **State-driven decision UX**. `ask` sends explicit action buttons for **Merge
|
|
12
|
-
- **Lifecycle-first cleanup**. Worktrees are
|
|
15
|
+
- **State-driven decision UX**. `ask` sends explicit action buttons for **Merge**, **Open PR**, **Later**, and **Discard**. The same action-token model backs Telegram and Discord interactive callbacks.
|
|
16
|
+
- **Lifecycle-first cleanup**. Worktrees are temporary task sandboxes. The plugin distinguishes `merged` from `released` so different-SHA branches whose content already landed on the base branch can still be cleaned safely.
|
|
13
17
|
- **Full session lifecycle**. Suspend, resume, fork, interrupt, and recover sessions across restarts with persisted metadata and output.
|
|
14
18
|
- **Explicit goal-task loops**. Opt into verifier-driven repair loops or Ralph-style completion loops when you need iterative autonomous execution toward a specific goal.
|
|
15
19
|
- **Real operator visibility**. `agent_sessions`, `agent_output`, and `agent_stats` show status, buffered output, duration, and USD cost.
|
|
16
20
|
- **Two harnesses, one control plane**. Claude Code and Codex share the same tools, routing, notification pipeline, and worktree strategy model while each backend uses its own native execution substrate.
|
|
17
|
-
- **One continuation
|
|
18
|
-
|
|
19
|
-
Need the ACPX vs Codex vs code-agent breakdown? See [docs/ACP-COMPARISON.md](docs/ACP-COMPARISON.md).
|
|
20
|
-
|
|
21
|
-
## Boundaries
|
|
22
|
-
|
|
23
|
-
`openclaw-code-agent` is separate from both OpenClaw's bundled `acpx` runtime plugin and OpenClaw's bundled `codex` plugin.
|
|
24
|
-
|
|
25
|
-
- **ACPX** is OpenClaw's ACP runtime backend for ACP session interoperability.
|
|
26
|
-
- **OpenClaw's bundled `codex` plugin** is the core native Codex provider/harness pair for embedded agent turns.
|
|
27
|
-
- **`openclaw-code-agent`** is the chat orchestration layer that adds plan approval, wake routing, session lifecycle, and worktree/merge/PR policy above its own native Claude Code and Codex harnesses.
|
|
28
|
-
|
|
29
|
-
The shared substrate is often the local `codex` command and Codex App Server, but the responsibilities are different. This plugin is not an ACP server and it does not depend on OpenClaw's bundled Codex provider to expose its own `codex` harness.
|
|
30
|
-
|
|
31
|
-
## New In 4.1.2
|
|
32
|
-
|
|
33
|
-
`4.1.2` is a plan-approval reliability patch for the OpenClaw `2026.5.4` release line. It keeps the `>=2026.4.21` compatibility floor and the `4.1.1` build/test target, while tightening the user-facing approval path that gates implementation.
|
|
34
|
-
|
|
35
|
-
- **Telegram plan approval buttons restored**. Plan prompts in Telegram use the shared direct-message presentation path and carry the canonical **Approve**, **Revise**, and **Reject** actions.
|
|
36
|
-
- **Plain-text fallback is explicit**. While a plan is awaiting review, replying `Approve`, `Revise`, or `Reject` triggers the same approval, revision, or rejection path as the buttons.
|
|
37
|
-
- **Stale prompts are suppressed**. Rejected or killed plan sessions no longer resurface an obsolete Plan v2 prompt as if it were still actionable.
|
|
38
|
-
- **Verified release evidence**. A plan-gated `rust-hello-world` run, `rust-hello-world-minor-change-2` (`FzPCkqjh`), completed as `approved_then_implemented` after explicit approval; a later run (`VmUBWOH2`) delivered a clean plan prompt without the old stale Plan v2-after-reject behavior.
|
|
39
|
-
|
|
40
|
-
The `4.1.1` OpenClaw `2026.5.4` compatibility work remains current: managed TaskFlow mirroring is opportunistic, deterministic runtime state is exposed in wakes, direct notification failures are surfaced, and local build/test metadata still targets stable OpenClaw `2026.5.4`.
|
|
41
|
-
|
|
42
|
-
## From Prompt To Merged Branch
|
|
21
|
+
- **One continuation path**. Follow-ups, approvals, revisions, interrupts, and redirects all continue the existing session instead of launching a duplicate.
|
|
43
22
|
|
|
44
|
-
|
|
45
|
-
2. Review the plan in the same thread before anything touches the repo.
|
|
46
|
-
3. Let the agent finish in an isolated worktree, then merge or publish the result from chat.
|
|
23
|
+
This plugin is separate from OpenClaw's bundled `acpx` runtime plugin and bundled core `codex` plugin. Those own adjacent OpenClaw runtime/provider surfaces; `openclaw-code-agent` owns chat orchestration and repository follow-through for its own Claude Code and Codex harnesses. See [docs/ACP-COMPARISON.md](docs/ACP-COMPARISON.md) for the boundary details.
|
|
47
24
|
|
|
48
|
-
|
|
25
|
+
## From Prompt To Shipped Branch
|
|
49
26
|
|
|
50
|
-
|
|
51
|
-
|
|
52
|
-
|
|
53
|
-
|
|
54
|
-
- `/goal ...`
|
|
55
|
-
- `goal_launch(...)`
|
|
56
|
-
|
|
57
|
-
The plugin does not automatically switch into goal mode just because a freeform prompt contains the words `goal task`.
|
|
58
|
-
|
|
59
|
-
Use them when you want the plugin to keep looping toward one concrete outcome:
|
|
60
|
-
|
|
61
|
-
- **Verifier mode** reruns one or more shell checks after each coding turn and keeps iterating until they pass or the iteration budget is exhausted.
|
|
62
|
-
- **Ralph mode** keeps resuming the same task until the agent emits an exact completion promise, with optional verifiers run after completion is claimed.
|
|
63
|
-
|
|
64
|
-
Examples:
|
|
65
|
-
|
|
66
|
-
```bash
|
|
67
|
-
/goal --workdir /repo --verify "npm test" --verify "npm run lint" Fix the failing auth flow
|
|
68
|
-
/goal --workdir /repo --mode ralph --completion-promise DONE Ship the draft blog post workflow end to end
|
|
69
|
-
goal_launch(goal="Fix the failing auth flow", verifier_commands=["npm test", "npm run lint"], workdir="/repo")
|
|
70
|
-
goal_launch(goal="Ship the draft blog post workflow end to end", goal_mode="ralph", completion_promise="DONE", workdir="/repo")
|
|
71
|
-
```
|
|
72
|
-
|
|
73
|
-
Once launched, use `goal_status` / `/goal_status` to inspect progress and `goal_stop` / `/goal_stop` to terminate the loop. Goal-task state is persisted so recoverable loops can resume after a gateway restart.
|
|
27
|
+
1. Ask OpenClaw to launch a coding session from chat.
|
|
28
|
+
2. Review the plan in the same thread before implementation starts.
|
|
29
|
+
3. Let the agent finish in an isolated worktree.
|
|
30
|
+
4. Merge into the base branch, open a PR, defer the decision, or discard the sandbox from the same control plane.
|
|
74
31
|
|
|
75
32
|
### Plan First
|
|
76
33
|
|
|
77
|
-
The
|
|
78
|
-
|
|
79
|
-
> Demo note: the GIFs below were recorded on an older build. They still show the overall flow correctly, but they do not include the newer explicit action buttons and some other current thread controls.
|
|
34
|
+
The core loop is plan review. Claude Code and Codex feed the same approval UX: the plugin receives a structured plan artifact, keeps execution blocked until approval, and continues the same session after the plan is approved. If the user asks for revisions, the revised plan becomes the latest actionable version for that same session.
|
|
80
35
|
|
|
81
|
-
|
|
36
|
+
### Finish Cleanly
|
|
82
37
|
|
|
83
|
-
|
|
38
|
+
When a task completes, the plugin can leave the branch for review, merge it automatically, open or update a PR, or wake the orchestrator with diff context. In `ask`, the user gets explicit decision buttons in the originating thread. In `delegate`, the orchestrator reviews the worktree result and escalates user-facing decisions such as PR creation.
|
|
84
39
|
|
|
85
|
-
|
|
40
|
+
|
|
86
41
|
|
|
87
|
-
|
|
42
|
+
*`delegate` keeps the main checkout clean while the branch lifecycle happens in the worktree. The chat thread stays current on what was attempted, what changed, and what follow-through is needed.*
|
|
88
43
|
|
|
89
|
-
|
|
44
|
+
|
|
90
45
|
|
|
91
|
-
|
|
46
|
+
*`ask` keeps the human in the loop for branch follow-through. Current buttons adapt to state: new branches can show **Merge**, **Open PR**, **Later**, and **Discard**; branches with an existing PR can show **View PR** and **Sync PR** instead of **Open PR**. Older recordings may show prior wording.*
|
|
92
47
|
|
|
93
48
|
### Worktree Lifecycle
|
|
94
49
|
|
|
95
50
|
Worktree-backed sessions move through product-facing lifecycle states:
|
|
96
51
|
|
|
97
52
|
- `active`: sandbox still in use
|
|
98
|
-
- `pending decision`: waiting for merge
|
|
53
|
+
- `pending decision`: waiting for merge, PR, later, or discard follow-through
|
|
99
54
|
- `pr_open`: PR exists and the sandbox is being preserved
|
|
100
55
|
- `merged`: branch landed by normal git ancestry
|
|
101
|
-
- `released`: content is already on the base branch
|
|
56
|
+
- `released`: content is already on the base branch after rebase, squash, or cherry-pick
|
|
102
57
|
- `dismissed`: user intentionally discarded the sandbox
|
|
103
58
|
- `no_change`: session finished without a committed delta
|
|
104
59
|
|
|
105
|
-
|
|
106
|
-
|
|
107
|
-
## Supported Harnesses
|
|
108
|
-
|
|
109
|
-
| Harness | Status | Notes |
|
|
110
|
-
| --- | --- | --- |
|
|
111
|
-
| [Claude Code](https://docs.anthropic.com/en/docs/claude-code) | Supported | Native harness via `@anthropic-ai/claude-agent-sdk` |
|
|
112
|
-
| [Codex](https://github.com/openai/codex) | Supported | Native harness via Codex App Server over stdio |
|
|
113
|
-
|
|
114
|
-
Launches and notifications work from Telegram, Discord, or any OpenClaw-supported channel. Telegram and Discord now share the same action-token callback flow for plan approvals, question options, resume/restart, and worktree decisions.
|
|
60
|
+
Use `agent_worktree_status` for current state and `agent_worktree_cleanup(mode="preview_safe")` before removing resolved sandboxes.
|
|
115
61
|
|
|
116
62
|
## Quick Start
|
|
117
63
|
|
|
@@ -124,25 +70,20 @@ openclaw gateway restart
|
|
|
124
70
|
openclaw plugins inspect openclaw-code-agent --runtime --json
|
|
125
71
|
```
|
|
126
72
|
|
|
127
|
-
|
|
128
|
-
|
|
129
|
-
|
|
73
|
+
If OpenClaw blocks installation with a dangerous-code scanner finding for
|
|
74
|
+
`child_process`, that is expected for this trusted plugin because it launches
|
|
75
|
+
local coding harnesses and git tooling. Review the rationale in
|
|
76
|
+
[docs/SECURITY.md](docs/SECURITY.md), then rerun the trusted package/source with
|
|
77
|
+
the unsafe-install override:
|
|
130
78
|
|
|
131
|
-
|
|
132
|
-
|
|
133
|
-
|
|
134
|
-
|
|
135
|
-
### First-Run Onboarding
|
|
136
|
-
|
|
137
|
-
In OpenClaw's Manual setup flow, the plugin should only ask for three first-run decisions:
|
|
138
|
-
|
|
139
|
-
- `defaultWorkdir`: the git repo path you expect to launch from most often
|
|
140
|
-
- `defaultHarness`: whether your default harness is `claude-code` or `codex`
|
|
141
|
-
- `fallbackChannel`: an optional but recommended fully routable notification target for async updates
|
|
79
|
+
```bash
|
|
80
|
+
openclaw plugins install openclaw-code-agent --force --pin --dangerously-force-unsafe-install
|
|
81
|
+
```
|
|
142
82
|
|
|
143
|
-
|
|
83
|
+
Use that override only for a package/source you already trust. When validating a
|
|
84
|
+
specific reviewed release, add its version after the package name.
|
|
144
85
|
|
|
145
|
-
Add
|
|
86
|
+
Add the smallest useful config under `plugins.entries["openclaw-code-agent"]` in `~/.openclaw/openclaw.json`:
|
|
146
87
|
|
|
147
88
|
```json
|
|
148
89
|
{
|
|
@@ -152,19 +93,7 @@ Add a minimal config block under `plugins.entries["openclaw-code-agent"]` in `~/
|
|
|
152
93
|
"enabled": true,
|
|
153
94
|
"config": {
|
|
154
95
|
"defaultWorkdir": "/home/user/project",
|
|
155
|
-
"defaultHarness": "claude-code"
|
|
156
|
-
"fallbackChannel": "telegram|my-bot|123456789",
|
|
157
|
-
"harnesses": {
|
|
158
|
-
"claude-code": {
|
|
159
|
-
"defaultModel": "anthropic/claude-sonnet-4-7",
|
|
160
|
-
"allowedModels": ["sonnet", "opus"]
|
|
161
|
-
},
|
|
162
|
-
"codex": {
|
|
163
|
-
"defaultModel": "gpt-5.5",
|
|
164
|
-
"allowedModels": ["gpt-5.5", "gpt-5.5-pro"],
|
|
165
|
-
"reasoningEffort": "medium"
|
|
166
|
-
}
|
|
167
|
-
}
|
|
96
|
+
"defaultHarness": "claude-code"
|
|
168
97
|
}
|
|
169
98
|
}
|
|
170
99
|
}
|
|
@@ -172,110 +101,119 @@ Add a minimal config block under `plugins.entries["openclaw-code-agent"]` in `~/
|
|
|
172
101
|
}
|
|
173
102
|
```
|
|
174
103
|
|
|
175
|
-
|
|
104
|
+
For the first run, choose:
|
|
105
|
+
|
|
106
|
+
- `defaultWorkdir`: a git repository root you expect to use often.
|
|
107
|
+
- `defaultHarness`: `claude-code` or `codex`.
|
|
108
|
+
|
|
109
|
+
The default policy is intentionally review-first:
|
|
176
110
|
|
|
177
111
|
- `permissionMode: "plan"`
|
|
178
112
|
- `planApproval: "delegate"`
|
|
179
113
|
- `defaultWorktreeStrategy: "delegate"`
|
|
180
114
|
|
|
181
|
-
Because
|
|
115
|
+
Because worktree isolation defaults to `delegate`, `defaultWorkdir` should normally be a git repo. For non-git directories, set `defaultWorktreeStrategy` to `off` or launch with `worktree_strategy: "off"`.
|
|
116
|
+
|
|
117
|
+
Chat-launched sessions route updates back to their originating chat thread. For agent-launched tool sessions without an origin route, configure `fallbackChannel` or `agentChannels` in the reference guide.
|
|
182
118
|
|
|
183
|
-
|
|
119
|
+
This release targets the OpenClaw SDK package `openclaw@2026.5.6`, while keeping the plugin peer floor at `>=2026.4.21`.
|
|
120
|
+
|
|
121
|
+
If you use Codex, make sure the local `codex` command or `OPENCLAW_CODEX_APP_SERVER_COMMAND` override is available and authenticated. When Codex auth is inconsistent, this is the recommended `~/.codex/config.toml` setting:
|
|
184
122
|
|
|
185
123
|
```toml
|
|
186
124
|
forced_login_method = "chatgpt"
|
|
187
125
|
```
|
|
188
126
|
|
|
189
|
-
|
|
127
|
+
## First Session
|
|
190
128
|
|
|
191
|
-
|
|
129
|
+
In chat, ask OpenClaw to start work:
|
|
192
130
|
|
|
193
|
-
|
|
131
|
+
```text
|
|
132
|
+
Start a coding session named fix-auth to fix the auth middleware bug.
|
|
133
|
+
```
|
|
194
134
|
|
|
195
|
-
|
|
135
|
+
When the plan arrives, respond in the same thread:
|
|
196
136
|
|
|
197
|
-
|
|
198
|
-
|
|
137
|
+
```text
|
|
138
|
+
Approve.
|
|
139
|
+
```
|
|
199
140
|
|
|
200
|
-
|
|
141
|
+
Send follow-ups as ordinary chat replies:
|
|
201
142
|
|
|
202
|
-
|
|
143
|
+
```text
|
|
144
|
+
Add unit tests too.
|
|
145
|
+
Show me the latest output.
|
|
146
|
+
Stop this session.
|
|
147
|
+
```
|
|
203
148
|
|
|
204
|
-
|
|
149
|
+
## Core Workflows
|
|
205
150
|
|
|
206
|
-
|
|
207
|
-
/agent --name fix-auth Fix the auth middleware bug
|
|
208
|
-
/agent_sessions
|
|
209
|
-
/agent_respond fix-auth Add unit tests too
|
|
210
|
-
agent_launch(prompt="<new task>", resume_session_id="fix-auth", fork_session=true)
|
|
211
|
-
```
|
|
151
|
+
### Plan Review
|
|
212
152
|
|
|
213
|
-
|
|
153
|
+
By default, Claude Code and Codex produce a plan before implementation. The plan can be approved, revised, or rejected through buttons when available, or with plain-text `Approve`, `Revise`, or `Reject` in the same thread.
|
|
214
154
|
|
|
215
|
-
|
|
155
|
+
Revisions stay attached to the same session, so the newest plan is the actionable one.
|
|
216
156
|
|
|
217
|
-
###
|
|
157
|
+
### Worktree Follow-Through
|
|
218
158
|
|
|
219
|
-
|
|
159
|
+
New sessions use delegated worktree follow-through unless configured otherwise. That keeps changes in an isolated branch and wakes the orchestrator with diff context. In `ask` mode, user-facing buttons depend on state:
|
|
220
160
|
|
|
221
|
-
|
|
222
|
-
|
|
223
|
-
|
|
224
|
-
|
|
225
|
-
|
|
161
|
+
| State | Buttons |
|
|
162
|
+
| --- | --- |
|
|
163
|
+
| New branch and GitHub CLI available | `Merge`, `Open PR`, `Later`, `Discard` |
|
|
164
|
+
| Existing PR | `Merge`, `View PR`, `Sync PR`, `Later`, `Discard` |
|
|
165
|
+
| GitHub CLI unavailable | `Merge`, `Later`, `Discard` |
|
|
226
166
|
|
|
227
|
-
|
|
167
|
+
Ask OpenClaw for worktree status before cleaning resolved sandboxes.
|
|
228
168
|
|
|
229
|
-
|
|
230
|
-
- Direct notification failures are now surfaced more explicitly. Treat a missing button delivery as a delivery/routing problem, not as evidence that the underlying plan or worktree state changed.
|
|
231
|
-
- Runtime and approval state fields in wakes are authoritative. Prefer them over transcript fragments when deciding whether execution was approved, bypassed, completed, or still waiting.
|
|
169
|
+
### Goal Tasks
|
|
232
170
|
|
|
233
|
-
|
|
171
|
+
Goal tasks are explicit autonomous loops for work that should keep iterating toward a defined finish line. They do not replace ordinary coding sessions.
|
|
234
172
|
|
|
235
|
-
|
|
173
|
+
Ask in normal chat:
|
|
236
174
|
|
|
237
|
-
|
|
238
|
-
|
|
239
|
-
-
|
|
240
|
-
|
|
241
|
-
|
|
175
|
+
```text
|
|
176
|
+
Start a verifier goal in /repo: fix the failing auth flow and keep running pnpm test until it passes.
|
|
177
|
+
Start a Ralph-style goal for /repo: ship the draft workflow, and consider it complete when the output says DONE.
|
|
178
|
+
Show goal status.
|
|
179
|
+
Stop the auth goal.
|
|
180
|
+
```
|
|
242
181
|
|
|
243
|
-
|
|
182
|
+
OpenClaw agents can use the goal tools directly when they need explicit loop control; humans can usually describe the goal in plain language.
|
|
244
183
|
|
|
245
|
-
|
|
246
|
-
- Codex now runs through App Server structured events and may execute inside a native backend-managed worktree.
|
|
247
|
-
- Merge, PR, reminder, and decision policy remain plugin-owned above both backends.
|
|
248
|
-
- Operators should continue sessions by plugin session ID or name. Backend conversation IDs are accepted only for recovery and diagnostics.
|
|
184
|
+
## Tools And Commands
|
|
249
185
|
|
|
250
|
-
|
|
186
|
+
Most users interact in chat. The tool surface is for OpenClaw agents and advanced integrations.
|
|
251
187
|
|
|
252
|
-
|
|
|
188
|
+
| Agent-facing tool | Purpose |
|
|
253
189
|
| --- | --- |
|
|
254
190
|
| `agent_launch` | Start a background coding session |
|
|
255
191
|
| `agent_respond` | Reply, redirect, approve a plan, or escalate permissions |
|
|
192
|
+
| `agent_request_plan_approval` | Escalate a delegated plan review to the user |
|
|
193
|
+
| `agent_send_plan_offer` | Send a message with Start Plan / Dismiss buttons for a plan-gated follow-up |
|
|
256
194
|
| `agent_output` | Read buffered session output |
|
|
257
195
|
| `agent_sessions` | List active and recent sessions |
|
|
258
196
|
| `agent_kill` | Stop or mark a session completed |
|
|
259
197
|
| `agent_stats` | Show aggregate usage and cost |
|
|
260
198
|
| `agent_merge` | Merge a worktree branch back to base |
|
|
261
199
|
| `agent_pr` | Create or update a GitHub PR |
|
|
262
|
-
| `agent_worktree_status` | Show
|
|
263
|
-
| `agent_worktree_cleanup` | Clean
|
|
200
|
+
| `agent_worktree_status` | Show worktree lifecycle state and cleanup safety |
|
|
201
|
+
| `agent_worktree_cleanup` | Clean safe worktrees or dismiss one pending decision |
|
|
264
202
|
| `goal_launch` | Start an explicit verifier or Ralph-style goal loop |
|
|
265
203
|
| `goal_status` | Show one goal task or list all goal tasks |
|
|
266
204
|
| `goal_stop` | Stop a running goal task |
|
|
267
205
|
|
|
268
|
-
|
|
206
|
+
Chat commands mirror the common workflows when you want explicit commands instead of natural-language chat, but most human use should start with plain requests like the examples above. Available commands are `/agent`, `/agent_sessions`, `/agent_output`, `/agent_respond`, `/agent_kill`, `/agent_stats`, `/goal`, `/goal_status`, and `/goal_stop`.
|
|
269
207
|
|
|
270
208
|
## Docs
|
|
271
209
|
|
|
272
210
|
| Doc | What It Covers |
|
|
273
211
|
| --- | --- |
|
|
274
|
-
| [docs/REFERENCE.md](docs/REFERENCE.md) |
|
|
275
|
-
| [docs/ARCHITECTURE.md](docs/ARCHITECTURE.md) |
|
|
276
|
-
| [docs/DEVELOPMENT.md](docs/DEVELOPMENT.md) | Local setup,
|
|
277
|
-
| [docs/SECURITY.md](docs/SECURITY.md) | Accepted subprocess surfaces, verifier
|
|
278
|
-
| [docs/ACP-COMPARISON.md](docs/ACP-COMPARISON.md) |
|
|
212
|
+
| [docs/REFERENCE.md](docs/REFERENCE.md) | Full operator reference: install, config, tools, commands, routing, worktrees, troubleshooting |
|
|
213
|
+
| [docs/ARCHITECTURE.md](docs/ARCHITECTURE.md) | Internal architecture and lifecycle design |
|
|
214
|
+
| [docs/DEVELOPMENT.md](docs/DEVELOPMENT.md) | Local setup, validation, release prep, extension points |
|
|
215
|
+
| [docs/SECURITY.md](docs/SECURITY.md) | Accepted subprocess surfaces, verifier shell boundary, scanner findings |
|
|
216
|
+
| [docs/ACP-COMPARISON.md](docs/ACP-COMPARISON.md) | Boundary with OpenClaw ACPX and bundled Codex surfaces |
|
|
279
217
|
| [skills/code-agent-orchestration/SKILL.md](skills/code-agent-orchestration/SKILL.md) | Operational skill for orchestrating sessions from an agent |
|
|
280
218
|
| [CHANGELOG.md](CHANGELOG.md) | Release history |
|
|
281
219
|
|