@getmarrow/install 0.1.26 → 0.1.27
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 +13 -8
- package/package.json +1 -1
package/README.md
CHANGED
|
@@ -21,6 +21,8 @@ npx @getmarrow/install openclaw
|
|
|
21
21
|
v0.1.26 expands Marrow's supported harness registry so teams can attach governance to the agent tools, IDE agents, model CLIs, MCP clients, CI runners, and custom harnesses they already use.
|
|
22
22
|
|
|
23
23
|
- `npx @getmarrow/install integrations` lists supported surfaces, support level, install command, capture path, and detection signals.
|
|
24
|
+
- `GET /v1/agent/data-quality` lets agents verify attribution coverage after install, including agent ID, source metadata, harness/client, workflow type, outcome closure, and exact repair guidance.
|
|
25
|
+
- `GET /v1/agent/integrations/{client}` gives supported harnesses a per-client setup guide with install command, capture points, source metadata, runtime/commit/batch mapping, and exact next action.
|
|
24
26
|
- `npx @getmarrow/install govern` detects Codex, Claude Code, Cursor, Cursor Composer, Windsurf, Cline, OpenCode, Hermes, OpenClaw, Gemini, Grok, DeepSeek, Qwen, Kimi, MiniMax, GLM, MCP clients, CI scripts, and custom commands.
|
|
25
27
|
- Hermes Agent and OpenClaw remain first-class add-ons.
|
|
26
28
|
- Codex, Claude Code, Cursor, Cursor Composer, Windsurf, Cline, OpenCode, Gemini, Grok, DeepSeek, Qwen, Kimi, MiniMax, GLM, MCP clients, CI scripts, and custom shell/API harnesses can use MCP/SDK hooks, the governed runner, or `POST /v1/agent/integrations/events`.
|
|
@@ -73,19 +75,19 @@ npx @getmarrow/install govern
|
|
|
73
75
|
Run a harmless command through Marrow:
|
|
74
76
|
|
|
75
77
|
```bash
|
|
76
|
-
MARROW_API_KEY
|
|
78
|
+
MARROW_API_KEY=<your_marrow_key> npx @getmarrow/install run --agent codex-prod --profile production -- node -e "process.exit(0)"
|
|
77
79
|
```
|
|
78
80
|
|
|
79
81
|
Gate a production action before the agent executes it:
|
|
80
82
|
|
|
81
83
|
```bash
|
|
82
|
-
MARROW_API_KEY
|
|
84
|
+
MARROW_API_KEY=<your_marrow_key> npx @getmarrow/install gate "deploy production worker after tests pass"
|
|
83
85
|
```
|
|
84
86
|
|
|
85
87
|
Wrap a real deploy, publish, merge, or migration command only after the agent has the required proof:
|
|
86
88
|
|
|
87
89
|
```bash
|
|
88
|
-
MARROW_API_KEY
|
|
90
|
+
MARROW_API_KEY=<your_marrow_key> npx @getmarrow/install run \
|
|
89
91
|
--agent deploy-agent \
|
|
90
92
|
--type deploy \
|
|
91
93
|
--profile production \
|
|
@@ -125,7 +127,7 @@ npx @getmarrow/install --yes
|
|
|
125
127
|
One command should prove Marrow is active and useful:
|
|
126
128
|
|
|
127
129
|
```bash
|
|
128
|
-
MARROW_API_KEY
|
|
130
|
+
MARROW_API_KEY=<your_marrow_key> npx @getmarrow/install --yes
|
|
129
131
|
```
|
|
130
132
|
|
|
131
133
|
Expected result:
|
|
@@ -133,6 +135,7 @@ Expected result:
|
|
|
133
135
|
- Marrow writes the safest detected MCP/SDK/agent config.
|
|
134
136
|
- A harmless setup decision is created and its outcome is committed.
|
|
135
137
|
- `/v1/agent/status` confirms capture health and missing hooks.
|
|
138
|
+
- `/v1/agent/data-quality` confirms whether attribution is clean enough for per-agent, per-harness, and per-workflow value proof.
|
|
136
139
|
- `/v1/agent/runtime` verifies the one-call runtime gate and returns the before-action intervention contract.
|
|
137
140
|
- `/v1/agent/first-value` returns the five-minute proof payload used by installer, SDK, and MCP clients.
|
|
138
141
|
- `/v1/agent/value/proof` returns token value proof from passive model-usage capture.
|
|
@@ -189,7 +192,7 @@ npx @getmarrow/install --md --dry-run
|
|
|
189
192
|
When `MARROW_API_KEY` is present, the installer creates a harmless test decision, commits the outcome, reads `/v1/agent/status`, calls the one-call runtime, reads `/v1/agent/value/proof`, and prints the first useful Marrow signal plus token value proof.
|
|
190
193
|
|
|
191
194
|
```bash
|
|
192
|
-
MARROW_API_KEY
|
|
195
|
+
MARROW_API_KEY=<your_marrow_key> npx @getmarrow/install --yes
|
|
193
196
|
```
|
|
194
197
|
|
|
195
198
|
Skip self-test:
|
|
@@ -201,13 +204,13 @@ npx @getmarrow/install --yes --no-self-test
|
|
|
201
204
|
Doctor check:
|
|
202
205
|
|
|
203
206
|
```bash
|
|
204
|
-
MARROW_API_KEY
|
|
207
|
+
MARROW_API_KEY=<your_marrow_key> npx @getmarrow/install doctor
|
|
205
208
|
```
|
|
206
209
|
|
|
207
210
|
Repair missing hooks/config:
|
|
208
211
|
|
|
209
212
|
```bash
|
|
210
|
-
MARROW_API_KEY
|
|
213
|
+
MARROW_API_KEY=<your_marrow_key> npx @getmarrow/install --repair
|
|
211
214
|
```
|
|
212
215
|
|
|
213
216
|
## SDK Dependency
|
|
@@ -251,7 +254,9 @@ Day-one behavior:
|
|
|
251
254
|
|
|
252
255
|
## Trust and Data Boundaries
|
|
253
256
|
|
|
254
|
-
Marrow is tenant-aware by design. Private account, fleet,
|
|
257
|
+
Marrow is tenant-aware by design. Private account, fleet, workflow, proof-pack, and agent data stays scoped to the authenticated account and authorized agent-bound keys.
|
|
258
|
+
|
|
259
|
+
Enterprise tenants receive a strong private governance baseline from day one: risk gates, proof requirements, workflow templates, private/account learning, and exact next actions. Teams that enable sanitized aggregate contribution unlock richer k-anonymous collective workflow guidance. Contribution never means raw prompts, decisions, proof packs, code, secrets, account identifiers, agent identifiers, or customer identities.
|
|
255
260
|
|
|
256
261
|
For business pilots, review the live trust notes before production rollout: https://getmarrow.ai/docs#trust-boundaries
|
|
257
262
|
|