riskrails 3.2.1 → 3.2.2

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.
@@ -5,7 +5,7 @@
5
5
  },
6
6
  "metadata": {
7
7
  "description": "A weight-based engineering pipeline for Claude Code and Codex: each change is weighed on six axes, runs light, guarded or full, edits only the files its plan names, and ends at human approval — enforced by hooks, reviewed adversarially, routed to the cheap model tier by default.",
8
- "version": "3.2.1"
8
+ "version": "3.2.2"
9
9
  },
10
10
  "plugins": [
11
11
  {
@@ -14,7 +14,7 @@
14
14
  "source": "url",
15
15
  "url": "https://github.com/vanssata/claude-agentic-sdlc-module.git"
16
16
  },
17
- "version": "3.2.1",
17
+ "version": "3.2.2",
18
18
  "strict": true
19
19
  }
20
20
  ]
@@ -1,6 +1,6 @@
1
1
  {
2
2
  "name": "riskrails",
3
- "version": "3.2.1",
3
+ "version": "3.2.2",
4
4
  "description": "A weight-based engineering pipeline for Claude Code and Codex: each change is weighed on six axes, runs light, guarded or full, edits only the files its plan names, and ends at human approval — enforced by hooks, reviewed adversarially, routed to the cheap model tier by default.",
5
5
  "author": {
6
6
  "name": "Ivan Kakurov"
@@ -1,6 +1,6 @@
1
1
  {
2
2
  "name": "riskrails",
3
- "version": "3.2.1",
3
+ "version": "3.2.2",
4
4
  "description": "A weight-based engineering pipeline for Claude Code and Codex: each change is weighed on six axes, runs light, guarded or full, edits only the files its plan names, and ends at human approval — enforced by hooks, reviewed adversarially, routed to the cheap model tier by default.",
5
5
  "author": {
6
6
  "name": "Ivan Kakurov"
package/README.md CHANGED
@@ -1,6 +1,6 @@
1
1
  # RiskRails
2
2
 
3
- [![Version](https://img.shields.io/badge/version-3.2.1-d2f878?labelColor=101210)](https://github.com/vanssata/claude-agentic-sdlc-module/releases/tag/v3.2.1)
3
+ [![Version](https://img.shields.io/badge/version-3.2.2-d2f878?labelColor=101210)](https://github.com/vanssata/claude-agentic-sdlc-module/releases/tag/v3.2.2)
4
4
  [![Runtimes](https://img.shields.io/badge/runtimes-Claude%20Code%20%7C%20Codex-d2f878?labelColor=101210)](docs/routing.md)
5
5
  [![Known risks](https://img.shields.io/badge/known%20risks-documented-d2f878?labelColor=101210)](docs/known-risks.md)
6
6
  [![License: MIT](https://img.shields.io/badge/license-MIT-d2f878?labelColor=101210)](LICENSE)
@@ -18,7 +18,7 @@ approval. Risky actions are stopped by a hook, not by a polite request in a
18
18
  prompt.
19
19
 
20
20
  ```bash
21
- npx riskrails@3.2.1 # detects Claude Code, Codex or both (Node 18+, Python 3.11+)
21
+ npx riskrails@3.2.2 # detects Claude Code, Codex or both (Node 18+, Python 3.11+)
22
22
  ```
23
23
 
24
24
  Then, in any project: `/rr-setup` once, and `/rr-build <what you want>` for
@@ -50,12 +50,12 @@ Tuned for **one developer who knows the codebase**, on a Claude Pro, Max or
50
50
  Team plan, or a ChatGPT Plus or Pro plan, following the
51
51
  [AI-native SDLC playbook](https://claude.com/blog/the-ai-native-sdlc-playbook).
52
52
 
53
- **Version 3.2.1.** The guards have limits: read [Known risks](docs/known-risks.md)
53
+ **Version 3.2.2.** The guards have limits: read [Known risks](docs/known-risks.md)
54
54
  before relying on them. What is decided but not built is in [ROADMAP.md](ROADMAP.md).
55
55
 
56
56
  ## Upgrade to 3.1
57
57
 
58
- From 3.0.x: update the home (`npx riskrails@3.2.1`, restart the runtime), then
58
+ From 3.0.x: update the home (`npx riskrails@3.2.2`, restart the runtime), then
59
59
  in each project `/rr-setup --update` (dry run first, then `--apply`). Schema 10
60
60
  becomes **11**: migration `0011` proposes deleting `.ai/policies/risk-tiers.json`
61
61
  and `risk-tiers.md`, which `weight.json` and `weight.md` replaced; confirm with
@@ -82,7 +82,7 @@ version. Step by step, in this order:
82
82
  3. **Update the home** on every machine, for every runtime:
83
83
 
84
84
  ```bash
85
- npx riskrails@3.2.1 # or: npx -y riskrails@latest --yes
85
+ npx riskrails@3.2.2 # or: npx -y riskrails@latest --yes
86
86
  ```
87
87
 
88
88
  It moves `<home>/claude-agentic/` to `<home>/riskrails/` and leaves a
@@ -120,13 +120,13 @@ home-side details in [docs/installation.md](docs/installation.md).
120
120
  ## Install
121
121
 
122
122
  ```bash
123
- npx riskrails@3.2.1 # detects Claude Code, Codex, or both; proposes the detected plan
124
- npx riskrails@3.2.1 --target codex # auto | claude | codex | both
125
- npx riskrails@3.2.1 --plan max --fable no # pro | team-pro | team-max | max | max20 | balanced-max
126
- npx riskrails@3.2.1 --codex-plan plus # plus | pro | balanced-max
127
- npx riskrails@3.2.1 --context economy # the plan's compaction window; the context guard also blocks
128
- npx riskrails@3.2.1 --statusline own # keep your own statusline command (from 3.2.1; default: the plugin's two-line statusline)
129
- npx riskrails@3.2.1 --dry-run # print what would be written, write nothing
123
+ npx riskrails@3.2.2 # detects Claude Code, Codex, or both; proposes the detected plan
124
+ npx riskrails@3.2.2 --target codex # auto | claude | codex | both
125
+ npx riskrails@3.2.2 --plan max --fable no # pro | team-pro | team-max | max | max20 | balanced-max
126
+ npx riskrails@3.2.2 --codex-plan plus # plus | pro | balanced-max
127
+ npx riskrails@3.2.2 --context economy # the plan's compaction window; the context guard also blocks
128
+ npx riskrails@3.2.2 --statusline own # keep your own statusline command (from 3.2.1; default: the plugin's two-line statusline)
129
+ npx riskrails@3.2.2 --dry-run # print what would be written, write nothing
130
130
  npx -y riskrails@latest --yes # update in place, keeping the recorded plan
131
131
  ```
132
132
 
package/package.json CHANGED
@@ -1,6 +1,6 @@
1
1
  {
2
2
  "name": "riskrails",
3
- "version": "3.2.1",
3
+ "version": "3.2.2",
4
4
  "description": "RiskRails: a weight-based engineering pipeline for Claude Code and Codex — scoped steps, enforcement hooks, adversarial review, model routing.",
5
5
  "keywords": ["claude-code", "codex", "sdlc", "agents", "guardrails", "code-review"],
6
6
  "homepage": "https://github.com/vanssata/claude-agentic-sdlc-module#readme",