contract-driven-delivery 2.0.0 → 2.0.1
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/CHANGELOG.md +12 -0
- package/README.md +13 -0
- package/assets/CODEX.template.md +4 -4
- package/assets/agents/change-classifier.md +2 -1
- package/assets/agents/contract-reviewer.md +2 -1
- package/assets/agents/dependency-security-reviewer.md +2 -2
- package/assets/agents/qa-reviewer.md +2 -1
- package/assets/agents/repo-context-scanner.md +2 -2
- package/assets/agents/spec-drift-auditor.md +2 -2
- package/assets/agents/ui-ux-reviewer.md +2 -2
- package/assets/agents/visual-reviewer.md +2 -2
- package/package.json +1 -1
package/CHANGELOG.md
CHANGED
|
@@ -1,5 +1,17 @@
|
|
|
1
1
|
# Changelog
|
|
2
2
|
|
|
3
|
+
## [2.0.1] - 2026-04-30
|
|
4
|
+
|
|
5
|
+
### Fixed
|
|
6
|
+
|
|
7
|
+
- Clarified the agent ownership model in the public docs so read-only reviewers
|
|
8
|
+
and write-capable implementation agents have explicit, non-conflicting file
|
|
9
|
+
ownership rules.
|
|
10
|
+
- Aligned bundled prompts so read-only agents emit an `Agent Log` YAML block
|
|
11
|
+
for main Claude to persist, while write-capable agents continue writing their
|
|
12
|
+
own artifacts and `agent-log/*.yml` files.
|
|
13
|
+
- Synchronized package version metadata for the post-`2.0.0` publish path.
|
|
14
|
+
|
|
3
15
|
## [2.0.0] - 2026-04-30
|
|
4
16
|
|
|
5
17
|
### BREAKING: structured YAML for tasks and agent-log
|
package/README.md
CHANGED
|
@@ -99,6 +99,19 @@ or
|
|
|
99
99
|
8. `cdd-kit gate <change-id>` runs automatically to confirm all artifacts are complete
|
|
100
100
|
9. Claude reports a summary and the suggested git commit
|
|
101
101
|
|
|
102
|
+
### Agent Ownership Model
|
|
103
|
+
|
|
104
|
+
CDD uses two agent classes on purpose:
|
|
105
|
+
|
|
106
|
+
- `change-classifier`, `contract-reviewer`, `qa-reviewer`, `visual-reviewer`, `dependency-security-reviewer`, `ui-ux-reviewer`, `repo-context-scanner`, and `spec-drift-auditor` are read-only. They return analysis, verdicts, or an `Agent Log` YAML block; main Claude writes the corresponding files.
|
|
107
|
+
- `backend-engineer`, `frontend-engineer`, `e2e-resilience-engineer`, `monkey-test-engineer`, `stress-soak-engineer`, `ci-cd-gatekeeper`, `test-strategist`, and `spec-architect` are write-capable. They write their own implementation artifacts and their own `agent-log/*.yml`.
|
|
108
|
+
|
|
109
|
+
This split is deliberate:
|
|
110
|
+
|
|
111
|
+
- Review and audit agents stay read-only so they do not silently change the thing they are supposed to assess.
|
|
112
|
+
- Implementation and planning agents write directly so large artifacts and code edits do not have to be relayed back through the main orchestrator, which reduces token waste and preserves clearer ownership.
|
|
113
|
+
- `tasks.yml` remains owned by main Claude so task state changes stay centralized even when multiple agents contribute files.
|
|
114
|
+
|
|
102
115
|
**You stay in control by:**
|
|
103
116
|
- Reviewing the `change-classification.md` before implementation starts
|
|
104
117
|
- Checking the `test-plan.md` to confirm the right test families are planned
|
package/assets/CODEX.template.md
CHANGED
|
@@ -18,12 +18,12 @@ Read `specs/changes/<change-id>/context-manifest.md` before using file-reading o
|
|
|
18
18
|
- Read only paths allowed by the manifest or approved expansions.
|
|
19
19
|
- Do not use broad repository search unless the manifest authorizes it.
|
|
20
20
|
- If more context is needed, stop and write a Context Expansion Request in the manifest.
|
|
21
|
-
- Record every file read through tools in the relevant `agent-log/*.
|
|
21
|
+
- Record every file read through tools in the relevant `agent-log/*.yml` under `files-read:`.
|
|
22
22
|
|
|
23
|
-
Required `agent-log/*.
|
|
23
|
+
Required `agent-log/*.yml` format:
|
|
24
24
|
|
|
25
|
-
```
|
|
26
|
-
|
|
25
|
+
```yaml
|
|
26
|
+
files-read:
|
|
27
27
|
- contracts/api/api-contract.md
|
|
28
28
|
- src/server/routes/users.ts
|
|
29
29
|
```
|
|
@@ -225,7 +225,8 @@ Note: `archive.md` is created during change close-out, not at classification tim
|
|
|
225
225
|
|
|
226
226
|
## Machine-Verifiable Evidence
|
|
227
227
|
|
|
228
|
-
After completing your task,
|
|
228
|
+
After completing your task, end your response with an `Agent Log` YAML block
|
|
229
|
+
for main Claude to write to
|
|
229
230
|
`specs/changes/<change-id>/agent-log/<your-agent-name>.yml`. Required fields,
|
|
230
231
|
field rules, and gate-enforcement behavior are defined once in
|
|
231
232
|
`references/agent-log-protocol.md` — do not duplicate them in this prompt.
|
|
@@ -63,7 +63,8 @@ approved / changes-required
|
|
|
63
63
|
|
|
64
64
|
## Machine-Verifiable Evidence
|
|
65
65
|
|
|
66
|
-
After completing your task,
|
|
66
|
+
After completing your task, end your response with an `Agent Log` YAML block
|
|
67
|
+
for main Claude to write to
|
|
67
68
|
`specs/changes/<change-id>/agent-log/<your-agent-name>.yml`. Required fields,
|
|
68
69
|
field rules, and gate-enforcement behavior are defined once in
|
|
69
70
|
`references/agent-log-protocol.md` — do not duplicate them in this prompt.
|
|
@@ -64,7 +64,8 @@ approved / changes-required / blocked
|
|
|
64
64
|
|
|
65
65
|
## Machine-Verifiable Evidence
|
|
66
66
|
|
|
67
|
-
After completing your task,
|
|
67
|
+
After completing your task, end your response with an `Agent Log` YAML block
|
|
68
|
+
for main Claude to write to
|
|
68
69
|
`specs/changes/<change-id>/agent-log/<your-agent-name>.yml`. Required fields,
|
|
69
70
|
field rules, and gate-enforcement behavior are defined once in
|
|
70
71
|
`references/agent-log-protocol.md` — do not duplicate them in this prompt.
|
|
@@ -74,4 +75,3 @@ field rules, and gate-enforcement behavior are defined once in
|
|
|
74
75
|
- `cve-findings`: count + severity buckets
|
|
75
76
|
- `license-issues`: list or "none"
|
|
76
77
|
- `lockfile-changes`: list of files
|
|
77
|
-
|
|
@@ -75,7 +75,8 @@ approved / blocked / approved-with-risk
|
|
|
75
75
|
|
|
76
76
|
## Machine-Verifiable Evidence
|
|
77
77
|
|
|
78
|
-
After completing your task,
|
|
78
|
+
After completing your task, end your response with an `Agent Log` YAML block
|
|
79
|
+
for main Claude to write to
|
|
79
80
|
`specs/changes/<change-id>/agent-log/<your-agent-name>.yml`. Required fields,
|
|
80
81
|
field rules, and gate-enforcement behavior are defined once in
|
|
81
82
|
`references/agent-log-protocol.md` — do not duplicate them in this prompt.
|
|
@@ -84,7 +84,8 @@ frontend / backend / fullstack / monorepo / library / tool
|
|
|
84
84
|
|
|
85
85
|
## Machine-Verifiable Evidence
|
|
86
86
|
|
|
87
|
-
After completing your task,
|
|
87
|
+
After completing your task, end your response with an `Agent Log` YAML block
|
|
88
|
+
for main Claude to write to
|
|
88
89
|
`specs/changes/<change-id>/agent-log/<your-agent-name>.yml`. Required fields,
|
|
89
90
|
field rules, and gate-enforcement behavior are defined once in
|
|
90
91
|
`references/agent-log-protocol.md` — do not duplicate them in this prompt.
|
|
@@ -93,4 +94,3 @@ field rules, and gate-enforcement behavior are defined once in
|
|
|
93
94
|
- `profile-path`: `project-profile.generated.md`
|
|
94
95
|
- `stack-detected`: from cdd-kit detect-stack
|
|
95
96
|
- `surfaces-flagged`: list of missing standardization surfaces
|
|
96
|
-
|
|
@@ -52,7 +52,8 @@ By default, do NOT read `specs/changes/` history. Only read historical change re
|
|
|
52
52
|
|
|
53
53
|
## Machine-Verifiable Evidence
|
|
54
54
|
|
|
55
|
-
After completing your task,
|
|
55
|
+
After completing your task, end your response with an `Agent Log` YAML block
|
|
56
|
+
for main Claude to write to
|
|
56
57
|
`specs/changes/<change-id>/agent-log/<your-agent-name>.yml`. Required fields,
|
|
57
58
|
field rules, and gate-enforcement behavior are defined once in
|
|
58
59
|
`references/agent-log-protocol.md` — do not duplicate them in this prompt.
|
|
@@ -62,4 +63,3 @@ field rules, and gate-enforcement behavior are defined once in
|
|
|
62
63
|
- `drift-items`: count + severity
|
|
63
64
|
- `drift-summary-path`: `specs/audits/<YYYY-MM-DD>-drift-audit.md`
|
|
64
65
|
- `next-audit-due`: ISO date
|
|
65
|
-
|
|
@@ -51,7 +51,8 @@ approved / changes-required
|
|
|
51
51
|
|
|
52
52
|
## Machine-Verifiable Evidence
|
|
53
53
|
|
|
54
|
-
After completing your task,
|
|
54
|
+
After completing your task, end your response with an `Agent Log` YAML block
|
|
55
|
+
for main Claude to write to
|
|
55
56
|
`specs/changes/<change-id>/agent-log/<your-agent-name>.yml`. Required fields,
|
|
56
57
|
field rules, and gate-enforcement behavior are defined once in
|
|
57
58
|
`references/agent-log-protocol.md` — do not duplicate them in this prompt.
|
|
@@ -61,4 +62,3 @@ field rules, and gate-enforcement behavior are defined once in
|
|
|
61
62
|
- `state-coverage`: list of `<screen>: empty/loading/error/success` matrix
|
|
62
63
|
- `copy-issues`: count + severity
|
|
63
64
|
- `accessibility-findings`: count + severity
|
|
64
|
-
|
|
@@ -53,7 +53,8 @@ approved / changes-required
|
|
|
53
53
|
|
|
54
54
|
## Machine-Verifiable Evidence
|
|
55
55
|
|
|
56
|
-
After completing your task,
|
|
56
|
+
After completing your task, end your response with an `Agent Log` YAML block
|
|
57
|
+
for main Claude to write to
|
|
57
58
|
`specs/changes/<change-id>/agent-log/<your-agent-name>.yml`. Required fields,
|
|
58
59
|
field rules, and gate-enforcement behavior are defined once in
|
|
59
60
|
`references/agent-log-protocol.md` — do not duplicate them in this prompt.
|
|
@@ -63,4 +64,3 @@ field rules, and gate-enforcement behavior are defined once in
|
|
|
63
64
|
- `diff-percentage`: per-screen
|
|
64
65
|
- `state-coverage`: matrix
|
|
65
66
|
- `tokens-violated`: list of CSS contract violations or "none"
|
|
66
|
-
|
package/package.json
CHANGED
|
@@ -1,6 +1,6 @@
|
|
|
1
1
|
{
|
|
2
2
|
"name": "contract-driven-delivery",
|
|
3
|
-
"version": "2.0.
|
|
3
|
+
"version": "2.0.1",
|
|
4
4
|
"description": "Contract-driven delivery kit for AI coding agents with deterministic context indexes, manifest-backed read-scope governance, and orchestrated contracts-first delivery.",
|
|
5
5
|
"keywords": [
|
|
6
6
|
"contract-driven",
|