cc-codeconductor - npm Package Compare versions

Comparing version 0.3.0 to 0.3.1

package.json

 {
   "name": "cc-codeconductor",
-  "version": "0.3.0",
+  "version": "0.3.1",
   "description": "A multi-agent orchestration framework for AI-assisted software engineering workflows.",
@@ -5,0 +5,0 @@ "keywords": [

presets/agy/AGENTS.md

@@ -9,2 +9,22 @@ <!-- CODECONDUCTOR:BEGIN managed -->
 
+## Behavioral Discipline
+
+These principles apply to **all agents** in every workflow. They reduce common
+LLM coding mistakes and bias toward caution over speed.
+
+1. **Think Before Coding** — State assumptions explicitly. If uncertain, ask. If
+   multiple interpretations exist, present them — don't pick silently. If a
+   simpler approach exists, say so.
+2. **Simplicity First** — Minimum code that solves the problem. No features
+   beyond what was asked. No abstractions for single-use code. No speculative
+   "flexibility." Ask: "Would a senior engineer say this is overcomplicated?"
+3. **Surgical Changes** — Touch only what you must. Don't "improve" adjacent
+   code. Match existing style. Remove only what YOUR changes made unused. Every
+   changed line must trace directly to the user's request.
+4. **Goal-Driven Execution** — Transform tasks into verifiable goals with
+   success criteria. For multi-step tasks, state a plan with verification
+   checks. Loop until verified.
+
+---
+
 ## Workflow Contract
@@ -105,4 +125,9 @@
 3. Select and document the agent route.
-4. Surface blockers rather than working around them.
-5. Declare completion only when all Deliverables are produced and verified.
+4. Enforce **Behavioral Discipline Gates**:
+   - **Think Before Coding Checkpoint**: Verify assumptions are explicitly documented before architect starts.
+   - **Simplicity Gate**: Review Technical Plan to ensure no speculative code or abstractions are planned.
+   - **Surgical Changes Audit**: Audit reviewer report and diff to verify only planned files were modified.
+   - **Goal-Driven Verification**: Confirm all acceptance criteria have passing tests.
+5. Surface blockers rather than working around them.
+6. Declare completion only when all Deliverables are produced and verified.
 
@@ -268,2 +293,6 @@ **Task Card validation — required fields before routing:**
 
+**Surgical Changes Rules:**
+- Modify ONLY planned files. Do not improve adjacent code, comments, or formatting.
+- Match existing style. Remove imports/variables/functions made unused by YOUR changes. Do not touch existing dead code.
+
 **Implementation Summary format:**
@@ -329,2 +358,6 @@ ```markdown
 
+**Review Axes & Gates:**
+- **Simplicity Gate**: Flag overcomplicated/speculative code. Ask: "Would a senior engineer say this is overbuilt?"
+- **Surgical Changes**: Verify no adjacent or unrelated code was changed.
+
 **Review Report format:**
@@ -331,0 +364,0 @@ ```markdown

presets/claude/CLAUDE.md

@@ -9,2 +9,20 @@ # CodeConductor — Multi-Agent Orchestration Framework
 
+## Behavioral Discipline
+
+These principles apply to **all agents** in every workflow. They reduce common
+LLM coding mistakes and bias toward caution over speed.
+
+1. **Think Before Coding** — State assumptions explicitly. If uncertain, ask. If
+   multiple interpretations exist, present them — don't pick silently. If a
+   simpler approach exists, say so.
+2. **Simplicity First** — Minimum code that solves the problem. No features
+   beyond what was asked. No abstractions for single-use code. No speculative
+   "flexibility." Ask: "Would a senior engineer say this is overcomplicated?"
+3. **Surgical Changes** — Touch only what you must. Don't "improve" adjacent
+   code. Match existing style. Remove only what YOUR changes made unused. Every
+   changed line must trace directly to the user's request.
+4. **Goal-Driven Execution** — Transform tasks into verifiable goals with
+   success criteria. For multi-step tasks, state a plan with verification
+   checks. Loop until verified.
+
 ---
@@ -49,4 +67,9 @@
 3. Execute the correct agent sequence.
-4. Surface blockers rather than working around them.
-5. Declare completion only when all Deliverables are produced and verified.
+4. Enforce **Behavioral Discipline Gates**:
+   - **Think Before Coding Checkpoint**: Verify assumptions are explicitly documented before architect starts.
+   - **Simplicity Gate**: Review Technical Plan to ensure no speculative code or abstractions are planned.
+   - **Surgical Changes Audit**: Audit reviewer report and diff to verify only planned files were modified.
+   - **Goal-Driven Verification**: Confirm all acceptance criteria have passing tests.
+5. Surface blockers rather than working around them.
+6. Declare completion only when all Deliverables are produced and verified.
 
@@ -307,2 +330,3 @@ **Task Card validation — required fields before routing:**
   before completing.
+- **Surgical Changes.** Modify ONLY planned files. Do not improve adjacent code, comments, or formatting. Match existing style. Remove imports/variables/functions made unused by YOUR changes. Do not touch existing dead code.
 
@@ -406,2 +430,4 @@ **Implementation Summary format:**
 | Technical debt | Does the implementation introduce debt without acknowledging it? |
+| Simplicity     | Flag overcomplicated or speculative code (overbuilt patterns).   |
+| Surgical       | Verify that NO adjacent or unrelated code/comments were changed. |
 
@@ -408,0 +434,0 @@ **Finding categories:**

presets/codex/AGENTS.md

@@ -11,2 +11,20 @@ <!-- CODECONDUCTOR:BEGIN managed -->
 
+## Behavioral Discipline
+
+These principles apply to **all agents** in every workflow. They reduce common
+LLM coding mistakes and bias toward caution over speed.
+
+1. **Think Before Coding** — State assumptions explicitly. If uncertain, ask. If
+   multiple interpretations exist, present them — don't pick silently. If a
+   simpler approach exists, say so.
+2. **Simplicity First** — Minimum code that solves the problem. No features
+   beyond what was asked. No abstractions for single-use code. No speculative
+   "flexibility." Ask: "Would a senior engineer say this is overcomplicated?"
+3. **Surgical Changes** — Touch only what you must. Don't "improve" adjacent
+   code. Match existing style. Remove only what YOUR changes made unused. Every
+   changed line must trace directly to the user's request.
+4. **Goal-Driven Execution** — Transform tasks into verifiable goals with
+   success criteria. For multi-step tasks, state a plan with verification
+   checks. Loop until verified.
+
 ---
@@ -115,4 +133,9 @@
 3. Select and document the agent route.
-4. Surface blockers rather than working around them.
-5. Declare completion only when all Deliverables are produced and verified.
+4. Enforce **Behavioral Discipline Gates**:
+   - **Think Before Coding Checkpoint**: Verify assumptions are explicitly documented before architect starts.
+   - **Simplicity Gate**: Review Technical Plan to ensure no speculative code or abstractions are planned.
+   - **Surgical Changes Audit**: Audit reviewer report and diff to verify only planned files were modified.
+   - **Goal-Driven Verification**: Confirm all acceptance criteria have passing tests.
+5. Surface blockers rather than working around them.
+6. Declare completion only when all Deliverables are produced and verified.
 
@@ -405,2 +428,3 @@ **Task Card validation — required fields before routing:**
 - **Run tests before declaring done.** If any test fails, investigate and fix.
+- **Surgical Changes.** Modify ONLY planned files. Do not improve adjacent code, comments, or formatting. Match existing style. Remove imports/variables/functions made unused by YOUR changes. Do not touch existing dead code.
 
@@ -533,2 +557,4 @@ **Completion Summary format:**
 | Technical debt | Does the implementation introduce debt without acknowledging it? |
+| Simplicity     | Flag overcomplicated or speculative code (overbuilt patterns).   |
+| Surgical       | Verify that NO adjacent or unrelated code/comments were changed. |
 
@@ -535,0 +561,0 @@ **Finding categories:**

presets/opencode/agents/implementer.md

@@ -58,5 +58,5 @@ ---
 
-**Minimal diff.** Change only what the Technical Plan specifies. If you notice
+**Minimal diff (Surgical Changes).** Change only what the Technical Plan specifies. If you notice
 something unrelated that could be improved, do not fix it. Log it as a
-suggestion in your completion summary and move on.
+suggestion in your completion summary and move on. Modify ONLY planned files. Do not improve adjacent code, comments, or formatting. Match existing style. Remove imports/variables/functions made unused by YOUR changes. Do not touch existing dead code.
 
@@ -63,0 +63,0 @@ **Follow existing patterns.** If the codebase uses a specific naming convention,

presets/opencode/agents/orchestrator.md

@@ -47,5 +47,10 @@ ---
 4. Select and document the agent route
-5. Delegate to the first agent in the route
-6. Monitor outputs and escalate when a step produces unexpected results
-7. Report the final outcome to the human
+5. Enforce **Behavioral Discipline Gates**:
+   - **Think Before Coding Checkpoint**: Verify assumptions are explicitly documented before architect starts.
+   - **Simplicity Gate**: Review Technical Plan to ensure no speculative code or abstractions are planned.
+   - **Surgical Changes Audit**: Audit reviewer report and diff to verify only planned files were modified.
+   - **Goal-Driven Verification**: Confirm all acceptance criteria have passing tests.
+6. Delegate to the first agent in the route
+7. Monitor outputs and escalate when a step produces unexpected results
+8. Report the final outcome to the human
 
@@ -323,3 +328,5 @@ ---
 - After the Routing Decision is produced
-- After `architect` produces a Technical Plan (before `implementer` is invoked)
+- After `repo-explorer` maps the repo but before `architect` starts (verify "Think Before Coding" assumptions are documented)
+- After `architect` produces a Technical Plan (perform the "Simplicity Gate" review before `implementer` is invoked)
+- After `reviewer` produces a report (perform "Surgical Changes Audit" and verify "Goal-Driven Verification" of tests)
 - After `reviewer` produces a CRITICAL finding
@@ -326,0 +333,0 @@ - When any agent reports unexpected complexity or a new risk that was not in the

presets/opencode/agents/reviewer.md

@@ -52,2 +52,4 @@ ---
 | Technical debt     | Does the implementation introduce debt without acknowledging it? |
+| Simplicity         | Flag overcomplicated or speculative code (overbuilt patterns).   |
+| Surgical           | Verify that NO adjacent or unrelated code/comments were changed. |
 
@@ -54,0 +56,0 @@ ## Finding Categories

README.md

@@ -60,3 +60,2 @@ # CodeConductor
 > - Safe Merger
-> - Multi-target `update` (currently updates only the `defaults.target` runner)
 >
@@ -256,5 +255,5 @@ > Security note:
 
-Checks config exists and is valid, reports runner directory status.
+Checks config exists and is valid, reports runner directory status, validates that `AGENTS.md` and `CLAUDE.md` do not exceed the 40KB size limit, and checks if updates are available for installed presets, target runner configurations, or skills.
 
-#### `update` — re-apply preset
+#### `update` — smart update preset
 
@@ -265,6 +264,8 @@ ```bash
 npx cc-codeconductor update --dry-run
+npx cc-codeconductor update --global
 ```
 
-Re-generates preset files for the `defaults.target` in your config.
+Smart updates all currently installed target presets, council configurations, and skills (from `skills-lock.json`), preserving user edits outside managed blocks. Also validates that `AGENTS.md` and `CLAUDE.md` do not exceed the 40KB size limit.
 
+
 ### Global options
@@ -271,0 +272,0 @@

New alerts

Filesystem access

Supply chain risk

Accesses the file system, and could potentially read sensitive data.

Fixed alerts

Filesystem access

Supply chain risk

Accesses the file system, and could potentially read sensitive data.

Improved metrics

Total package byte prevSize

2254135

0.86%

Lines of code

20825

1.58%

Number of lines in readme file

425

0.24%

Worsened metrics

Number of low supply chain risk alerts

18

12.5%

No dependency changes