feat: add Behavioral_RL ECC bundle#6
Open
ecc-tools[bot] wants to merge 11 commits into
Open
Conversation
…rited/Behavioral_RL-instincts.yaml)
![cubic-dev-ai[bot]](https://avatars.githubusercontent.com/in/1082092?s=60&v=4){kind=small}
There was a problem hiding this comment.
7 issues found across 11 files
Prompt for AI agents (unresolved issues)
Check if these issues are valid — if so, understand the root cause of each and fix them. If appropriate, use sub-agents to investigate and fix each issue separately.
<file name=".codex/AGENTS.md">
<violation number="1" location=".codex/AGENTS.md:26">
P3: Contradiction in Workflow Files section: the first bullet says no workflow files were generated, but the next sentence says 'Use these workflow files...', which has no antecedent. Remove the dangling sentence or rephrase it to avoid ambiguity (e.g., 'When workflow files are added in the future, use them as reusable task scaffolds...').</violation>
</file>
<file name=".claude/identity.json">
<violation number="1" location=".claude/identity.json:9">
P2: `domains` is set to `["typescript"]` but this is a Python project with zero TypeScript files. This will cause Claude Code to apply incorrect language-specific conventions and patterns.</violation>
</file>
<file name=".claude/homunculus/instincts/inherited/Behavioral_RL-instincts.yaml">
<violation number="1" location=".claude/homunculus/instincts/inherited/Behavioral_RL-instincts.yaml:25">
P3: Grammatical error: "Based on 1 commits" should be "Based on 1 commit" (singular).</violation>
<violation number="2" location=".claude/homunculus/instincts/inherited/Behavioral_RL-instincts.yaml:28">
P2: Duplicate instincts covering the same topics (naming, imports, exports, tests, workflows, commits) create ambiguity for the AI agent, with different confidence levels and potentially conflicting guidance (e.g., 55-char limit vs freeform commit messages). Deduplicate to keep the higher-confidence or more accurate version of each.</violation>
</file>
<file name=".agents/skills/Behavioral_RL/SKILL.md">
<violation number="1" location=".agents/skills/Behavioral_RL/SKILL.md:1">
P1: Remove the outer ` ```markdown` and ` ``` ` code fences. Since the file is already a `.md` file, the content should be raw markdown — wrapping it in a code block causes headings, tables, and lists to render as literal code text rather than formatted instructions, which defeats the purpose of the skill file.</violation>
</file>
<file name=".claude/skills/Behavioral_RL/SKILL.md">
<violation number="1" location=".claude/skills/Behavioral_RL/SKILL.md:1">
P2: The entire .md file is wrapped in ```markdown ... ``` fenced code blocks. This will cause markdown renderers to display the content as a literal code block rather than rendering headings, tables, and formatting. Remove the outer code fence markers so the file is bare markdown.</violation>
</file>
<file name=".codex/config.toml">
<violation number="1" location=".codex/config.toml:48">
P3: Add a trailing newline at the end of the file to comply with POSIX conventions.</violation>
</file>
Reply with feedback, questions, or to request a fix.
Re-trigger cubic
| @@ -0,0 +1,88 @@ | |||
| ```markdown | |||
There was a problem hiding this comment.
P1: Remove the outer ```markdown and ``` code fences. Since the file is already a .md file, the content should be raw markdown — wrapping it in a code block causes headings, tables, and lists to render as literal code text rather than formatted instructions, which defeats the purpose of the skill file.
Prompt for AI agents
Check if this issue is valid — if so, understand the root cause and fix it. At .agents/skills/Behavioral_RL/SKILL.md, line 1:
<comment>Remove the outer ` ```markdown` and ` ``` ` code fences. Since the file is already a `.md` file, the content should be raw markdown — wrapping it in a code block causes headings, tables, and lists to render as literal code text rather than formatted instructions, which defeats the purpose of the skill file.</comment>
<file context>
@@ -0,0 +1,88 @@
+```markdown
+# Behavioral_RL Development Patterns
+
</file context>
| "codeComments": true, | ||
| "explanations": true | ||
| }, | ||
| "domains": [ |
There was a problem hiding this comment.
P2: domains is set to ["typescript"] but this is a Python project with zero TypeScript files. This will cause Claude Code to apply incorrect language-specific conventions and patterns.
Prompt for AI agents
Check if this issue is valid — if so, understand the root cause and fix it. At .claude/identity.json, line 9:
<comment>`domains` is set to `["typescript"]` but this is a Python project with zero TypeScript files. This will cause Claude Code to apply incorrect language-specific conventions and patterns.</comment>
<file context>
@@ -0,0 +1,14 @@
+ "codeComments": true,
+ "explanations": true
+ },
+ "domains": [
+ "typescript"
+ ],
</file context>
| - Based on 1 commits | ||
|
|
||
| --- | ||
| id: Behavioral_RL-naming-files |
There was a problem hiding this comment.
P2: Duplicate instincts covering the same topics (naming, imports, exports, tests, workflows, commits) create ambiguity for the AI agent, with different confidence levels and potentially conflicting guidance (e.g., 55-char limit vs freeform commit messages). Deduplicate to keep the higher-confidence or more accurate version of each.
Prompt for AI agents
Check if this issue is valid — if so, understand the root cause and fix it. At .claude/homunculus/instincts/inherited/Behavioral_RL-instincts.yaml, line 28:
<comment>Duplicate instincts covering the same topics (naming, imports, exports, tests, workflows, commits) create ambiguity for the AI agent, with different confidence levels and potentially conflicting guidance (e.g., 55-char limit vs freeform commit messages). Deduplicate to keep the higher-confidence or more accurate version of each.</comment>
<file context>
@@ -0,0 +1,303 @@
+- Based on 1 commits
+
+---
+id: Behavioral_RL-naming-files
+trigger: "when creating a new file"
+confidence: 0.8
</file context>
| @@ -0,0 +1,88 @@ | |||
| ```markdown | |||
There was a problem hiding this comment.
P2: The entire .md file is wrapped in markdown ... fenced code blocks. This will cause markdown renderers to display the content as a literal code block rather than rendering headings, tables, and formatting. Remove the outer code fence markers so the file is bare markdown.
Prompt for AI agents
Check if this issue is valid — if so, understand the root cause and fix it. At .claude/skills/Behavioral_RL/SKILL.md, line 1:
<comment>The entire .md file is wrapped in ```markdown ... ``` fenced code blocks. This will cause markdown renderers to display the content as a literal code block rather than rendering headings, tables, and formatting. Remove the outer code fence markers so the file is bare markdown.</comment>
<file context>
@@ -0,0 +1,88 @@
+```markdown
+# Behavioral_RL Development Patterns
+
</file context>
|
|
||
| - No dedicated workflow command files were generated for this repo. | ||
|
|
||
| Use these workflow files as reusable task scaffolds when the detected repository workflows recur. No newline at end of file |
There was a problem hiding this comment.
P3: Contradiction in Workflow Files section: the first bullet says no workflow files were generated, but the next sentence says 'Use these workflow files...', which has no antecedent. Remove the dangling sentence or rephrase it to avoid ambiguity (e.g., 'When workflow files are added in the future, use them as reusable task scaffolds...').
Prompt for AI agents
Check if this issue is valid — if so, understand the root cause and fix it. At .codex/AGENTS.md, line 26:
<comment>Contradiction in Workflow Files section: the first bullet says no workflow files were generated, but the next sentence says 'Use these workflow files...', which has no antecedent. Remove the dangling sentence or rephrase it to avoid ambiguity (e.g., 'When workflow files are added in the future, use them as reusable task scaffolds...').</comment>
<file context>
@@ -0,0 +1,26 @@
+
+- No dedicated workflow command files were generated for this repo.
+
+Use these workflow files as reusable task scaffolds when the detected repository workflows recur.
\ No newline at end of file
</file context>
| ## Evidence | ||
|
|
||
| - Average commit message length: 55 chars | ||
| - Based on 1 commits |
There was a problem hiding this comment.
P3: Grammatical error: "Based on 1 commits" should be "Based on 1 commit" (singular).
Prompt for AI agents
Check if this issue is valid — if so, understand the root cause and fix it. At .claude/homunculus/instincts/inherited/Behavioral_RL-instincts.yaml, line 25:
<comment>Grammatical error: "Based on 1 commits" should be "Based on 1 commit" (singular).</comment>
<file context>
@@ -0,0 +1,303 @@
+## Evidence
+
+- Average commit message length: 55 chars
+- Based on 1 commits
+
+---
</file context>
|
|
||
| [agents.docs_researcher] | ||
| description = "Documentation specialist that verifies APIs, framework behavior, and release notes." | ||
| config_file = "agents/docs-researcher.toml" No newline at end of file |
There was a problem hiding this comment.
P3: Add a trailing newline at the end of the file to comply with POSIX conventions.
Prompt for AI agents
Check if this issue is valid — if so, understand the root cause and fix it. At .codex/config.toml, line 48:
<comment>Add a trailing newline at the end of the file to comply with POSIX conventions.</comment>
<file context>
@@ -0,0 +1,48 @@
+
+[agents.docs_researcher]
+description = "Documentation specialist that verifies APIs, framework behavior, and release notes."
+config_file = "agents/docs-researcher.toml"
\ No newline at end of file
</file context>
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Summary
Auto-generated ECC bundle from repository analysis.
What This Does
Merging this PR adds repo-local ECC artifacts for both Claude Code and Codex. The generated bundle captures repository patterns, Codex baseline config, and reusable workflow scaffolds derived from git history analysis.
Analysis Scope
Files
.claude/ecc-tools.json.claude/skills/Behavioral_RL/SKILL.md.agents/skills/Behavioral_RL/SKILL.md.agents/skills/Behavioral_RL/agents/openai.yaml.claude/identity.json.codex/config.toml.codex/AGENTS.md.codex/agents/explorer.toml.codex/agents/reviewer.toml.codex/agents/docs-researcher.toml.claude/homunculus/instincts/inherited/Behavioral_RL-instincts.yamlOptional: Continuous Learning (15 instincts)
This PR also includes instincts for the continuous-learning-v2 skill. These are optional and only useful if you use that skill.
Import after merging:
Review Checklist
ECC Tools | Everything Claude Code
Summary by cubic
Add an ECC bundle with repo-specific skills, a Codex multi-agent baseline, and optional continuous-learning instincts to standardize workflows. Enables Claude Code/Codex to follow the repo’s patterns with no runtime app changes.
New Features
.claude/skills/Behavioral_RL/SKILL.md,.agents/skills/Behavioral_RL/SKILL.md)..codex/config.tomlwith multi-agent roles (explorer, reviewer, docs researcher) and MCP servers:@modelcontextprotocol/server-github,@upstash/context7-mcp@latest,@modelcontextprotocol/server-memory,@playwright/mcp@latest,@modelcontextprotocol/server-sequential-thinking, and Exa..claude/ecc-tools.json,.claude/identity.json, plus usage guide.codex/AGENTS.md..claude/homunculus/instincts/inherited/Behavioral_RL-instincts.yaml.Migration
/instinct-import .claude/homunculus/instincts/inherited/Behavioral_RL-instincts.yaml..codexconfig; keep credentials/private MCPs in~/.codex/config.toml.Written for commit c1c5915. Summary will update on new commits. Review in cubic