feat: add compound-engineering ECC bundle#2
Open
ecc-tools[bot] wants to merge 11 commits into
Open
Conversation
…gineering/SKILL.md)
…gineering/SKILL.md)
…gineering/agents/openai.yaml)
…ts/inherited/compound-engineering-instincts.yaml)
Reviewer's GuideAdds an auto-generated ECC bundle for the compound-engineering repo, wiring up Claude Code and Codex with shared repo-specific skills, a Codex MCP/multi-agent baseline, and optional continuous-learning instincts derived from repository analysis. File-Level Changes
Tips and commandsInteracting with Sourcery
Customizing Your ExperienceAccess your dashboard to:
Getting Help
|
![sourcery-ai[bot]](https://avatars.githubusercontent.com/in/48477?s=60&v=4){kind=small}
There was a problem hiding this comment.
Hey - I've found 2 issues, and left some high level feedback:
- The instincts YAML contains multiple overlapping entries for similar behaviors (e.g., file naming, import/export style, commit format, test location); consider consolidating or pruning duplicates to avoid conflicting guidance for downstream tools.
- Both SKILL.md files are wrapped in a top-level ```markdown code fence, which will cause the entire content to render as a code block rather than normal markdown; you may want to remove the outer fence so consumers see formatted headings and lists.
- There is a mismatch between the instincts (tests in tests/tests directories) and the SKILL.md description (tests colocated with source files); it would be helpful to reconcile this so the documented testing pattern is consistent across artifacts.
Prompt for AI Agents
Please address the comments from this code review:
## Overall Comments
- The instincts YAML contains multiple overlapping entries for similar behaviors (e.g., file naming, import/export style, commit format, test location); consider consolidating or pruning duplicates to avoid conflicting guidance for downstream tools.
- Both SKILL.md files are wrapped in a top-level ```markdown code fence, which will cause the entire content to render as a code block rather than normal markdown; you may want to remove the outer fence so consumers see formatted headings and lists.
- There is a mismatch between the instincts (tests in tests/__tests__ directories) and the SKILL.md description (tests colocated with source files); it would be helpful to reconcile this so the documented testing pattern is consistent across artifacts.
## Individual Comments
### Comment 1
<location path=".claude/homunculus/instincts/inherited/compound-engineering-instincts.yaml" line_range="134" />
<code_context>
+confidence: 0.9
+domain: code-style
+source: repo-analysis
+source_repo: aegntic/compound-engineering
+---
+
</code_context>
<issue_to_address>
**suggestion:** Align `source_repo` format across instincts to keep provenance consistent and machine-parseable.
Earlier entries use a full URL (`https://github.com/aegntic/compound-engineering`), while this one uses `aegntic/compound-engineering`. If any downstream tooling assumes a single format, this inconsistency may break provenance parsing. Please choose one representation and use it consistently for `source_repo` in this file.
```suggestion
source_repo: https://github.com/aegntic/compound-engineering
```
</issue_to_address>
### Comment 2
<location path=".codex/config.toml" line_range="14-23" />
<code_context>
+
+[mcp_servers.context7]
+command = "npx"
+args = ["-y", "@upstash/context7-mcp@latest"]
+
+[mcp_servers.exa]
+url = "https://mcp.exa.ai/mcp"
+
+[mcp_servers.memory]
+command = "npx"
+args = ["-y", "@modelcontextprotocol/server-memory"]
+
+[mcp_servers.playwright]
+command = "npx"
+args = ["-y", "@playwright/mcp@latest", "--extension"]
+
+[mcp_servers.sequential-thinking]
</code_context>
<issue_to_address>
**suggestion (bug_risk):** Avoid `@latest` in MCP server commands to reduce risk of unexpected breaking changes.
Several servers here are pinned to `@latest` (e.g., `@upstash/context7-mcp@latest`, `@playwright/mcp@latest`). This tightly couples behavior to upstream releases and can introduce regressions without any changes in this repo. Please pin these to specific versions and update deliberately as needed.
Suggested implementation:
```
[mcp_servers.context7]
command = "npx"
args = ["-y", "@upstash/context7-mcp@X.Y.Z"]
```
```
[mcp_servers.playwright]
command = "npx"
args = ["-y", "@playwright/mcp@A.B.C", "--extension"]
```
Replace the placeholder versions `X.Y.Z` and `A.B.C` with specific, tested versions of `@upstash/context7-mcp` and `@playwright/mcp` that are compatible with your environment (for example, the versions currently deployed in production or known stable releases). When upgrading these MCP servers in the future, update the pinned versions here as part of a deliberate, tested change.
</issue_to_address>Help me be more useful! Please click 👍 or 👎 on each comment and I'll use the feedback to improve your reviews.
| confidence: 0.9 | ||
| domain: code-style | ||
| source: repo-analysis | ||
| source_repo: aegntic/compound-engineering |
There was a problem hiding this comment.
suggestion: Align source_repo format across instincts to keep provenance consistent and machine-parseable.
Earlier entries use a full URL (https://github.com/aegntic/compound-engineering), while this one uses aegntic/compound-engineering. If any downstream tooling assumes a single format, this inconsistency may break provenance parsing. Please choose one representation and use it consistently for source_repo in this file.
Suggested change
| source_repo: aegntic/compound-engineering | |
| source_repo: https://github.com/aegntic/compound-engineering |
Comment on lines
+14
to
+23
| args = ["-y", "@upstash/context7-mcp@latest"] | ||
|
|
||
| [mcp_servers.exa] | ||
| url = "https://mcp.exa.ai/mcp" | ||
|
|
||
| [mcp_servers.memory] | ||
| command = "npx" | ||
| args = ["-y", "@modelcontextprotocol/server-memory"] | ||
|
|
||
| [mcp_servers.playwright] |
There was a problem hiding this comment.
suggestion (bug_risk): Avoid @latest in MCP server commands to reduce risk of unexpected breaking changes.
Several servers here are pinned to @latest (e.g., @upstash/context7-mcp@latest, @playwright/mcp@latest). This tightly couples behavior to upstream releases and can introduce regressions without any changes in this repo. Please pin these to specific versions and update deliberately as needed.
Suggested implementation:
[mcp_servers.context7]
command = "npx"
args = ["-y", "@upstash/context7-mcp@X.Y.Z"]
[mcp_servers.playwright]
command = "npx"
args = ["-y", "@playwright/mcp@A.B.C", "--extension"]
Replace the placeholder versions X.Y.Z and A.B.C with specific, tested versions of @upstash/context7-mcp and @playwright/mcp that are compatible with your environment (for example, the versions currently deployed in production or known stable releases). When upgrading these MCP servers in the future, update the pinned versions here as part of a deliberate, tested change.
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/compound-engineering/SKILL.md.agents/skills/compound-engineering/SKILL.md.agents/skills/compound-engineering/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/compound-engineering-instincts.yamlOptional: Continuous Learning (16 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 Sourcery
Add repository-specific ECC configuration and skills for Claude Code and Codex, including development conventions, multi-agent setups, and continuous-learning instincts.
New Features:
Enhancements:
Documentation: