docs: Add repo assessment, commands reference, and evaluation docs#986
Conversation
There was a problem hiding this comment.
Your free trial has ended. If you'd like to continue receiving code reviews, you can add a payment method here.
|
Analysis Failed
Troubleshooting
Retry: |
|
Caution Review failedThe pull request is closed. ℹ️ Recent review info⚙️ Run configurationConfiguration used: defaults Review profile: CHILL Plan: Pro Run ID: 📒 Files selected for processing (4)
📝 WalkthroughWalkthroughAdded four documentation files: Node.js project rules at Changes
Estimated code review effort🎯 1 (Trivial) | ⏱️ ~4 minutes Suggested reviewers
Poem
🚥 Pre-merge checks | ✅ 3✅ Passed checks (3 passed)
✏️ Tip: You can configure your own custom pre-merge checks in the settings. ✨ Finishing Touches🧪 Generate unit tests (beta)
Thanks for using CodeRabbit! It's free for OSS, and your support helps us grow. If you like it, consider giving us a shout-out. Comment |
There was a problem hiding this comment.
Actionable comments posted: 4
🤖 Prompt for all review comments with AI agents
Verify each finding against the current code and only fix it if needed.
Inline comments:
In @.claude/rules/node.md:
- Line 33: Update the documentation line that incorrectly refers to
CLAUDE_ECC_MODE: replace that reference with the actual gating environment
variables used by the hook layer (ECC_HOOK_PROFILE and ECC_DISABLED_HOOKS) and
mention that run-with-flags.js uses ECC_HOOK_PROFILE (with ECC_DISABLED_HOOKS as
the disable list) to control hook enablement; update any surrounding text to
consistently reference ECC_HOOK_PROFILE and ECC_DISABLED_HOOKS so guidance
matches the actual gating implementation.
- Line 30: The rule incorrectly requires all hook scripts to read JSON from
stdin via fs.readFileSync(0), but hooks may instead be invoked through
run-with-flags.js which calls the exported run(rawInput) function; update the
doc/rule to allow both input patterns by removing the absolute "always"
statement and document that hook implementations should accept either reading
JSON from stdin or supporting an exported run(rawInput) entrypoint (reference
run-with-flags.js and the run(rawInput) export) so contributors can follow the
correct invocation pattern.
In `@EVALUATION.md`:
- Around line 44-45: Update the install profile names in the EVALUATION.md table
and example commands: change the table row labeled "Install profiles" to list
the actual supported profiles "core, developer, security, research, full" and
replace any example CLI usage of `ecc install --profile minimal` (and `--profile
standard`/`--profile enterprise` if present) with valid profiles such as `ecc
install --profile core` (or `developer`, `security`, `research`, `full`) so
examples match manifest-supported profiles and avoid "Unknown install profile"
errors.
In `@REPO-ASSESSMENT.md`:
- Line 171: Replace the hardcoded local path "/home/user/everything-claude-code"
in REPO-ASSESSMENT.md with a portable instruction such as "cd <path-to-clone>"
or "cd from your local repo root" so setup steps are not tied to a specific
user; update the single line containing that path to use a placeholder like
<path-to-clone> or wording "from your local repo root" for clarity and
portability.
🪄 Autofix (Beta)
Fix all unresolved CodeRabbit comments on this PR:
- Push a commit to this branch (recommended)
- Create a new PR with the fixes
ℹ️ Review info
⚙️ Run configuration
Configuration used: defaults
Review profile: CHILL
Plan: Pro
Run ID: fc6d2514-627b-405b-a3a4-a2b3be50c87e
📒 Files selected for processing (4)
.claude/rules/node.mdCOMMANDS-QUICK-REF.mdEVALUATION.mdREPO-ASSESSMENT.md
There was a problem hiding this comment.
Your free trial has ended. If you'd like to continue receiving code reviews, you can add a payment method here.
|
REPO-ASSESSMENT.md — Complete fork health check, available components inventory (28 agents, 116 skills, 59 commands, 60+ rules), and five install profiles (core, developer, security, research, full) with setup recommendations. COMMANDS-QUICK-REF.md — Quick reference guide for all 59 slash commands organized by workflow category (core, testing, code review, build fixers, planning, session management, learning, refactoring, docs, loops, project infrastructure) EVALUATION.md — Gap analysis comparing current minimal setup (1 hook, 0 agents/skills/commands) against the full repo capabilities, with prioritized recommendations for immediate value |
Compares everything-claude-code v1.9.0 against the minimal ~/.claude/ installation. Documents gap analysis across agents, skills, commands, hooks, and rules. https://claude.ai/code/session_014SqRA9y6HwVVPGeSCJfwVF
Covers fork health, gap analysis, install profile guidance, and priority components to add to the current minimal ~/.claude/ setup. https://claude.ai/code/session_014SqRA9y6HwVVPGeSCJfwVF
- Expand permissions.allow (git, node, npm, npx, ls, cat, Read, Edit, Write, Glob, Grep) to reduce approval prompts - Set CLAUDE_ECC_MODE=standard in env for consistent hook profile - Gate stop-hook-git-check.sh behind ECC_GIT_CHECK=1 to prevent blocking mid-session - Add project-level Node.js rules for ECC repo (stack, file conventions, hook dev standards) - observe.sh confirmed already async — no change needed https://claude.ai/code/session_014SqRA9y6HwVVPGeSCJfwVF
a16c879 to
c865d4c
Compare
|
Analysis Failed
Troubleshooting
Retry: |
Greptile SummaryThis PR adds four documentation files to improve onboarding and daily-use guidance for the Key findings:
Confidence Score: 3/5Not safe to merge as-is — two install commands are incorrect and will fail for users who follow them verbatim, and component counts conflict with the authoritative AGENTS.md throughout all three major docs. There are three P1 findings: the EVALUATION.md (wrong install command, stale branch, stale counts) and REPO-ASSESSMENT.md (invalid npx command, stale counts) need fixes before merge. COMMANDS-QUICK-REF.md has minor duplicate-entry and count issues. Important Files Changed
Flowchart%%{init: {'theme': 'neutral'}}%%
flowchart TD
A[User wants to install ECC] --> B{Choose install profile}
B --> C[core: Minimal footprint]
B --> D[developer: Recommended for daily dev]
B --> E[security: Audits and vulnerability reviews]
B --> F[research: Content and market research]
B --> G[full: All agents and skills]
C --> H[ecc plan --profile core]
D --> I[ecc plan --profile developer]
E --> J[ecc plan --profile security]
F --> K[ecc plan --profile research]
G --> L[ecc plan --profile full]
H & I & J & K & L --> M[ecc install]
M --> N[Optionally add language rules]
N --> O[Enable MCP Context7]
O --> P[Review hook additions]
Reviews (1): Last reviewed commit: "docs: fix ECC setup reference drift" | Re-trigger Greptile |
| # Repo Evaluation vs Current Setup | ||
|
|
||
| **Date:** 2026-03-21 | ||
| **Branch:** `claude/evaluate-repo-comparison-ASZ9Y` |
There was a problem hiding this comment.
Stale session-branch reference should be removed
Line 4 hard-codes claude/evaluate-repo-comparison-ASZ9Y, which is the ephemeral branch from the AI session that generated this file. After this PR is merged that branch will not exist, making the doc look like an unfinished draft rather than reference material. The **Branch:** field adds no value for a documentation file committed to main.
| **Branch:** `claude/evaluate-repo-comparison-ASZ9Y` | |
| **Branch:** `main` |
| Run `ecc install --profile core` to get: | ||
| - Core agents (code-reviewer, planner, tdd-guide, security-reviewer) | ||
| - Essential skills (tdd-workflow, coding-standards, security-review) | ||
| - Key commands (/tdd, /plan, /code-review, /build-fix) | ||
|
|
||
| ### Full install | ||
| Run `ecc install --profile full` to get all 28 agents, 116 skills, and 59 commands. |
There was a problem hiding this comment.
ecc install --profile routes to the wrong script
ecc install is mapped to install-apply.js in scripts/ecc.js (line 9). The --profile flag belongs to the plan step (install-plan.js / ecc plan), not the apply step. A user who runs ecc install --profile core verbatim will skip the planning step and likely end up with nothing installed (or the apply script will error because no plan file exists yet).
The correct two-step invocation, consistent with REPO-ASSESSMENT.md and CLAUDE.md, is:
ecc plan --profile core
ecc install
The same problem applies to the full-profile block (ecc install --profile full on line 98).
| Run `ecc install --profile core` to get: | |
| - Core agents (code-reviewer, planner, tdd-guide, security-reviewer) | |
| - Essential skills (tdd-workflow, coding-standards, security-review) | |
| - Key commands (/tdd, /plan, /code-review, /build-fix) | |
| ### Full install | |
| Run `ecc install --profile full` to get all 28 agents, 116 skills, and 59 commands. | |
| Run `ecc plan --profile core && ecc install` to get: |
| | Component | Repo | | ||
| |-----------|------| | ||
| | Agents | 28 | | ||
| | Skills | 116 | | ||
| | Commands | 59 | | ||
| | Rules sets | 12 languages + common (60+ rule files) | | ||
| | Hooks | Comprehensive system (PreToolUse, PostToolUse, SessionStart, Stop) | | ||
| | MCP configs | 1 (Context7 + others) | | ||
| | Schemas | 9 JSON validators | | ||
| | Scripts/CLI | 46+ Node.js modules + multiple CLIs | | ||
| | Tests | 58 test files | | ||
| | Install profiles | core, developer, security, research, full | | ||
| | Supported harnesses | Claude Code, Codex, Cursor, OpenCode | |
There was a problem hiding this comment.
Component counts differ from the authoritative
AGENTS.md
AGENTS.md (the canonical reference file) states 125 skills, 60 commands, and 14 MCP server configurations. This file (and REPO-ASSESSMENT.md) report 116 skills, 59 commands, and 1 MCP config, which will mislead users trying to understand the scope of the repository.
The same discrepancy appears in REPO-ASSESSMENT.md (lines 29–35) and the COMMANDS-QUICK-REF.md header ("59 slash commands"). Please reconcile with AGENTS.md before merging so all three docs tell a consistent story.
| # Commands Quick Reference | ||
|
|
||
| > 59 slash commands installed globally. Type `/` in any Claude Code session to invoke. |
There was a problem hiding this comment.
Header count and duplicate entries are inconsistent
The header claims "59 slash commands", but AGENTS.md says 60. More concretely, /tdd appears in both Core Workflow (line 14) and Testing (line 25), /code-review in both Core Workflow (line 16) and Code Review (line 38), and /plan in both Core Workflow (line 13) and Planning & Architecture (line 59). Each duplicate inflates the apparent command count without adding information.
Consider either (a) removing the duplicates from "Core Workflow" and keeping them only in their category section, or (b) adding a note like (see Testing) to make the cross-listing intentional and clear.
|
|
||
| ### Repo: `Infiniteyieldai/everything-claude-code` | ||
|
|
||
| This is a **fork of `affaan-m/everything-claude-code`** (the upstream project with 50K+ stars, 6K+ forks). |
There was a problem hiding this comment.
Hard-coded star/fork counts will become stale immediately
"50K+ stars, 6K+ forks" is a point-in-time claim. These numbers will be outdated within days and may already be inaccurate. If the goal is to convey that the upstream is popular, a vaguer phrase like "a widely-adopted upstream project" is more durable. If the exact figures are desired, link to the GitHub page instead of hard-coding them.
| ### Option C: Install from npm (simplest for fresh machines) | ||
| ```bash | ||
| npx ecc-universal install --profile developer | ||
| ``` | ||
| No need to clone the repo. This is the recommended install method for most users. |
There was a problem hiding this comment.
npx ecc-universal install is not a valid command
The package.json bin map exposes ecc (→ scripts/ecc.js), not ecc-universal. The correct install-from-npm invocation is npx ecc install, not npx ecc-universal install. Running the command as written will fail with "unknown command" for users who try the npm path.
| ### Option C: Install from npm (simplest for fresh machines) | |
| ```bash | |
| npx ecc-universal install --profile developer | |
| ``` | |
| No need to clone the repo. This is the recommended install method for most users. | |
| ```bash | |
| npx ecc plan --profile developer | |
| npx ecc install |
What Changed
Added three comprehensive documentation files to guide setup and usage of the everything-claude-code repository:
Why This Change
The repository provides a powerful toolkit (28 agents, 116 skills, 59 commands) but lacks clear guidance on:
These docs provide a clear onboarding path and reference material for both users installing ECC and contributors working on the codebase.
Testing Done
Type of Change
docs:DocumentationSecurity & Quality Checklist
docs:prefix)Documentation
https://claude.ai/code/session_014SqRA9y6HwVVPGeSCJfwVF
Summary by cubic
Adds repo assessment, commands quick reference, setup evaluation, and Node.js rules to streamline onboarding, workflows, and contributor standards. Documents fork health (synced to upstream v1.9.0) and provides install profiles with copy‑paste commands.
install-plan/install-applysteps, priority additions, and hook upgrades.~/.claude/(1 Stop hook) vs repo (28 agents, 116 skills, 59 commands) with install and rules recommendations.Node.jsstandards (Node ≥18, CommonJS,@eslint/jsflat config, c8, markdownlint), file conventions, hook development viarun-with-flags.js, and testing requirements.Written for commit c865d4c. Summary will update on new commits.
Summary by CodeRabbit