getAvailablePackageManagers() spawned where.exe/which for each package
manager (npm, pnpm, yarn, bun). During SessionStart hooks, these 4+
child processes combined with Bun's own initialization exceeded the
spawn limit on Windows, freezing the terminal.
Fix: Remove process spawning from the hot path. Steps 1-5 of detection
(env var, project config, package.json, lock file, global config) already
cover all file-based detection. If none match, default to npm without
spawning. Also fix getSelectionPrompt() to list supported PMs without
checking availability.
session-end.js: Extract meaningful summaries from CLAUDE_TRANSCRIPT_PATH
instead of writing blank template files. Pulls user messages, tools used,
and files modified from the session transcript JSONL.
session-start.js: Output the latest session summary to stdout (via the
output() helper) so it gets injected into Claude's conversation context,
instead of only logging to stderr which just shows briefly in the terminal.
Replace relative require('./scripts/lib/...') with dynamic path resolution
using CLAUDE_PLUGIN_ROOT env var (set by Claude Code for plugins) with
fallback to ~/.claude/ for manual installations. This fixes /sessions
command failing when ECC is installed as a plugin.
* fix: resolve multiple reported issues (#205, #182, #188, #172, #173)
- fix(observe.sh): replace triple-quote JSON parsing with stdin pipe to
prevent ~49% parse failures on payloads with quotes/backslashes/unicode
- fix(hooks.json): correct matcher syntax to use simple tool name regexes
instead of unsupported logical expressions; move command/path filtering
into hook scripts; use exit code 2 for blocking hooks
- fix(skills): quote YAML descriptions containing colons in 3 skill files
and add missing frontmatter to 2 skill files for Codex CLI compatibility
- feat(rules): add paths: filters to all 15 language-specific rule files
so they only load when working on matching file types
- fix(agents): align model fields with CONTRIBUTING.md recommendations
(opus for planner/architect, sonnet for reviewers/workers, haiku for
doc-updater)
* ci: use AgentShield GitHub Action instead of npx
Switch from npx ecc-agentshield to uses: affaan-m/agentshield@v1
for proper GitHub Action demo and marketplace visibility.
New skill: /security-scan wraps ecc-agentshield to audit .claude/ configs
for vulnerabilities, misconfigs, and injection risks.
Covers: CLAUDE.md secrets, settings.json permissions, MCP server risks,
hook injection, agent tool restrictions. Produces A-F security grade.
Also adds AgentShield section to Ecosystem Tools in README with
links to GitHub repo and npm package.
The .opencode/ directory was missing from the files array, so the npm
package only shipped Claude Code and Cursor configs. Selectively include
.opencode/ subdirectories to avoid bundling node_modules and dist.
Add complete .cursor/ directory with rules, agents, skills, commands,
and MCP config adapted for Cursor's format. This makes ecc-universal
a truly cross-IDE package supporting Claude Code, Cursor, and OpenCode.
- 27 rule files with YAML frontmatter (description, globs, alwaysApply)
- 13 agent files with full model IDs and readonly flags
- 30 skill directories (identical Agent Skills standard, no translation)
- 31 command files (5 multi-* stubbed for missing codeagent-wrapper)
- MCP config with Cursor env interpolation syntax
- README.md and MIGRATION.md documentation
- install.sh --target cursor flag for project-scoped installation
- package.json updated with .cursor/ in files and cursor keywords
Adding awesome-agent-skills as a related resource.
A curated list of 40+ AI Agent Skills with cross-platform installer (bash/PowerShell), supporting Cursor, Claude Code, Copilot, Windsurf, Codex, and OpenCode.
GitHub: https://github.com/JackyST0/awesome-agent-skills
- Remove trailing whitespace from inline code
- Add blank line before table
- Fix heading levels to ensure proper hierarchy
- Convert bare URLs to markdown links
- Fix PluginContext → PluginInput type rename in @opencode-ai/plugin
- Import tool from @opencode-ai/plugin/tool subpath (fixes broken barrel export)
- Update client.app.log() calls to use new options-object API signature
- Stringify tool execute return values (SDK now requires Promise<string>)
- Add .js extensions to relative imports for NodeNext module resolution
- Update README star count (42K+) and contributor count (24)
- Add forks (5K+) and contributors (22) badges
- Add Python and Java language badges
- Add stats summary line (41K+ stars, 5K+ forks, 22 contributors)
- Add What's New section covering v1.2.0 through v1.4.1
- Update What's Inside tree with new commands (PM2, multi-agent)
- Update skills list with Django, Spring Boot, Python, configure-ecc
- Update agents list with python-reviewer, database-reviewer
- Update OpenCode feature parity table with latest counts
- Update contribution ideas to reflect current language coverage
parse_instinct_file() was appending the instinct and resetting state
when frontmatter ended (second ---), before any content lines could be
collected. This caused all content (Action, Evidence, Examples) to be
lost during import.
Fix: only set in_frontmatter=False when frontmatter ends. The existing
logic at the start of next frontmatter (or EOF) correctly appends the
instinct with its collected content.
Fixes#148
Add a new skill that guides users through selective installation of
ECC skills and rules via AskUserQuestion. Clones the repo to /tmp,
lets users choose components and install level (user/project), verifies
path correctness, offers optimization, and cleans up on completion.
Co-authored-by: Hor1zonZzz <Hor1zonZzz@users.noreply.github.com>
Co-authored-by: Claude Opus 4.5 <noreply@anthropic.com>
Major OpenCode integration overhaul:
- llms.txt: Comprehensive OpenCode documentation for LLMs (642 lines)
- .opencode/plugins/ecc-hooks.ts: All Claude Code hooks translated to OpenCode's plugin system
- .opencode/tools/*.ts: 3 custom tools (run-tests, check-coverage, security-audit)
- .opencode/commands/*.md: All 24 commands in OpenCode format
- .opencode/package.json: npm package structure for opencode-ecc
- .opencode/index.ts: Main plugin entry point
- Delete incorrect LIMITATIONS.md (hooks ARE supported via plugins)
- Rewrite MIGRATION.md with correct hook event mapping
- Update README.md OpenCode section to show full feature parity
OpenCode has 20+ events vs Claude Code's 3 phases:
- PreToolUse → tool.execute.before
- PostToolUse → tool.execute.after
- Stop → session.idle
- SessionStart → session.created
- SessionEnd → session.deleted
- Plus: file.edited, file.watcher.updated, permission.asked, todo.updated
- 12 agents: Full parity
- 24 commands: Full parity (+1 from original 23)
- 16 skills: Full parity
- Hooks: OpenCode has MORE (20+ events vs 3 phases)
- Custom Tools: 3 native OpenCode tools
The OpenCode configuration can now be:
1. Used directly: cd everything-claude-code && opencode
2. Installed via npm: npm install opencode-ecc
Add a new /sessions command to manage Claude Code session history with
alias support for quick access to previous sessions.
Features:
- List sessions with pagination and filtering (by date, ID)
- Load and view session content and metadata
- Create memorable aliases for sessions
- Remove aliases
- Display session statistics (lines, items, size)
- List all aliases
New libraries:
- scripts/lib/session-manager.js - Core session CRUD operations
- scripts/lib/session-aliases.js - Alias management with atomic saves
New command:
- commands/sessions.md - Complete command with embedded scripts
Modified:
- scripts/lib/utils.js - Add getAliasesPath() export
- scripts/hooks/session-start.js - Show available aliases on session start
Session format support:
- Old: YYYY-MM-DD-session.tmp
- New: YYYY-MM-DD-<short-id>-session.tmp
Aliases are stored in ~/.claude/session-aliases.json with Windows-
compatible atomic writes and backup support.
Co-authored-by: 王志坚 <wangzhijian10@bgyfw.com>
Co-authored-by: Claude <noreply@anthropic.com>
Fixes#113
The instinct commands referenced hardcoded paths that only work with
manual installation (~/.claude/skills/...). When installed as a plugin,
files are at ~/.claude/plugins/cache/.../skills/...
Changes:
- Updated instinct-status, instinct-import, evolve commands to use
${CLAUDE_PLUGIN_ROOT} with fallback to manual path
- Updated observe.sh hook documentation with both install methods
- Updated SKILL.md with plugin vs manual installation instructions
- Removed duplicate commands from skills/continuous-learning-v2/commands/
(already exist in commands/)
Users should use ${CLAUDE_PLUGIN_ROOT} in their hooks config when
installed as a plugin.
BREAKING: Commands are now loaded as skills per Claude Code's unified architecture.
Changes:
- Removed separate `commands` field from plugin.json
- Added `./commands/` to `skills` array
- Bumped version to 1.2.0
- Updated description to reflect unified structure
This aligns with Claude Code's documentation which has merged skills and
slash commands into a single concept. Both directories are now loaded
as skills, maintaining backwards compatibility.
Closes#111
- Fix 16 ESLint no-unused-vars errors across hook scripts and tests
- Add eslint-disable comment for intentional control-regex in ANSI stripper
- Update session file test to use getSessionIdShort() instead of hardcoded 'default'
(reflects PR #110's project-name fallback behavior)
- Add marketing/ to .gitignore (local drafts)
- Add skill-create-output.js (terminal output formatter)
All 69 tests now pass. CI should be green.
- Add minimum Claude Code version requirement (v2.1.0+)
- Document hooks auto-loading behavior to prevent flip-flop cycles
- Add flip-flop history table to PLUGIN_SCHEMA_NOTES.md
- Reference issues #29, #52, #103 that were caused by this confusion
- Explain that regression test now prevents reintroduction
This documentation should prevent future confusion about whether to
add/remove the hooks field from plugin.json.
