mirror of
https://github.com/affaan-m/ECC.git
synced 2026-10-16 21:25:42 +02:00
fix(ci): skip POSIX $1 assignment in skill host-compat lint
Keep ${1} and echo $1 as Claude substitutions. Do not fail VAR=$1
function parameters or Perl/awk $1 compares. Sync catalog counts to
68 agents, 293 skills, and 95 commands after rebase onto main.
Co-authored-by: Matt Van Horn <mvanhorn@users.noreply.github.com>
This commit is contained in:
Cursor Agent
co-authored by
Matt Van Horn
Matt Van Horn
parent
0895f0d8b5
commit
d442f5c75e
@@ -11,7 +11,7 @@
|
||||
{
|
||||
"name": "ecc",
|
||||
"source": "./",
|
||||
"description": "Harness-native ECC operator layer - 68 agents, 292 skills, 94 legacy command shims, reusable hooks, rules, selective install profiles, and production-ready workflows for Claude Code, Codex, OpenCode, Cursor, and related agent harnesses",
|
||||
"description": "Harness-native ECC operator layer - 68 agents, 293 skills, 95 legacy command shims, reusable hooks, rules, selective install profiles, and production-ready workflows for Claude Code, Codex, OpenCode, Cursor, and related agent harnesses",
|
||||
"version": "2.2.2",
|
||||
"author": {
|
||||
"name": "Affaan Mustafa",
|
||||
|
||||
@@ -1,7 +1,7 @@
|
||||
{
|
||||
"name": "ecc",
|
||||
"version": "2.2.2",
|
||||
"description": "Harness-native ECC plugin for engineering teams - 68 agents, 292 skills, 94 legacy command shims, reusable hooks, rules, MCP conventions, and operator workflows for Claude Code plus adjacent agent harnesses",
|
||||
"description": "Harness-native ECC plugin for engineering teams - 68 agents, 293 skills, 95 legacy command shims, reusable hooks, rules, MCP conventions, and operator workflows for Claude Code plus adjacent agent harnesses",
|
||||
"author": {
|
||||
"name": "Affaan Mustafa",
|
||||
"url": "https://x.com/affaanmustafa"
|
||||
|
||||
@@ -1,6 +1,6 @@
|
||||
# Everything Claude Code (ECC) — Agent Instructions
|
||||
|
||||
This is a **production-ready AI coding plugin** providing 68 specialized agents, 292 skills, 94 commands, and automated hook workflows for software development.
|
||||
This is a **production-ready AI coding plugin** providing 68 specialized agents, 293 skills, 95 commands, and automated hook workflows for software development.
|
||||
|
||||
**Version:** 2.2.2
|
||||
|
||||
@@ -154,8 +154,8 @@ Troubleshoot failures: check test isolation → verify mocks → fix implementat
|
||||
|
||||
```
|
||||
agents/ — 68 specialized subagents
|
||||
skills/ — 292 workflow skills and domain knowledge
|
||||
commands/ — 94 slash commands
|
||||
skills/ — 293 workflow skills and domain knowledge
|
||||
commands/ — 95 slash commands
|
||||
hooks/ — Trigger-based automations
|
||||
rules/ — Always-follow guidelines (common + per-language)
|
||||
scripts/ — Cross-platform Node.js utilities
|
||||
|
||||
@@ -138,13 +138,13 @@ Instead of rebuilding that process in every prompt, you install it once and make
|
||||
|
||||
ECC is MIT-licensed open source. It works best with Claude Code today, has a supported Codex sync path, and provides capability-limited adapters for Cursor, OpenCode, Gemini, Zed, GitHub Copilot, Antigravity, Qwen, and other harnesses. See the [support status matrix](#platform-support) before assuming feature parity.
|
||||
|
||||
Access to 68 agents, 292 skills, and 94 legacy command shims, plus hooks, rules, memory, continuous learning, and AgentShield security scanning. The agents are specialized for planning, review, build repair, security, architecture, and domain work.
|
||||
Access to 68 agents, 293 skills, and 95 legacy command shims, plus hooks, rules, memory, continuous learning, and AgentShield security scanning. The agents are specialized for planning, review, build repair, security, architecture, and domain work.
|
||||
|
||||
| Included | Count | What it gives you |
|
||||
| ---------------- | ----------: | ------------------------------------------------------------------------------------ |
|
||||
| Agents | 68 agents | Planning, review, build repair, security, architecture, and domain work |
|
||||
| Skills | 292 skills | TDD, research, security, docs, frontend, data, ML, operations, and more |
|
||||
| Commands | 94 commands | Convenient entry points while ECC moves to a skills-first surface |
|
||||
| Skills | 293 skills | TDD, research, security, docs, frontend, data, ML, operations, and more |
|
||||
| Commands | 95 commands | Convenient entry points while ECC moves to a skills-first surface |
|
||||
| Hooks and memory | Runtime | Enforcement, session summaries, continuous learning, instincts, and context controls |
|
||||
| Rules | Selective | Always-loaded standards you choose by language or project |
|
||||
| AgentShield | Included | Scanning for prompts, hooks, MCP config, permissions, secrets, and agent files |
|
||||
|
||||
+1
-1
@@ -196,7 +196,7 @@ Copy-Item -Recurse rules/typescript "$HOME/.claude/rules/"
|
||||
/plugin list ecc@ecc
|
||||
```
|
||||
|
||||
**完成！** 你现在可以使用 68 个代理、292 个技能和 94 个命令。
|
||||
**完成！** 你现在可以使用 68 个代理、293 个技能和 95 个命令。
|
||||
|
||||
### multi-* 命令需要额外配置
|
||||
|
||||
|
||||
+3
-3
@@ -1,6 +1,6 @@
|
||||
# Everything Claude Code (ECC) — Agent Talimatları
|
||||
|
||||
Bu, yazılım geliştirme için 68 özel agent, 292 skill, 94 command ve otomatik hook iş akışları sağlayan **üretime hazır bir AI kodlama eklentisidir**.
|
||||
Bu, yazılım geliştirme için 68 özel agent, 293 skill, 95 command ve otomatik hook iş akışları sağlayan **üretime hazır bir AI kodlama eklentisidir**.
|
||||
|
||||
**Sürüm:** 2.2.2
|
||||
|
||||
@@ -142,8 +142,8 @@ Başarısızlık sorunlarını giderin: test izolasyonunu kontrol edin → mockl
|
||||
|
||||
```
|
||||
agents/ — 68 özel subagent
|
||||
skills/ — 292 iş akışı skillleri ve alan bilgisi
|
||||
commands/ — 94 slash command
|
||||
skills/ — 293 iş akışı skillleri ve alan bilgisi
|
||||
commands/ — 95 slash command
|
||||
hooks/ — Tetikleyici tabanlı otomasyonlar
|
||||
rules/ — Her zaman uyulması gereken kurallar (ortak + dile özel)
|
||||
scripts/ — Platformlar arası Node.js yardımcı programları
|
||||
|
||||
@@ -1,6 +1,6 @@
|
||||
# Everything Claude Code (ECC) — 智能体指令
|
||||
|
||||
这是一个**生产就绪的 AI 编码插件**，提供 68 个专业代理、292 项技能、94 条命令以及自动化钩子工作流，用于软件开发。
|
||||
这是一个**生产就绪的 AI 编码插件**，提供 68 个专业代理、293 项技能、95 条命令以及自动化钩子工作流，用于软件开发。
|
||||
|
||||
**版本:** 2.2.2
|
||||
|
||||
@@ -147,8 +147,8 @@
|
||||
|
||||
```
|
||||
agents/ — 68 个专业子代理
|
||||
skills/ — 292 个工作流技能和领域知识
|
||||
commands/ — 94 个斜杠命令
|
||||
skills/ — 293 个工作流技能和领域知识
|
||||
commands/ — 95 个斜杠命令
|
||||
hooks/ — 基于触发的自动化
|
||||
rules/ — 始终遵循的指导方针（通用 + 每种语言）
|
||||
scripts/ — 跨平台 Node.js 实用工具
|
||||
|
||||
@@ -260,7 +260,7 @@ Copy-Item -Recurse rules/typescript "$HOME/.claude/rules/"
|
||||
/plugin list ecc@ecc
|
||||
```
|
||||
|
||||
**搞定！** 你现在可以使用 68 个智能体、292 项技能和 94 个命令了。
|
||||
**搞定！** 你现在可以使用 68 个智能体、293 项技能和 95 个命令了。
|
||||
|
||||
***
|
||||
|
||||
@@ -1173,8 +1173,8 @@ opencode
|
||||
| 功能特性 | Claude Code | OpenCode | 状态 |
|
||||
|---------|---------------|----------|--------|
|
||||
| 智能体 | PASS: 68 个 | PASS: 12 个 | **Claude Code 领先** |
|
||||
| 命令 | PASS: 94 个 | PASS: 35 个 | **Claude Code 领先** |
|
||||
| 技能 | PASS: 292 项 | PASS: 37 项 | **Claude Code 领先** |
|
||||
| 命令 | PASS: 95 个 | PASS: 35 个 | **Claude Code 领先** |
|
||||
| 技能 | PASS: 293 项 | PASS: 37 项 | **Claude Code 领先** |
|
||||
| 钩子 | PASS: 8 种事件类型 | PASS: 11 种事件 | **OpenCode 更多！** |
|
||||
| 规则 | PASS: 29 条 | PASS: 13 条指令 | **Claude Code 领先** |
|
||||
| MCP 服务器 | PASS: 14 个 | PASS: 完整 | **完全对等** |
|
||||
@@ -1281,8 +1281,8 @@ ECC 是**第一个最大化利用每个主要 AI 编码工具的插件**。以
|
||||
| 功能特性 | Claude Code | Cursor IDE | Codex CLI | OpenCode |
|
||||
|---------|-----------------------|------------|-----------|----------|
|
||||
| **智能体** | 68 | 共享 (AGENTS.md) | 共享 (AGENTS.md) | 12 |
|
||||
| **命令** | 94 | 共享 | 基于指令 | 35 |
|
||||
| **技能** | 292 | 共享 | 10 (原生格式) | 37 |
|
||||
| **命令** | 95 | 共享 | 基于指令 | 35 |
|
||||
| **技能** | 293 | 共享 | 10 (原生格式) | 37 |
|
||||
| **钩子事件** | 8 种类型 | 15 种类型 | SessionStart（1 种类型） | 11 种类型 |
|
||||
| **钩子脚本** | 20+ 个脚本 | 16 个脚本 (DRY 适配器) | 1 个 SessionStart 引导脚本 | 插件钩子 |
|
||||
| **规则** | 34 (通用 + 语言) | 34 (YAML 前页) | 基于指令 | 13 条指令 |
|
||||
|
||||
@@ -335,8 +335,8 @@
|
||||
"skills/plankton-code-quality",
|
||||
"skills/production-audit",
|
||||
"skills/skill-comply",
|
||||
"skills/skill-scout",
|
||||
"skills/skill-host-compat",
|
||||
"skills/skill-scout",
|
||||
"skills/skill-stocktake",
|
||||
"skills/strategic-compact",
|
||||
"skills/tdd-workflow",
|
||||
|
||||
@@ -48,9 +48,9 @@ const CLAUDE_SUBSTITUTION_PATTERNS = [
|
||||
{ token: '${CLAUDE_PLUGIN_ROOT}', regex: /\$\{CLAUDE_PLUGIN_ROOT\}/g },
|
||||
{ token: '$CLAUDE_PLUGIN_ROOT', regex: /\$CLAUDE_PLUGIN_ROOT\b/g },
|
||||
{ token: '$ARGUMENTS', regex: /\$ARGUMENTS\b|\$\{ARGUMENTS\}/g },
|
||||
// Bare $1 is a Perl/awk capture in many examples; flag the Claude skill
|
||||
// form ${1} and $1 used as a shell positional, not `$1 <number>`.
|
||||
{ token: '$1', regex: /\$\{1\}|(?<![\w$])\$1(?!\d)(?!\s*[<>=])/g },
|
||||
// Claude skill form ${1}. Bare $1 is handled in findSubstitutionTokens so
|
||||
// POSIX `VAR=$1` and Perl/awk `$1 < 80` are not treated as Claude args.
|
||||
{ token: '$1', regex: /\$\{1\}|(?<![\w$])\$1(?!\d)/g },
|
||||
];
|
||||
|
||||
const EXECUTABLE_FENCE_LANGS = new Set(['bash', 'sh', 'zsh']);
|
||||
@@ -189,12 +189,30 @@ function precedingAllowsToken(body, fenceStart) {
|
||||
return /anti-pattern/i.test(window) || /do not/i.test(window);
|
||||
}
|
||||
|
||||
function isPortableBareDollarOne(fenceContent, index) {
|
||||
const before = fenceContent.slice(0, index);
|
||||
const after = fenceContent.slice(index + 2);
|
||||
// Perl/awk numeric compare: `$1 < 80`, `$1>=0`.
|
||||
if (/^\s*[<>=]/.test(after)) return true;
|
||||
// POSIX assignment of a function positional: `VAR=$1` or `VAR="$1"`.
|
||||
if (/=\s*["']?$/.test(before)) return true;
|
||||
return false;
|
||||
}
|
||||
|
||||
function findSubstitutionTokens(fenceContent) {
|
||||
const found = [];
|
||||
for (const pattern of CLAUDE_SUBSTITUTION_PATTERNS) {
|
||||
pattern.regex.lastIndex = 0;
|
||||
if (pattern.regex.test(fenceContent)) {
|
||||
found.push(pattern.token);
|
||||
let match = pattern.regex.exec(fenceContent);
|
||||
while (match !== null) {
|
||||
const skipBarePositional = pattern.token === '$1'
|
||||
&& match[0] === '$1'
|
||||
&& isPortableBareDollarOne(fenceContent, match.index);
|
||||
if (!skipBarePositional) {
|
||||
found.push(pattern.token);
|
||||
break;
|
||||
}
|
||||
match = pattern.regex.exec(fenceContent);
|
||||
}
|
||||
}
|
||||
return found;
|
||||
|
||||
@@ -489,6 +489,54 @@ check('bash fence ${1} is treated as a Claude substitution', () => {
|
||||
}
|
||||
});
|
||||
|
||||
check('POSIX VAR=$1 assignment is not a Claude substitution', () => {
|
||||
const root = createRoot();
|
||||
try {
|
||||
writeSkill(
|
||||
root,
|
||||
'posix',
|
||||
`${checklistBody('Posix')}\n## Code Examples\n\n\`\`\`bash\nmove_dir() {\n SOURCE=$1\n DEST=$2\n}\n\`\`\`\n`
|
||||
);
|
||||
const result = runValidator(root);
|
||||
assert.strictEqual(result.status, 0, result.stderr);
|
||||
assert.ok(!result.stderr.includes('ERROR:'));
|
||||
} finally {
|
||||
cleanup(root);
|
||||
}
|
||||
});
|
||||
|
||||
check('Perl/awk $1 numeric compare is not a Claude substitution', () => {
|
||||
const root = createRoot();
|
||||
try {
|
||||
writeSkill(
|
||||
root,
|
||||
'cover',
|
||||
`${checklistBody('Cover')}\n## Code Examples\n\n\`\`\`bash\nperl -ne 'if (/Total.*?(\\d+)/) { exit 1 if $1 < 80 }'\n\`\`\`\n`
|
||||
);
|
||||
const result = runValidator(root);
|
||||
assert.strictEqual(result.status, 0, result.stderr);
|
||||
assert.ok(!result.stderr.includes('ERROR:'));
|
||||
} finally {
|
||||
cleanup(root);
|
||||
}
|
||||
});
|
||||
|
||||
check('echo $1 in a bash fence is treated as a Claude substitution', () => {
|
||||
const root = createRoot();
|
||||
try {
|
||||
writeSkill(
|
||||
root,
|
||||
'echoone',
|
||||
`${checklistBody('Echo')}\n## Code Examples\n\n\`\`\`bash\necho $1\n\`\`\`\n`
|
||||
);
|
||||
const result = runValidator(root);
|
||||
assert.strictEqual(result.status, 1);
|
||||
assert.ok(result.stderr.includes('$1'));
|
||||
} finally {
|
||||
cleanup(root);
|
||||
}
|
||||
});
|
||||
|
||||
console.log(`\nPassed: ${passed}`);
|
||||
console.log(`Failed: ${failed}`);
|
||||
process.exit(failed > 0 ? 1 : 0);
|
||||
|
||||
@@ -187,6 +187,7 @@ function main() {
|
||||
"scripts/ci/scan-supply-chain-iocs.js",
|
||||
"scripts/ci/supply-chain-advisory-sources.js",
|
||||
"scripts/ci/validate-skill-host-compat.js",
|
||||
"scripts/ci/validate-skills.js",
|
||||
"scripts/consult.js",
|
||||
"scripts/control-pane.js",
|
||||
"scripts/feedback.js",
|
||||
@@ -235,6 +236,7 @@ function main() {
|
||||
"schemas/memory.schema.json",
|
||||
"skills/backend-patterns/SKILL.md",
|
||||
"skills/skill-comply/SKILL.md",
|
||||
"skills/skill-host-compat/SKILL.md",
|
||||
"skills/unified-memory/SKILL.md",
|
||||
]) {
|
||||
assert.ok(
|
||||
|
||||
Reference in New Issue
Block a user