Skill
agent-manager
Creates, lists, and removes custom project-specific agents. Custom agents are stored in .claude/crew-agents/ and registered in crew-team.json for routing.
Development
Skill
/task-history
Reads and displays task execution history from crew-history.json with filtering by type, agent, cost, and configurable limits.
Install
$ npx -y skills add d3x293/code-crew --skill task-history --agent claude-codeHow it fires
How this skill gets triggered: by you, by Claude, or both.
- Fires itselfAuto-invocation. Claude auto-loads it when your prompt matches the work.Auto-invocation is when the right skill fires by itself at the right moment, driven by a FLOW.md router and a hook, instead of you invoking it by name. It is the difference between a skill being installed and a skill actually getting used.Read the full definition →
- You can call itInvoke it directly when you want it.
- Slash command
/task-history
Context preview
The summary Claude sees to decide when to auto-load this skill.
Reads and displays task execution history from crew-history.json with filtering by type, agent, cost, and configurable limits.
SKILL.md
task-history.SKILL.mdname: task-history
description: Reads and displays task execution history from crew-history.json with filtering by type, agent, cost, and configurable limits.
Task History - Execution History Viewer
Displays past task executions with filtering and cost analysis.
When to Activate
- User runs `/crew history [flags]`
Prerequisites
- `.claude/crew-history.json` must exist (created after first task execution)
- If missing: display "No history yet. Run /crew task to start."
Process
Step 1: Read History
Read `.claude/crew-history.json` — this is a JSON array of task entries (see execution-orchestrator for schema).
Step 2: Apply Filters
| Flag | Filter Logic | |------|-------------| | `--type <type>` | Keep only entries where `type` matches (bug-fix, feature, refactor, docs, test, security, devops, review, performance) | | `--agent <name>` | Keep only entries where `agents[]` contains an agent with matching `name` | | `--limit <n>` | Show last N entries (default: 10) |
Filters stack: `--type bug-fix --agent debugger` shows bug-fixes that involved the debugger.
Step 3: Display Results
**Display format**:
Task History ({count} tasks shown, {total} total):
# | Timestamp | Type | Complexity | Agents | Mode | Status
1 | 2026-04-04 12:00 | bug-fix | moderate | debugger, senior-dev | full | SUCCESS
2 | 2026-04-04 11:30 | docs | trivial | doc-writer | lite | SUCCESS
3 | 2026-04-04 10:15 | feature | complex | vp-eng, senior-dev, test | full | SUCCESSStep 4: Summary Stats
After the table, show:
{count} tasks | Top: {type}({n}), {agent}({n}) | {percent}% successRead more
name: task-history description: Reads and displays task execution history from crew-history.json with filtering by type, agent, cost, and configurable limits.
Task History - Execution History Viewer
Displays past task executions with filtering and cost analysis.
When to Activate
- User runs `/crew history [flags]`
Prerequisites
- `.claude/crew-history.json` must exist (created after first task execution)
- If missing: display "No history yet. Run /crew task to start."
Process
Step 1: Read History
Read `.claude/crew-history.json` — this is a JSON array of task entries (see execution-orchestrator for schema).
Step 2: Apply Filters
| Flag | Filter Logic | |------|-------------| | `--type <type>` | Keep only entries where `type` matches (bug-fix, feature, refactor, docs, test, security, devops, review, performance) | | `--agent <name>` | Keep only entries where `agents[]` contains an agent with matching `name` | | `--limit <n>` | Show last N entries (default: 10) |
Filters stack: `--type bug-fix --agent debugger` shows bug-fixes that involved the debugger.
Step 3: Display Results
**Display format**:
Task History ({count} tasks shown, {total} total):
# | Timestamp | Type | Complexity | Agents | Mode | Status
1 | 2026-04-04 12:00 | bug-fix | moderate | debugger, senior-dev | full | SUCCESS
2 | 2026-04-04 11:30 | docs | trivial | doc-writer | lite | SUCCESS
3 | 2026-04-04 10:15 | feature | complex | vp-eng, senior-dev, test | full | SUCCESSStep 4: Summary Stats
After the table, show:
{count} tasks | Top: {type}({n}), {agent}({n}) | {percent}% success Ships withcodecrew
A virtual dev crew for Claude Code — 11 specialized AI agents that decompose, implement, review, and ship your tasks. Instead of one AI doing everything, CodeCrew breaks work into subtasks and routes each to the right specialist on the right model.
Get the whole plugin
Stats
13
Stars
2
Forks
Maintained
Maintenance
MIT
License
5mo ago
Last commit
5mo ago
Created
Repo: d3x293/code-crew
Other skills on codecrew.
Skill
codebase-index
3-layer codebase indexing system for token-efficient code navigation. Builds compact index + symbol map so agents read targeted lines instead of entire files.…
Skill
crew-config
Manages CodeCrew configuration. Allows users to customize default mode, model tiers, agent activation, token budgets, and auto-index settings without editing…
Skill
crew-init
Analyzes a project codebase, builds 3-layer index, generates project profile, and auto-configures the agent team with relevant skills. The main initialization…
Skill
execution-orchestrator
Smart hybrid execution engine that dispatches agents in parallel or sequential order based on task dependencies. Manages the Agent tool calls, result…
Skill
index-updater
Keeps the 3-layer codebase index fresh after file edits. Performs incremental updates by recomputing hashes and re-extracting metadata for only changed files.