Git Workflow

What it does

When your agent uses it

• Running claudikins-kernel:execute
• Decomposing plans into tasks
• Setting up two-stage review
• Deciding batch sizes

Example prompts

• “/git-workflow”

Requirements

• Pre-approved tools (allowed-tools): Read, Grep, Glob, Bash, Edit, Write, TodoWrite, Skill, mcp__plugin_claudikins-tool-executor_tool-executor__search_tools, mcp__plugin_claudikins-tool-executor_tool-executor__get_tool_schema, mcp__plugin_claudikins-tool-executor_tool-executor__execute_code

Workflow steps

2 steps, taken from the step headings in SKILL.md.

1. 1Spec Compliance (spec-reviewer, opus)
2. 2Code Quality (code-reviewer, opus)

What it can do on your machine

Read from SKILL.md and the folder at commit 8b626a4. It shows what the files ask for, not the result of running them.

• Tool permissions

  Pre-approves these tools, so the agent can use them without asking each time:

  • Read
  • Grep
  • Glob
  • Bash
  • Edit
  • Write
  • TodoWrite
  • Skill
  • mcp__plugin_claudikins-tool-executor_tool-executor__search_tools
  • mcp__plugin_claudikins-tool-executor_tool-executor__get_tool_schema

  …and 1 more on the same allowed-tools line.

  From allowed-tools in the SKILL.md frontmatter.

• Runs code

  Shell commands in SKILL.md call:

  • jq
  • git

  From the folder's file list and the shell code blocks in SKILL.md.

• Network

  No URLs in SKILL.md. Its commands use git, which can reach the network depending on how they are called.

  From URLs in SKILL.md, links to its own repository left out.

• Credentials

  Names no API keys, tokens, secrets or passwords.

  From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Git Workflow loads about 3.4k tokens when it runs, and up to ~24k if it reads all its reference files. Until then it costs about 68 tokens; SKILL.md has 1,246 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it

~68

When it runs · the whole SKILL.md, loaded when a task matches

~3.4k

With references · SKILL.md plus every file in references/, read only if the agent opens them

~24k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

• NotePre-approves every shell command (allowed-tools: Bash)SKILL.md

  allowed-tools: Read, Grep, Glob, Bash, Edit, Write, TodoWrite, Skill, mcp__plugin_claudikins-tool-executor_tool-exe

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from povvo/claudikins-kernel at commit 8b626a4, republished under its MIT licence (© povvo). 1,246 words, ~3,439 tokens.

name

git-workflow

description

Use when running claudikins-kernel:execute, decomposing plans into tasks, setting up two-stage review, deciding batch sizes, or handling stuck agents — enforces isolation, verification, and human checkpoints; prevents runaway parallelization and context death

allowed-tools

Read, Grep, Glob, Bash, Edit, Write, TodoWrite, Skill, mcp__plugin_claudikins-tool-executor_tool-executor__search_tools, mcp__plugin_claudikins-tool-executor_tool-executor__get_tool_schema, mcp__plugin_claudikins-tool-executor_tool-executor__execute_code

□ .claude/reviews/spec/{task_id}.json EXISTS for each task
□ .claude/reviews/code/{task_id}.json EXISTS for each task
□ Both files contain valid JSON with "verdict" field
□ spec-reviewer verdict is PASS (or user override documented)

All tasks in batch complete?
├── No → Wait for remaining
└── Yes →
    All reviews pass?
    ├── No →
    │   Retry count < 3?
    │   ├── Yes → Retry failed tasks
    │   └── No → Escalate to Klaus or human
    └── Yes →
        Present results to human
        └── Human decides: [Accept] [Revise] [Retry]

# Always backup first
echo "$OUTPUT" > "$BACKUP_DIR/agent-$(date +%s).json"
# Then move to primary
mv "$BACKUP_DIR/..." "$PRIMARY"

REQUIRED='["task_id", "status"]'
jq -e "all($REQUIRED[]; has(.))" "$OUTPUT" || exit 2

export TASK_BRANCH_DIR="$PROJECT_DIR"
export TASK_BRANCH_NAME="execute/task-${TASK_ID}-${SLUG}"

{
  "status": "partial",
  "files_changed": ["completed work..."],
  "next_steps": ["what remains..."],
  "checkpoint_hash": "sha256:..."
}

Circuit: agent_spawn
State: OPEN (3 failures in 60s)
Reset in: 30 seconds

[Wait for reset] [Force close] [Skip operation]

Trace: exec-session-xyz
├── batch_1 (45s)
│   ├── task-1 (20s) ✓
│   └── task-2 (25s) ✓
└── batch_2 (60s)
    └── task-3 (60s) ✓

Critical path: batch_1 → batch_2

© povvo, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 11 other files (references) in skills/git-workflow of povvo/claudikins-kernel.

• SKILL.md
• references/batch-patterns.md
• references/batch-size-verification.md
• references/branch-collision-detection.md
• references/branch-guard-recovery.md
• references/circuit-breakers.md
• references/dependency-failure-chains.md
• references/execution-tracing.md
• references/review-conflict-matrix.md
• references/review-criteria.md
• references/task-branch-recovery.md
• references/task-decomposition.md

Open the folder on GitHubat commit 8b626a4