start-feature

A command workflow for starting a software feature, including issue tracking, project review, and creation of a linked Git branch.

In plain words
What is it for?
Use it to create or connect a GitHub issue, inspect recent issues and project status, gather task context, create a feature branch, and push it to the remote repository.
Why use it?
It gives a feature a documented issue and a separate branch so the work can be tracked and developed independently.

Command

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add commands/cassler/awesome-claude-code-setup/start-feature
Clone the repo
git clone --depth 1 https://github.com/cassler/awesome-claude-code-setup
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 808 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5 $0.00000 $0.00808
Opus 5 $0.00000 $0.00404
Sonnet 5 $0.00000 $0.00162
Haiku 4.5 $0.00000 $0.00081

Measured 3d ago against content hash 7f7f7f12d16b, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

start-feature scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 3d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

commands/start-feature.md · 97 lines

How it starts

The opening of the file, as written. The whole thing — 97 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Start New Feature

Please help me start working on a new feature: $FEATURE_NAME

Related issue: ${ISSUE_NUMBER:-create new} Feature type: ${FEATURE_TYPE:-enhancement}

Workflow

  1. Create or link GitHub issue (if not provided):

    # If no issue number provided, create one
    if [ -z "$ISSUE_NUMBER" ]; then
      gh issue create \
        --title "$FEATURE_NAME" \
        --body "Feature implementation for: $FEATURE_NAME\n\n## Description\n$FEATURE_DESCRIPTION\n\n## Acceptance Criteria\n- [ ] TBD\n\n## Technical Notes\n- TBD" \
        --label "${FEATURE_TYPE:-enhancement}"
    fi
    
    # List recent issues to verify
    gh issue list --limit 5
    
  2. Generate focused context for the feature:

    ch ctx for-task "$FEATURE_NAME"
    
  3. Understand current project state:

    chp  # Project overview
    chg status  # Git status
    
  4. Create feature branch (linked to issue):

    # Slugify feature name using common function
    source ~/.claude/scripts/common-functions.sh
    FEATURE_NAME_SLUGIFIED=$(slugify "$FEATURE_NAME")
    
    # Branch name includes issue number for automatic linking
    BRANCH_NAME="feature/${ISSUE_NUMBER}-${FEATURE_NAME_SLUGIFIED}"
    git checkout -b "$BRANCH_NAME"
    
    # Push to remote to establish tracking
    git push -u origin "$BRANCH_NAME"
    
  5. Identify affected areas:

    • Search for related code: chs find-code "$SEARCH_TERMS"
    • Find related files: chs find-file "*$RELATED_PATTERN*"
    • Check imports: ch cr imports-of "$MAIN_FILE" (if applicable)
  6. Set up initial structure:

    • Identify where the feature should live
    • Check existing patterns in similar features
    • Create necessary directories
  7. Create initial commit and draft PR:

    # Create initial commit
    echo "# $FEATURE_NAME\n\nImplementation for #$ISSUE_NUMBER\n\n## TODO\n- [ ] Implementation\n- [ ] Tests\n- [ ] Documentation" > FEATURE_PLAN.md
    git add FEATURE_PLAN.md
    git commit -m "feat: Initial setup for $FEATURE_NAME (#$ISSUE_NUMBER)"
    git push
    
    # Create draft PR linked to issue
    gh pr create --draft \
      --title "feat: $FEATURE_NAME" \
      --body "## Description\n\nImplements $FEATURE_NAME\n\nCloses #$ISSUE_NUMBER\n\n## Changes\n- TBD\n\n## Testing\n- [ ] Unit tests\n- [ ] Integration tests\n- [ ] Manual testing\n\n## Checklist\n- [ ] Implementation complete\n- [ ] Tests added\n- [ ] Documentation updated" \
      --base main
    

Read the full file on GitHub · 97 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 3d ago First seen · 97 lines · 0 tokens per session scan A 7f7f7f12d16b

Subscribe to this mod's changes

start-feature is a command published in the GitHub repository cassler/awesome-claude-code-setup (267 stars, last pushed 4mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 808 tokens. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.