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.
npx agentmods add commands/sgaunet/claude-plugins/feature-flow-wgit clone --depth 1 https://github.com/sgaunet/claude-pluginsWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/commands/sgaunet/claude-plugins/feature-flow-w)<a href="https://agentmods.dev/commands/sgaunet/claude-plugins/feature-flow-w"><img src="https://agentmods.dev/badge/commands/sgaunet/claude-plugins/feature-flow-w.svg" alt="Measured on agentmods" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00030 | $0.05739 |
| Opus 5 | $0.00015 | $0.02870 |
| Sonnet 5 | $0.00006 | $0.01148 |
| Haiku 4.5 | $0.00003 | $0.00574 |
Grade A, and why
feature-flow-w 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 4d 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.
How it starts
The opening of the file, as written. The whole thing — 432 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Feature Flow Worktree Command
Orchestrate a complete git workflow using worktrees for feature development. Creates a parallel working directory instead of switching branches, keeping your current branch untouched. Two modes:
- Staged Changes Mode (default): Analyze staged changes → worktree + branch → create issue → commit (in worktree)
- Issue Mode (
#<number>): Retrieve issue → validate relevance → worktree + branch → implement → lint → test → verify → commit → merge (all in worktree)
Use feature-flow-w instead of feature-flow when you want to work on multiple features simultaneously without leaving your current branch.
Mode Detection
Route based on $argument: first positional argument matching #<number> or bare <number> → Issue Mode; otherwise → Staged Changes Mode.
Issue Mode examples: /feature-flow-w #42, /feature-flow-w 42 --squash
Staged Mode examples: /feature-flow-w, /feature-flow-w add user auth, /feature-flow-w --skip-issue
Worktree Path Computation
Before creating any worktree, compute the target path:
- If
--worktree-path <path>(or-w <path>) provided → use that path (resolve to absolute if relative) - Default:
<repo-parent>/<repo-name>-<sanitized-branch>where/in branch name becomes-- Example: repo at
/home/user/my-project, branchfeat/add-auth→/home/user/my-project-feat-add-auth
- Example: repo at
- Validate directory does not already exist
Store <worktree-path> and <original-path> (result of pwd) for use throughout all phases.
Staged Changes Mode (5 Phases)
Phase 1: Discovery & Validation (Automatic)
Execute parallel git commands: git status and git diff --staged
Detect Repository Host: Use the detect-repo-host skill to identify the hosting service (GitHub, GitLab, or Forgejo) and extract owner/repo details.
Analysis steps:
- Analyze staged changes:
- Extract file paths, extensions, and types
- Determine change type: new files →
feat, test+fixes →fix, docs only →docs, structural →refactor, build/config →chore - Extract primary scope from directory (e.g.,
src/api/→api,internal/auth/→auth)
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.
- 4d ago First seen · 432 lines · 30 tokens per session scan A f169a76e56ef
feature-flow-w is a command published in the GitHub repository sgaunet/claude-plugins (16 stars, last pushed 2d ago), licensed MIT. It adds 30 tokens to every session and 5,739 once invoked, about $0.0002 per session on Opus 5. 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.
Other commands, from other repositories
security-audit-static
Static security audit of AI-built code — map trust boundaries, cross-reference documented intent, self-refute every finding, and report only evidence-backed risks.
performance-audit-static
Static performance audit of AI-built code — find N+1 queries and request waterfalls, over-fetching, missing indexes, and caching opportunities, ranked by effort and impact.
document-app
Reverse-engineer an AI-built codebase into the system documents reviewers and auditors need — a core set (architecture, flows, permissions, variables) plus conditional docs (emails, cron, SEO, automation) when they apply.
plan-okrs
Brainstorm team-level OKRs aligned with company objectives — qualitative objectives with measurable key results.
write-stories
Break a feature into backlog items — user stories, job stories, or WWA format with acceptance criteria.
battlecard
Create a sales-ready competitive battlecard — positioning, feature comparison, objection handling, and win strategies.