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 skills/uta2000/feature-flow/settingsnpx skills add uta2000/feature-flow --skill settingsgit clone --depth 1 https://github.com/uta2000/feature-flowWhat 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 | $0.00046 | $0.06886 |
| Opus 5 | $0.00023 | $0.03443 |
| Sonnet 5 | $0.00009 | $0.01377 |
| Haiku 4.5 | $0.00005 | $0.00689 |
Grade B, and why
settings scanned grade B with 1 finding 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 yesterday.
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.
Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
macOS: ~/.claude/settings.json How it starts
The opening of the file, as written. The whole thing — 682 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Settings
Interactive dashboard for viewing and editing all feature-flow configuration values stored in .feature-flow.yml.
Announce at start: "Opening feature-flow settings..."
When to Use
- When the user wants to view or change any feature-flow configuration
- When
.feature-flow.ymlexists and the user wants to explore what's configured - When the user mentions a specific setting by name (notifications, YOLO, default branch, etc.)
- When the user wants to reset or review design preferences
Advisor Sub-Actions
If invoked with args advisor or advisor dismiss, handle as a direct command — do not show the dashboard.
feature-flow:settings advisor (no further args, or args == advisor):
Print the following block verbatim (substituting actual paths):
Advisor Beta Header — feature-flow integration
The Claude advisor tool (beta) provides automatic per-turn second-opinion checks on
complex tasks. To enable it, add the beta header to your Claude Code settings.json.
Settings file location:
macOS: ~/.claude/settings.json
Linux: ${XDG_CONFIG_HOME:-~/.config}/claude/settings.json
Windows: %APPDATA%\claude\settings.json
Add this to your settings.json under the "env" key:
{
"env": {
"ANTHROPIC_BETA": "advisor-tool-2026-03-01"
}
}
If you already have other ANTHROPIC_BETA values, append with a comma:
"ANTHROPIC_BETA": "other-header,advisor-tool-2026-03-01"
For full details, see docs/advisor.md in the feature-flow plugin source.
To stop the daily tip: feature-flow:settings advisor dismiss
Exit the skill after printing. Do not show the settings dashboard.
feature-flow:settings advisor dismiss:
- Read
.feature-flow.yml. If it does not exist, create it with default content (same as Step 1 default). - Set
hints.advisor.dismissed: truein the YAML. If ahints:block exists, addadvisor: {dismissed: true}under it. If the block does not exist, append:hints: advisor: dismissed: true - Write the updated file using the Edit tool (or Write tool if Edit fails).
- Print:
"Advisor hint dismissed. The daily tip will no longer appear. Re-enable with: feature-flow:settings advisor (then re-add the header)."
What ships with it
3 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- yesterday First seen · 682 lines · 46 tokens per session scan B 5d9bbe4eea58
settings is a skill published in the GitHub repository uta2000/feature-flow (4 stars, last pushed 1mo ago), licensed MIT. It adds 46 tokens to every session and 6,886 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
babysit-pr
Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…
imagegen
Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…