Borrowing it
Nothing to install: this file belongs to quality-screener/quality-screener-mcp-server. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/quality-screener/quality-screener-mcp-server/main/.claude/skills/new-feature/SKILL.mdgit clone --depth 1 https://github.com/quality-screener/quality-screener-mcp-serverWrote 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/skills/quality-screener/quality-screener-mcp-server/new-feature)<a href="https://agentmods.dev/skills/quality-screener/quality-screener-mcp-server/new-feature"><img src="https://agentmods.dev/badge/skills/quality-screener/quality-screener-mcp-server/new-feature/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/quality-screener/quality-screener-mcp-server/new-feature"><img src="https://agentmods.dev/badge/skills/quality-screener/quality-screener-mcp-server/new-feature.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00092 | $0.02326 |
| Opus 5.5 | $0.00037 | $0.00930 |
| Sonnet 5.5 | $0.00018 | $0.00465 |
| Haiku 4.5 | $0.00009 | $0.00233 |
Grade A, and why
new-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 2mo 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 — 251 lines — stays where its author put it; the contents beside it link to each section on GitHub.
New Feature Planner
Produce a solid, reviewable implementation plan before any code is written. A plan that survives 10 minutes of review saves 10 hours of rework.
The Flow (Non-Negotiable)
Always follow these steps in order.
Step 1 — Search docs/plans/ for related prior work
docs/plans/ is the canonical archive of every feature plan written for this
project. Before designing anything:
- List
docs/plans/(ls docs/plans/). - Skim filenames; open anything whose name overlaps with the request.
- Grep the folder for relevant keywords (feature name, domain term, ticker,
route, etc.):
grep -r -l "<keyword>" docs/plans/. - Read related plans end-to-end. Look specifically for:
- Architectural decisions that constrain the new plan
- Patterns the project has already adopted (reuse them)
- Lessons learned / what didn't work
- Open follow-ups that this feature might pick up
Tell the user what you found, including "nothing relevant" if that's the honest answer. Cite the plan filename you took inspiration from in the new plan.
If the feature also relates to the research/ prototypes (data fetching, scoring, helpers), check there too — the implementation pattern usually already exists.
Step 2 — Classify the feature type
Identify what kind of change this is, because the plan structure and the set of related prior plans depend on it. Use one of:
| Type | Description |
|---|---|
enhancement |
Adds a new user-visible capability to an existing feature |
new-capability |
Wholly new feature area (new domain, new page, new pipeline) |
refactoring |
Internal restructuring without behavior change |
performance |
Targeted performance work with measurable goals |
bug-fix |
Non-trivial bug fix that needs design (small fixes don't need a plan) |
test |
Adding meaningful test coverage (e.g., correctness suite) |
infrastructure |
Docker, CI, deployment, environment, secrets management |
ux |
UX redesign or audit follow-up |
security |
Security hardening (auth, input validation, secrets, rate limits) |
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.
- 2mo ago First seen · 251 lines · 92 tokens per session scan A 7bba736a19aa
new-feature is a skill published in the GitHub repository quality-screener/quality-screener-mcp-server (0 stars, last pushed 10d ago), licensed MIT. It adds 92 tokens to every session and 2,326 once invoked, about $0.0004 per session on Opus 5.5. 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 2026-08-31.
new-feature compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| new-featurequality-screener/quality-screener-mcp-server | Skill | 0 | 10d ago | MIT | A | 92 | Claude Code |
| imagegenopenai/codex | Skill | 133k | yesterday | Apache-2.0 | A | 113 | Codex |
| playwright-climicrosoft/playwright | Skill | 99k | yesterday | Apache-2.0 | A | 19 | Claude Code |
| local-ai-agentsmicrosoft/ai-agents-for-beginners | Skill | 79k | 4d ago | MIT | A | 200 | Claude Code, Codex |
| systematic-debuggingobra/superpowers | Skill | 313k | 3d ago | MIT | A | 21 | Claude Code |
| next-cache-components-adoptionvercel/next.js | Skill | 143k | yesterday | MIT | A | 95 | Claude Code |
| next-partial-prefetching-adoptionvercel/next.js | Skill | 143k | yesterday | MIT | A | 103 | Claude Code |