Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/athola/claude-night-marketnpx agentmods add skills/athola/claude-night-market/feature-reviewWrote 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/athola/claude-night-market/feature-review)<a href="https://agentmods.dev/skills/athola/claude-night-market/feature-review"><img src="https://agentmods.dev/badge/skills/athola/claude-night-market/feature-review/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/athola/claude-night-market/feature-review"><img src="https://agentmods.dev/badge/skills/athola/claude-night-market/feature-review.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 | $0.00037 | $0.02821 |
| Opus 5.5 | $0.00015 | $0.01128 |
| Sonnet 5.5 | $0.00007 | $0.00564 |
| Haiku 4.5 | $0.00004 | $0.00282 |
Grade A, and why
feature-review 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 13d 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 — 373 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Verification
Run make test-feature-review to verify scoring logic after changes.
Feature Review
Review implemented features and suggest new ones using evidence-based prioritization. Create GitHub issues for accepted suggestions.
Philosophy
Feature decisions rely on data. Every feature involves tradeoffs that require evaluation. This skill uses hybrid RICE+WSJF scoring with Kano classification to prioritize work and generates actionable GitHub issues for accepted suggestions.
When To Use
- Roadmap reviews (sprint planning, quarterly reviews).
- Retrospective evaluations.
- Planning new development cycles.
When NOT To Use
- Emergency bug fixes.
- Simple documentation updates.
- Active implementation (use
scope-guard).
Quick Start
1. Inventory Current Features
Discover and categorize existing features:
/feature-review --inventory
2. Score and Classify
Evaluate features against the prioritization framework:
/feature-review
3. Generate Suggestions
Review gaps and suggest new features:
/feature-review --suggest
4. Research-Enriched Scoring
Use tome plugin to adjust scores with external evidence:
/feature-review --research
5. Upload to GitHub
Create issues for accepted suggestions:
/feature-review --suggest --create-issues
Workflow
Phase 1: Feature Discovery (feature-review:inventory-complete)
Identify features by analyzing:
- Code artifacts: Entry points, public APIs, and configuration surfaces.
- Documentation: README lists, CHANGELOG entries, and user docs.
- Git history: Recent feature commits and branches.
Output: Feature inventory table.
Phase 2: Classification (feature-review:classified)
Classify each feature along two axes:
Axis 1: Proactive vs Reactive
| Type | Definition | Examples |
|---|---|---|
| Proactive | Anticipates user needs. | Suggestions, prefetching. |
| Reactive | Responds to explicit input. | Form handling, click actions. |
What ships with it
6 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.
- 13d ago First seen · 373 lines · 37 tokens per session scan A 31a8a313ad23
feature-review is a skill published in the GitHub repository athola/claude-night-market (342 stars, last pushed yesterday), licensed MIT. It adds 37 tokens to every session and 2,821 once invoked, about $0.0001 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 2026-10-03.
Other skills, from other repositories
html-ppt-knowledge-arch-blueprint
OpenDesign's incident retro: the daemon-restart data bug, the root cause, the fix, and the systemic follow-ups. Built as a decision-grade product management deck for engineering, SRE, leadership.
promote-idea
Converts an album idea from IDEAS.md into an actual album project in one step. Use when the user says "promote [idea title]", "turn idea into album", or "start working on [idea]".
preserve
Single write point for the vault. Centralizes entity detection, textual matching, entity creation/update, and bidirectional linking. Accepts structured input (list of entities), free-form input (text, meeting notes, session context), or graphify output (graph.json + obsidian markdown from /graphify pipeline). Use…
html-ppt-graphify-dark-graph
OpenDesign's feature business case for the plugin marketplace: the user pain, options, tradeoffs, and the measure of success. Built as a decision-grade product management deck for PM, eng, design, leadership.
fly
Fly one thought to its destination across concurrent agents, on whatever the project and harness already have. Lands only when the user has accounted for every detail, never on an agent's say-so.
foreman
The one entrance to Foreman, which keeps a project's plan and task history. Say what you want in plain language and this routes it to one of the six things Foreman does to a project: add work, show status, correct work, check the roadmap, pick work, or reconcile and pick. It owns no flow of its own. Use for Foreman or…