suggest-next-features

A review helper that reads recent Git history and progress notes, then drafts possible new features in a separate suggestions file. It leaves the main feature list unchanged.

In plain words
What is it for?
Use it when all listed features are complete, or when recent work has stalled while users describe missing behavior. It helps prepare candidate additions for human review.
Why use it?
It prevents an automated session from silently expanding its own workload or changing the agreed feature scope. A person can choose which suggestions to add later.

Skill for Claude CodeCodex

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 skills/archive228/loopkit/suggest-next-features
Any agent
npx skills add Archive228/loopkit --skill suggest-next-features
Clone the repo
git clone --depth 1 https://github.com/Archive228/loopkit

Made for: Claude Code, Codex.

Per session 34 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,065 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 $0.00034 $0.01065
Opus 5 $0.00017 $0.00532
Sonnet 5 $0.00007 $0.00213
Haiku 4.5 $0.00003 $0.00106

Measured 2d ago against content hash 24d3ec232753, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

suggest-next-features 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 2d 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.

skills/suggest-next-features/SKILL.md · 72 lines

How it starts

The opening of the file, as written. The whole thing — 72 lines — stays where its author put it; the contents beside it link to each section on GitHub.

suggest-next-features

The ledger runs dry. Either every feature_list.json entry has passes: true, or the last few sessions have been shuffling half-features and adding no new work because the spec grew and the list did not.

This skill drafts candidate additions — but to a separate file, feature_list.suggestions.json. feature_list.json is immutable except for the single passes: false → true flip that [[feature-list-json]] permits. Silently appending entries would break that contract and let a runaway session invent its own scope.

The suggestions file is a proposal. A human hand-merges chosen entries into feature_list.json; the rest are ignored or deleted. No agent, ever, edits feature_list.json directly from this skill.

Trigger

Apply when either condition holds:

  • jq '[.[] | select(.passes==false)] | length' feature_list.json returns 0.
  • The last 3 progress entries in claude-progress.txt show no new passes: true flips AND the user has referenced behavior not present in feature_list.json.

Do not apply just because the list looks short. 30 unfinished entries is not a trigger; 0 is.

Procedure

  1. git log --pretty=format:'%h %s' "$(git log --grep='chore: initial scaffold' --format=%H | tail -1)"..HEAD — every commit since the scaffold. This is what actually shipped, not what was claimed.
  2. Read the last 3 "What's done" / "Notes for the next session" entries from claude-progress.txt. This is where recent scope creep leaks.
  3. Read feature_list.json in full. You need to know what is already enumerated so you do not propose duplicates.
  4. Compare (1)+(2) against (3). Look for:
    • Behavior the user asked for in recent sessions that has no matching entry.
    • Natural next steps implied by shipped features (a feature ships a POST endpoint but no list view for its results).
    • Categories the initial list under-covered (error states, empty states, mobile layout, keyboard shortcuts, offline behavior).
  5. Draft 5–10 candidate entries in the same shape as feature_list.json. Every one starts passes: false. Order them roughly by priority.
  6. Write the array to feature_list.suggestions.json at the project root. Overwrite any prior draft — this file is regenerable, not append-only.
  7. Print a one-line summary per suggestion so the operator can scan without opening the file.
  8. Stop. Do not touch feature_list.json. Do not commit feature_list.suggestions.json (it is a proposal, not project state).

Read the full file on GitHub · 72 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. 2d ago First seen · 72 lines · 34 tokens per session scan A 24d3ec232753

Subscribe to this mod's changes

suggest-next-features is a skill published in the GitHub repository Archive228/loopkit (753 stars, last pushed 1mo ago), licensed MIT. It adds 34 tokens to every session and 1,065 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.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

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…

vercel/next.js · 95 tokens

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…

openai/codex · 114 tokens

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…

openai/codex · 113 tokens

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…

microsoft/vscode · 71 tokens

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…

vercel/next.js · 170 tokens