review

A review workflow for checking locally saved capsule drafts one at a time before deciding what to do with them. It includes authentication, listing drafts, scanning for personally identifying information, and choosing whether to push, skip, or delete each draft.

In plain words
What is it for?
Use it to review recent exploration drafts, inspect PII findings, and choose a visibility option when pushing a draft. If authentication or a required script fails, the workflow stops and reports the problem.
Why use it?
It prevents drafts from being published without review and checks for personal information first. Processing one draft at a time makes each decision explicit.

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/fragcap/plugin/review
Any agent
npx skills add fragcap/plugin --skill review
Clone the repo
git clone --depth 1 https://github.com/fragcap/plugin

Made for: Claude Code, Codex.

Per session 25 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 540 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 $0.00025 $0.00540
Opus 5 $0.00013 $0.00270
Sonnet 5 $0.00005 $0.00108
Haiku 4.5 $0.00003 $0.00054

Measured yesterday against content hash 5cc7e35ddede, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

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 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.

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/review/SKILL.md · 59 lines

What it actually says

Review Capsule Drafts

Guide the user through reviewing locally saved capsule drafts (SKILL.md files).

Script Convention

FRAGCAP_DATA="${CLAUDE_PLUGIN_DATA}" node "${CLAUDE_PLUGIN_ROOT}/scripts/<n>.mjs" [args]

If a script exits with a non-zero code or returns { error: "..." }, stop immediately and surface the error to the user. Never silently retry with a different command or skip the step.

When to Activate

  • User runs /fragcap:review
  • SessionStart hook reports pending drafts
  • User asks about their recent explorations

Flow

  1. Auth gate — run auth-status.mjs. Not authenticated → tell user to run /fragcap:auth and stop.

  2. List drafts — run list-drafts.mjs.

    • Empty: "No pending drafts." Stop.
    • Has drafts: show a numbered summary with ID, problem, tags, and status.
  3. Review each draft — process one at a time:

    a. PII scan — run preview-pii.mjs <draft-id>. Display findings if any. If clean: "No PII detected."

    b. Ask for decision — present numbered options inline, do not ask the user to type free text:

    [1] Push  [2] Skip  [3] Delete
    
    • 1 Push — present visibility options:
      [1] anonymous (default)  [2] attributed
      
      Then present gist scope options:
      [1] public (default) — searchable by others, registered in central index
      [2] secret — unlisted, not registered in index
      
      Then run push.mjs <draft-id> <visibility> <scope> where scope is public or secret.
    • 2 Skip — keep the draft for later, move to next
    • 3 Delete — run delete-draft.mjs <draft-id> to permanently remove
  4. Summary — after all drafts are processed:

    Done! Pushed: 2 | Skipped: 1 | Deleted: 0
    

Error Handling

  • If push fails: the draft is still saved locally. Tell the user: "Push failed ({error}). Your draft is safe — try again later."
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. yesterday First seen · 59 lines · 25 tokens per session scan A 5cc7e35ddede

Subscribe to this mod's changes

review is a skill published in the GitHub repository fragcap/plugin (2 stars, last pushed 5mo ago), licensed MIT. It adds 25 tokens to every session and 540 once invoked, about $0.0001 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 2026-08-31.

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