review

review is a command for Claude Code from jamditis/claude-skills-journalism. It costs 8 tokens per session (1,315 once invoked), scanned A, original, MIT.

An interactive command for reviewing lessons saved from earlier development sessions. It groups active lessons separately from lessons that were intentionally removed.

In plain words
What is it for?
Use it to inspect lessons in batches, review their confidence and history, and curate or remove accumulated project knowledge.
Why use it?
It helps teams examine low-confidence or new lessons and decide which project guidance should remain active.

Command for Claude Code

Written for Claude Code: ${CLAUDE_PLUGIN_ROOT} variable. Also seen: reads .claude/ paths; names the AskUserQuestion tool.

Runs only inside its plugin — its command needs a path that Claude Code sets for a plugin’s own hooks and for nothing else. Install the plugin, not this.

Part of the autocontext plugin — 5 commands, 1 agent shipped together

Good fit Use it to inspect lessons in batches, review their confidence and history, and curate or remove accumulated project knowledge.

Compare 6 commands from other repositories ↓
Install

Getting it into your agent

This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.

Claude Code
/plugin marketplace add jamditis/claude-skills-journalism
Claude Code
/plugin install autocontext

Made for: Claude Code.

Or install autocontext, the plugin that ships this one along with the rest of its 5 commands, 1 agent.

Wrote 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.

agentmods badge for review

README.md
[![agentmods](https://agentmods.dev/badge/commands/jamditis/claude-skills-journalism/review/github.svg)](https://agentmods.dev/commands/jamditis/claude-skills-journalism/review)
Your own site
<a href="https://agentmods.dev/commands/jamditis/claude-skills-journalism/review"><img src="https://agentmods.dev/badge/commands/jamditis/claude-skills-journalism/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.

agentmods 80×15 button for review

Your own site · 80×15
<a href="https://agentmods.dev/commands/jamditis/claude-skills-journalism/review"><img src="https://agentmods.dev/badge/commands/jamditis/claude-skills-journalism/review.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 8 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,315 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00008 $0.01315
Opus 5 $0.00004 $0.00658
Sonnet 5 $0.00002 $0.00263
Haiku 4.5 $0.00001 $0.00131

Measured 11d ago against content hash 75c034a568c9, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, 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 11d 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.

autocontext/commands/review.md · 144 lines

How it starts

The opening of the file, as written. The whole thing — 144 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Review accumulated lessons in .autocontext/lessons.json. Use AskUserQuestion to walk through lessons.

Initialization

The script first reads .autocontext/lessons.json and separates lessons into two groups:

  • Active lessons, deleted: false or not marked deleted
  • Tombstoned lessons, deleted: true (lessons that were intentionally removed)

If .autocontext/cache/curated-pending.json exists (from previous curation sessions with pending items), those are presented first for final approval.

Review order

Active lessons are sorted by confidence score (lowest first). Low-confidence lessons need the most attention, these are either new, frequently contradicted, or validated by few developers.

Lesson presentation

Lessons are presented in batches of 3-4 using AskUserQuestion. For each lesson, the review shows:

  • Text, the lesson content
  • Category, lesson type (bug-fix, architecture, workflow, pattern, gotcha, etc.)
  • Confidence, current score (0.0 to 1.0)
  • Validated count, how many sessions/developers have confirmed it
  • Created by, which developer/session discovered it
  • Age, how long ago it was created

Example format:

Lesson: "Always run git pull before pushing to main"
Category: workflow
Confidence: 0.9 | Validated: 12 times | Created by: alice | Age: 45 days

Review actions

For each lesson, you choose one action:

Options:

  • Approve, increase confidence by +0.2 (confirms lesson is valuable)
  • Edit, modify lesson text, category, or tags
  • Delete, tombstone the lesson (marks as deleted: true)
  • Supersede, replace this lesson with a newer/better version
  • Skip, leave unchanged and move to next

Approve

Bumps confidence by 0.2. Use this when you confirm a lesson is still valid and useful.

Edit

Opens the lesson for modification. You can update:

  • Lesson text (the knowledge itself)
  • Category (bug-fix, architecture, workflow, pattern, gotcha, integration, test-strategy)
  • Tags (optional metadata)

Read the full file on GitHub · 144 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. 11d ago First seen · 144 lines · 8 tokens per session scan A 75c034a568c9

Subscribe to this mod's changes

review is a command published in the GitHub repository jamditis/claude-skills-journalism (389 stars, last pushed 3d ago), licensed MIT. It adds 8 tokens to every session and 1,315 once invoked, about $0.0000 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 commands, from other repositories

export-latex

Export the current paper draft to production-ready LaTeX (.tex) and PDF using the arxiv-style template. Converts draft.md + references.bib + figures/ into a complete LaTeX project with resolved citations, tables, and figures. Compiles to PDF automatically.

TobiasBlask/open-paper-machine · 55 tokens

review-paper

Simulate a double-blind peer review of the current paper. Generates 2 independent reviewer reports in the style of top IS/CS conferences (ICIS, ECIS, MISQ level). Each report includes Summary, Strengths, Weaknesses, Minor Comments, and Overall Recommendation. Output is saved as simulatedreviews.md and can be fed…

TobiasBlask/open-paper-machine · 79 tokens

triage-project

Strategic project triage — should you continue, pivot, or kill your current research project? Evaluates 5 signals (results, competition, impact, effort, motivation) and delivers a clear Continue/Pivot/Kill recommendation. For Pivot: suggests concrete new framing. For Kill: suggests what to salvage.

TobiasBlask/open-paper-machine · 62 tokens

analyze-writing

Analyze academic writing quality of the current draft. Checks for passive voice overuse, weak openings, hedging balance, readability, sentence length variation, and word repetitions. Produces a writing quality report with specific improvement suggestions per section.

TobiasBlask/open-paper-machine · 46 tokens

scooping-check

Scooping risk assessment — is someone else working on your research idea? Identifies competing groups, assesses pace of publication, evaluates whether the core insight is "in the air", and provides a watch list with search terms, key researchers, and venues to monitor.

TobiasBlask/open-paper-machine · 52 tokens

audit-paper

Audit a paper's empirical claims against the linked code repository — catches MISMATCH, MISSING, and PARTIAL claims before submission.

TobiasBlask/open-paper-machine · 26 tokens