workflows-review

workflows-review is a skill for Claude Code from Kastalien-Research/thoughtbox. It costs 21 tokens per session (1,306 once invoked), scanned A, original, MIT.

A workflow step that checks whether an implementation really does what its claims, tests, and specification say. It is the fifth stage of the development process and uses review agents without changing the code.

In plain words
What is it for?
Use it to collect implementation claims and test evidence, run focused reviews, and report findings that later revision work must address.
Why use it?
It catches incorrect claims, regressions, missing tests, and quality problems before the work moves to revision or completion.

Skill for Claude Code

Written for Claude Code: user-invocable in frontmatter. Also seen: mentions subagents; installed under .agents/ (shared by several agents).

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/kastalien-research/thoughtbox/workflows-review
Any agent
npx skills add Kastalien-Research/thoughtbox --skill workflows-review
Clone the repo
git clone --depth 1 https://github.com/Kastalien-Research/thoughtbox

Made for: Claude Code.

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 workflows-review

README.md
[![agentmods](https://agentmods.dev/badge/skills/kastalien-research/thoughtbox/workflows-review.svg)](https://agentmods.dev/skills/kastalien-research/thoughtbox/workflows-review)
Your own site
<a href="https://agentmods.dev/skills/kastalien-research/thoughtbox/workflows-review"><img src="https://agentmods.dev/badge/skills/kastalien-research/thoughtbox/workflows-review.svg" alt="Measured on agentmods" height="20"></a>
Per session 21 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,306 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 5.1 $0.00021 $0.01306
Opus 5 $0.00010 $0.00653
Sonnet 5 $0.00004 $0.00261
Haiku 4.5 $0.00002 $0.00131

Measured 6d ago against content hash 901f1b5111f2, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

workflows-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 6d 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.

.agents/skills/workflows-review/SKILL.md · 158 lines

How it starts

The opening of the file, as written. The whole thing — 158 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Review the implementation: $ARGUMENTS

Purpose

You are executing Stage 5 (Review) of the development workflow. Implementation is complete and sub-agent summaries exist on disk. Your job is to dispatch review agents that verify claims, check for regressions, and assess quality. You do NOT fix issues — that's Stage 6's job.

Pre-Conditions

Before starting, verify:

  1. .workflow/state.json exists and currentStage is "review"
  2. Implementation summaries exist (check stages.implementation.artifacts.summaries in state)
  3. Read each summary to build the claims list

If pre-conditions are not met, report what's missing and halt.

Process

Step 1: Collect Claims

Read all sub-agent summaries from .workflow/summaries/*.md. Extract:

  • Every claim from each summary's ### Claims section
  • Every test command from ### Tests section
  • Every spec claim alignment statement from ### Spec/Evidence Alignment
  • Every risk from ### Risks section

Step 2: Dispatch Review Agents

Dispatch specialized review agents in parallel. Each gets the full claims list and the relevant source files.

Required reviews (always run these):

  1. Claim Verification — Use a general-purpose agent to:

    • Run every test command listed in summaries
    • Verify each claim by reading the implementation
    • Flag claims that are unsupported or contradicted
  2. Type Safety — Use the compound-engineering:review:kieran-typescript-reviewer agent (or dispatch via Agent tool with instructions to check types):

    • Run npm run build or tsc --noEmit
    • Check for type errors, unsafe casts, any-typed escape hatches
  3. Pattern Consistency — Use compound-engineering:review:pattern-recognition-specialist agent:

    • Check that new code follows existing codebase patterns
    • Flag naming inconsistencies, structural deviations

Conditional reviews (run when relevant):

  1. Security — If changes touch auth, input handling, or external APIs:
    • Use compound-engineering:review:security-sentinel agent

Read the full file on GitHub · 158 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. 6d ago First seen · 158 lines · 21 tokens per session scan A 901f1b5111f2

Subscribe to this mod's changes

workflows-review is a skill published in the GitHub repository Kastalien-Research/thoughtbox (64 stars, last pushed 1mo ago), licensed MIT. It adds 21 tokens to every session and 1,306 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 2026-08-30.

Related

Other skills, from other repositories

continual-learning

Nightly refinement of an existing per-repo review-style prompt using this reviewer's own finding outcomes. Read confirmed (resolved-by-commit / thumbs-up) and dismissed (thumbs-down) findings, promote the bug patterns the team actually fixes, demote the false-positive patterns, reconcile against the current prompt…

langchain-ai/open-swe · 89 tokens

remarc

Manage Remarc session comments and contextual feedback. Use when the user mentions Remarc sessions, comments, handoff, triage, review, addressing, resolving, status updates, or summaries.

metedata/Remarc · 41 tokens

code-review

Review ServiceNow server-side scripts for ES5 violations, ACL/injection/XSS issues, N+1 queries, missing setLimit/error handling, hard-coded sysids, and business-rule recursion risks.

serac-labs/serac · 43 tokens

pr-self-review

Draft short, plainspoken notes in the author's voice that help reviewers understand non-obvious choices, boundaries, and preserved behavior in the author's own pull request or local diff. Use when the user asks to self-review, annotate, or add reviewer context to their PR or changes. Draft locally when no PR exists…

petekp/claude-code-setup · 110 tokens

challenge

Use before a root-cause, done/verified claim, irreversible action, or 2nd-time fix reaches the owner (APEX or plain conversation); also fires at every eLicit/Verify gate. Not for code correctness (use sniper).

fusengine/agents · 52 tokens

code-quality

Use when validating code quality after modifications -- SOLID compliance, DRY duplication, linter errors, architecture violations. Do NOT use for functional verification (run verification FIRST, then code-quality).

fusengine/agents · 41 tokens