workflow-revision

workflow-revision is a skill for Claude Code from Kastalien-Research/thoughtbox. It costs 26 tokens per session (1,211 once invoked), scanned A, original, MIT.

A workflow step that fixes problems found during a code review and checks the changes again. It is the sixth stage in a larger development process.

In plain words
What is it for?
Use it to classify review findings, send coding fixes to sub-agents, add missing tests, resolve differences from the specification, and flag conflicts with recorded decisions.
Why use it?
It prevents known review issues from being left unresolved and repeats checking until the implementation passes or needs a decision after three rounds.

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/workflow-revision
Any agent
npx skills add Kastalien-Research/thoughtbox --skill workflow-revision
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 workflow-revision

README.md
[![agentmods](https://agentmods.dev/badge/skills/kastalien-research/thoughtbox/workflow-revision.svg)](https://agentmods.dev/skills/kastalien-research/thoughtbox/workflow-revision)
Your own site
<a href="https://agentmods.dev/skills/kastalien-research/thoughtbox/workflow-revision"><img src="https://agentmods.dev/badge/skills/kastalien-research/thoughtbox/workflow-revision.svg" alt="Measured on agentmods" height="20"></a>
Per session 26 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,211 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 $0.00026 $0.01211
Opus 5 $0.00013 $0.00606
Sonnet 5 $0.00005 $0.00242
Haiku 4.5 $0.00003 $0.00121

Measured 6d ago against content hash 88a9b89334c3, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

workflow-revision 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/workflow-revision/SKILL.md · 145 lines

How it starts

The opening of the file, as written. The whole thing — 145 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Execute revision based on review findings: $ARGUMENTS

Purpose

You are executing Stage 6 (Revision) of the development workflow. Review found issues with the implementation. Your job is to dispatch sub-agents to fix them, then re-run review until it passes — or escalate after 3 iterations.

Pre-Conditions

Before starting, verify:

  1. .workflow/state.json exists and currentStage is "revision"
  2. Review findings exist (either passed as argument or in stages.review.artifacts.findings)
  3. The working tree has uncommitted changes from implementation (since commits happen post-review)

Process

Step 1: Classify Review Findings

Read the review findings and classify each into:

Category Action Example
Claim failure Re-dispatch sub-agent for the specific claim "Function X does not handle case Y"
Test gap Add missing test coverage "No test for edge case Z"
Spec divergence Fix code OR update spec (with justification) "Implementation differs from spec section 3.2"
ADR conflict Flag for user decision "This contradicts accepted ADR-005"
Style/quality Fix inline (no sub-agent needed) "Missing error handling on line 42"

Step 2: Dispatch Fixes

For each finding that requires a sub-agent:

  1. Dispatch a sub-agent with:
    • The specific finding to address
    • The relevant spec section
    • The file(s) to modify
    • Instructions to return the structured summary format (from the conductor skill)
  2. Persist the returned summary to disk immediately

For findings that can be fixed inline (style/quality):

  • Make the fix directly
  • Note it in the revision log

For ADR conflicts:

  • Present to the user with the four ADR reconciliation dispositions:
    1. STILL VALID — false positive, ADR reasoning holds
    2. NEEDS AMENDMENT — core decision correct, context needs updating
    3. SUPERSEDED — another ADR has replaced this one
    4. INVALIDATED — reasoning no longer holds, no replacement
  • Wait for user decision before proceeding

Read the full file on GitHub · 145 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 · 145 lines · 26 tokens per session scan A 88a9b89334c3

Subscribe to this mod's changes

workflow-revision is a skill published in the GitHub repository Kastalien-Research/thoughtbox (64 stars, last pushed 1mo ago), licensed MIT. It adds 26 tokens to every session and 1,211 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