wf-guardian

wf-guardian is a skill for Claude Code from ParkerM2/create-claude-workflow. It costs 27 tokens per session (578 once invoked), scanned B, original, MIT.

A workflow step that checks the structure of a merged feature branch after all planned work and quality checks are complete. A feature branch is a separate line of code changes for one task.

In plain words
What is it for?
Use it at the end of an agent-team workflow to run the Codebase Guardian, handle its result, or skip that check in fast mode.
Why use it?
It adds a final structural check before the changes are handed off, helping catch problems introduced during merging.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the claude-workflow plugin — 10 skills, 25 commands, 3 agents, 6 hooks shipped together

Good fit Use it at the end of an agent-team workflow to run the Codebase Guardian, handle its result, or skip that check in fast mode.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/parkerm2/create-claude-workflow/wf-guardian
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.

Any agent
npx skills add ParkerM2/create-claude-workflow --skill wf-guardian
Clone the repo
git clone --depth 1 https://github.com/ParkerM2/create-claude-workflow

Made for: Claude Code.

Or install claude-workflow, the plugin that ships this one along with the rest of its 10 skills, 25 commands, 3 agents, 6 hooks.

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 wf-guardian

README.md
[![agentmods](https://agentmods.dev/badge/skills/parkerm2/create-claude-workflow/wf-guardian.svg)](https://agentmods.dev/skills/parkerm2/create-claude-workflow/wf-guardian)
Your own site
<a href="https://agentmods.dev/skills/parkerm2/create-claude-workflow/wf-guardian"><img src="https://agentmods.dev/badge/skills/parkerm2/create-claude-workflow/wf-guardian.svg" alt="Measured on agentmods" height="20"></a>
Per session 27 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 578 The whole file, excluding the scripts and references it only reads on demand.
Security scan B 1 finding. 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 $0.00027 $0.00578
Opus 5 $0.00014 $0.00289
Sonnet 5 $0.00005 $0.00116
Haiku 4.5 $0.00003 $0.00058

Measured 8d ago against content hash 73adab98be36, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade B, and why

wf-guardian scanned grade B with 1 finding 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 8d 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.

Reads agent configuration directoriesmediumAgent snooping

.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.

cat .claude/.workflow-state/all-waves-complete.json
skills/wf-guardian/SKILL.md · 102 lines

How it starts

The opening of the file, as written. The whole thing — 102 lines — stays where its author put it; the contents beside it link to each section on GitHub.

WF: Guardian

Gate Check

cat .claude/.workflow-state/all-waves-complete.json

If the file does not exist: STOP — "Not all waves are complete. Finish all waves with wf-qa-gate before running the Guardian."

Load TICKET, TEAM_LEADER_NAME, PLUGIN_ROOT, mode, featureBranch from state files.


Your Task

Spawn the Codebase Guardian on the feature branch and handle its verdict. Skip in fast mode.


Checklist

1. Fast Mode Skip

If mode is "fast":

touch .claude/.workflow-state/guardian-passed.json

Emit: /claude-workflow:track checkpoint "guardian-passed (fast mode skip)"

Skip to "Done."

2. Confirm on Feature Branch

git checkout <featureBranch>
git status

Must be on the feature branch with a clean working tree before spawning.

3. Read Guardian Spawn Template

cat {PLUGIN_ROOT}/prompts/implementing-features/THIN-SPAWN-TEMPLATE.md

Use the Codebase Guardian template section.

4. Spawn Guardian

Agent tool:
  description: "guardian"
  subagent_type: codebase-guardian
  team_name: "<TICKET>"
  name: "guardian"
  mode: bypassPermissions
  model: sonnet
  run_in_background: false
  prompt: <substitute Guardian template>

Wait for the Guardian to complete and SendMessage its verdict.

5. Handle Verdict

On PASS:

  1. Write stamp:
    touch .claude/.workflow-state/guardian-passed.json
    
  2. Emit: /claude-workflow:track checkpoint "guardian-passed"
  3. Shut down: SendMessage(to: "guardian", message: {"type": "shutdown_request"})

On FAIL:

  1. Emit: /claude-workflow:track checkpoint "guardian-failed"
  2. Spawn a fix agent on a new workbranch with the Guardian's findings
  3. Merge fix branch into feature branch
  4. Spawn Guardian again: name: "guardian-r2"
  5. Repeat until PASS (max 3 rounds; escalate to user on round 3)

Done

Report: "Guardian passed. Feature branch <featureBranch> is structurally clean. Return to the /agent-team checklist and proceed to Step 6 (wf-finalize)."

Read the full file on GitHub · 102 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. 8d ago First seen · 102 lines · 27 tokens per session scan B 73adab98be36

Subscribe to this mod's changes

wf-guardian is a skill published in the GitHub repository ParkerM2/create-claude-workflow (4 stars, last pushed 5mo ago), licensed MIT. It adds 27 tokens to every session and 578 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it B with 1 finding (reads agent configuration directories). 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

local-ai-agents

Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…

microsoft/ai-agents-for-beginners · 200 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

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

next-partial-prefetching-adoption

Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…

vercel/next.js · 103 tokens

chronicle

Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…

microsoft/vscode · 72 tokens