bulwark-fix-validator

bulwark-fix-validator is an agent for Claude Code from QBall-Inc/the-bulwark. It costs 54 tokens per session (5,036 once invoked), scanned A, original, MIT.

A fix-checking agent that uses a debugging report to run its staged test plan and assess whether a code change is ready for review.

In plain words
What is it for?
Use it after implementing a fix to run ordered tests, inspect affected call sites, assess confidence, document manual checks, and recommend whether the fix can proceed.
Why use it?
It provides evidence about whether a fix addresses the reported problem and whether related uses of changed code still work. It stops when the first required test stage fails.

Agent for Claude Code

Written for Claude Code: ${CLAUDE_PROJECT_DIR} variable. Also seen: model in frontmatter; mentions subagents.

Needs its repository: it runs a file that does not travel with it, so clone the repository first. The line is node tests/auth.test.js # JavaScript.

Part of the the-bulwark plugin — 30 skills, 17 agents, 6 hooks shipped together

Good fit Use it after implementing a fix to run ordered tests, inspect affected call sites, assess confidence, document manual checks, and recommend whether the fix can proceed.

Compare 6 agents from other repositories ↓
Install

Getting it into your agent

It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.

Clone the repo
git clone --depth 1 https://github.com/QBall-Inc/the-bulwark
agentmods
npx agentmods add agents/qball-inc/the-bulwark/bulwark-fix-validator

Made for: Claude Code.

Or install the-bulwark, the plugin that ships this one along with the rest of its 30 skills, 17 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 bulwark-fix-validator

README.md
[![agentmods](https://agentmods.dev/badge/agents/qball-inc/the-bulwark/bulwark-fix-validator/github.svg)](https://agentmods.dev/agents/qball-inc/the-bulwark/bulwark-fix-validator)
Your own site
<a href="https://agentmods.dev/agents/qball-inc/the-bulwark/bulwark-fix-validator"><img src="https://agentmods.dev/badge/agents/qball-inc/the-bulwark/bulwark-fix-validator/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 bulwark-fix-validator

Your own site · 80×15
<a href="https://agentmods.dev/agents/qball-inc/the-bulwark/bulwark-fix-validator"><img src="https://agentmods.dev/badge/agents/qball-inc/the-bulwark/bulwark-fix-validator.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 54 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 5,036 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 $0.00054 $0.05036
Opus 5 $0.00027 $0.02518
Sonnet 5 $0.00011 $0.01007
Haiku 4.5 $0.00005 $0.00504

Measured 9d ago against content hash 50305f7673b0, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

bulwark-fix-validator 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 9d 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/bulwark-fix-validator.md · 644 lines

How it starts

The opening of the file, as written. The whole thing — 644 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Bulwark Fix Validator

You are a fix validation specialist in the Bulwark quality system. Your role is to validate fixes against the debug report produced by bulwark-issue-analyzer, execute the tiered validation plan, assess confidence, and determine if the fix is ready for code review.


Mission

DO:

  • Read and parse the debug report from IssueAnalyzer
  • Execute tiered tests (P1 → P2 → P3) per the validation plan
  • Validate functionalities listed in the debug report
  • Analyze call sites of modified functions
  • Assess confidence using criteria from the debug report
  • Produce validation report with clear recommendation
  • Document escalation items requiring manual testing

DO NOT:

  • Modify any source code, test files, or config files
  • Implement fixes (that's the orchestrator's job)
  • Skip validation steps without documenting why
  • Write to any location outside logs/, tmp/
  • Proceed if P1 tests fail (stop and report)

Invocation

This agent is invoked via the Task tool. Agents are distinct from skills: they run in isolated context, cannot be invoked via slash commands, and the user-invocable frontmatter field has no effect on them.

Invocation Method How to Use
/fix-bug skill /fix-bug path/to/code "description" - triggers full Fix Validation pipeline
Orchestrator invokes Agent(subagent_type="bulwark-fix-validator", prompt="...")
User requests Ask Claude to "validate the fix" or "run the fix validator"
Pipeline stage Fix Validation pipeline Stage 4

Input handling:

  1. Read fix details and debug report path from CONTEXT section of the prompt
  2. Debug report path is required - if not provided, ask orchestrator
  3. Fix details should include: files modified, before/after code, tests added (if any)

Example CONTEXT:

Debug Report: logs/debug-reports/production-bug-new-account-login-20260119-143425.yaml

Fix Applied (src/auth.ts line 74):
  Before: const name = user.profile.displayName;
  After:  const name = user.profile?.displayName || user.email;

Test Added (tests/auth.test.ts):
  'should login new user without profile and use email in welcome'

Files Modified:
  - src/auth.ts
  - tests/auth.test.ts

Read the full file on GitHub · 644 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. 9d ago First seen · 644 lines · 54 tokens per session scan A 50305f7673b0

Subscribe to this mod's changes

bulwark-fix-validator is an agent published in the GitHub repository QBall-Inc/the-bulwark (8 stars, last pushed today), licensed MIT. It adds 54 tokens to every session and 5,036 once invoked, about $0.0003 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 agents, from other repositories

qa-analyzer

Use this agent after cycle completion or when the user requests bug hunting and QA analysis. World-class QA analyst that finds bugs before users do — thinks like a confused user, power user, and malicious attacker. Documents issues precisely for quick fixes. Context: User just completed a cycle and wants to review…

drobins25/craft · 217 tokens

debugger

Systematic debugger using the Iron Law: no fix without confirmed root cause. Reproduces errors, traces execution paths, forms and verifies hypotheses, then implements…

KevinZai/commander · 35 tokens

test-writer-fixer

Use this agent when code changes have been made and you need to write new tests, run existing tests, analyze failures, and fix them while maintaining test integrity. This agent should be triggered proactively after code modifications to ensure comprehensive test coverage and suite health. Examples:\n\n \nContext: The…

composio-community/awesome-claude-plugins · 0 tokens

bug-reporter

Use this agent when qa-output/functional-review.md or qa-output/browser-validation.md reports any gap, failed scenario, or blocked verdict. Turns each finding into one developer-ready bug report with repro steps, severity, and code references. One finding per report — never grouped.

Anasss/qa-orchestra · 58 tokens

debugger

Root-cause debugging agent that finds and fixes bugs in an isolated worktree. Use for: diagnosing failures, tracking down root causes, fixing regressions. Returns a branch with a minimal, tested fix and all quality gates green.

SyloRei/claude-godmode · 49 tokens

verifier

Adversarial checker. Dispatch to attack a claim rather than confirm it — does this bug actually reproduce, does this fix actually work, do these tests actually cover what they say, does the artifact on disk match what was reported. Prompted to refute by default, so a finding that survives it is worth trusting. Run…

phil9922/claude-swarm · 96 tokens