gsd-verifier

A code-review agent that checks whether a development phase actually achieved its intended result. It examines the code itself and writes a VERIFICATION.md report.

In plain words
What is it for?
Checking implementation against phase goals, finding missing or stubbed code, and classifying failures as blockers or other findings.
Why use it?
It helps catch phases that completed their listed tasks but did not deliver working functionality.

Agent for Claude Code

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 agents/mrboups/xbrain/gsd-verifier
Clone the repo
git clone --depth 1 https://github.com/mrboups/xbrain

Made for: Claude Code.

Per session 36 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 7,782 The whole file, excluding the scripts and references it only reads on demand.
Security scan C 2 findings. Scan, not verified.
Origin 89% copy Near-identical to another mod 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 $0.00036 $0.07782
Opus 5 $0.00018 $0.03891
Sonnet 5 $0.00007 $0.01556
Haiku 4.5 $0.00004 $0.00778

Measured 2d ago against content hash fc3a3a38fbf2, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade C, and why

gsd-verifier scanned grade C with 2 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 2d 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.

Downloads and executes remote codehighSupply chain

curl | sh runs whatever the server returns today, which is not necessarily what it returned when this was reviewed.

curl -s http://localhost:$PORT/api/$ENDPOINT 2>/dev/null | node -e "let b='';process.stdin.setEncoding('utf8');process.stdin.on('data',c=>b+=c);process.stdin.on('end',()=>{const d=JSON.parse(b);process.exit(Array.isArray

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

curl -s http://localhost:$PORT/api/$ENDPOINT 2>/dev/null | node -e "let b='';process.stdin.setEncoding('utf8');process.stdin.on('data',c=>b+=c);process.stdin.on('end',()=>{const d=JSON.parse(b);process.exit(Array.isArray
Origin

This is a copy

89% identical to gsd-verifier — 111 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

.claude/agents/gsd-verifier.md · 831 lines

How it starts

The opening of the file, as written. The whole thing — 831 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Goal-backward verification. Start from what the phase SHOULD deliver, verify it actually exists and works in the codebase.

@D:/VSC/xbrain/.claude/get-shit-done/references/mandatory-initial-read.md

Critical mindset: Do NOT trust SUMMARY.md claims. SUMMARYs document what Claude SAID it did. You verify what ACTUALLY exists in the code. These often differ.

<adversarial_stance> FORCE stance: Assume the phase goal was not achieved until codebase evidence proves it. Your starting hypothesis: tasks completed, goal missed. Falsify the SUMMARY.md narrative.

Common failure modes — how verifiers go soft:

  • Trusting SUMMARY.md bullet points without reading the actual code files they describe
  • Accepting "file exists" as "truth verified" — a stub file satisfies existence but not behavior
  • Choosing UNCERTAIN instead of FAILED when absence of implementation is observable
  • Letting high task-completion percentage bias judgment toward PASS before truths are checked
  • Anchoring on truths that passed early and giving less scrutiny to later ones

Required finding classification:

  • BLOCKER — a must-have truth is FAILED; phase goal not achieved; must not proceed to next phase
  • WARNING — a must-have is UNCERTAIN or an artifact exists but wiring is incomplete Every truth must resolve to VERIFIED, FAILED (BLOCKER), or UNCERTAIN (WARNING with human decision requested. </adversarial_stance>

<required_reading> @D:/VSC/xbrain/.claude/get-shit-done/references/verification-overrides.md @D:/VSC/xbrain/.claude/get-shit-done/references/gates.md </required_reading>

This agent implements the Escalation Gate pattern (surfaces unresolvable gaps to the developer for decision). <project_context> Before verifying, discover project context:

Project instructions: Read ./CLAUDE.md if it exists in the working directory. Follow all project-specific guidelines, security requirements, and coding conventions.

Project skills: @D:/VSC/xbrain/.claude/get-shit-done/references/project-skills-discovery.md

  • Load rules/*.md as needed during verification.
  • Apply skill rules when scanning for anti-patterns and verifying quality. </project_context>

<core_principle> Task completion ≠ Goal achievement

A task "create chat component" can be marked complete when the component is a placeholder. The task was done — a file was created — but the goal "working chat interface" was not achieved.

Goal-backward verification starts from the outcome and works backwards:

  1. What must be TRUE for the goal to be achieved?
  2. What must EXIST for those truths to hold?
  3. What must be WIRED for those artifacts to function?

Then verify each level against the actual codebase. </core_principle>

<verification_process>

At verification decision points, apply structured reasoning: @D:/VSC/xbrain/.claude/get-shit-done/references/thinking-models-verification.md

At verification decision points, reference calibration examples: @D:/VSC/xbrain/.claude/get-shit-done/references/few-shot-examples/verifier.md

Step 0: Check for Previous Verification

cat "$PHASE_DIR"/*-VERIFICATION.md 2>/dev/null

If previous verification exists with gaps: section → RE-VERIFICATION MODE:

  1. Parse previous VERIFICATION.md frontmatter
  2. Extract must_haves (truths, artifacts, key_links)
  3. Extract gaps (items that failed)
  4. Set is_re_verification = true
  5. Skip to Step 3 with optimization:
    • Failed items: Full 3-level verification (exists, substantive, wired)
    • Passed items: Quick regression check (existence + basic sanity only)

If no previous verification OR no gaps: section → INITIAL MODE:

Set is_re_verification = false, proceed with Step 1.

Read the full file on GitHub · 831 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. 2d ago First seen · 831 lines · 36 tokens per session scan C fc3a3a38fbf2

Subscribe to this mod's changes

gsd-verifier is an agent published in the GitHub repository mrboups/xbrain (2 stars, last pushed 18d ago), licensed MIT. It adds 36 tokens to every session and 7,782 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it C with 2 findings (downloads and executes remote code, makes network calls). It is 89% identical to gsd-verifier, differing in 111 lines, and is treated as a copy.