gsd-verifier

gsd-verifier is an agent for Claude Code, Codex from Oisinwang/get-shit-done-codex. It costs 36 tokens per session (7,596 once invoked), scanned C, a copy of gsd-verifier, MIT.

A verification agent that checks whether a development phase achieved its intended result in the codebase, rather than merely completing its task list.

In plain words
What is it for?
It reads the project instructions and applicable rules, examines the actual code, performs goal-backward checks, and creates a VERIFICATION.md report, escalating unresolved gaps to the developer.
Why use it?
It independently tests the claimed outcome instead of trusting a summary written by another agent. This exposes missing or non-working parts of the promised result.

Agent for Claude CodeCodex

Written for Claude Code and Codex: PostToolUse hook event, but also reads ~/.codex or $CODEX_HOME. Also seen: mentions AGENTS.md; mentions Codex.

Good fit It reads the project instructions and applicable rules, examines the actual code, performs goal-backward checks, and creates a VERIFICATION.md report, escalating unresolved gaps to the developer.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/oisinwang/get-shit-done-codex/gsd-verifier
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.

Clone the repo
git clone --depth 1 https://github.com/Oisinwang/get-shit-done-codex

Made for: Claude Code, Codex.

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 gsd-verifier

README.md
[![agentmods](https://agentmods.dev/badge/agents/oisinwang/get-shit-done-codex/gsd-verifier.svg)](https://agentmods.dev/agents/oisinwang/get-shit-done-codex/gsd-verifier)
Your own site
<a href="https://agentmods.dev/agents/oisinwang/get-shit-done-codex/gsd-verifier"><img src="https://agentmods.dev/badge/agents/oisinwang/get-shit-done-codex/gsd-verifier.svg" alt="Measured on agentmods" height="20"></a>
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 7,596 The whole file, excluding the scripts and references it only reads on demand.
Security scan C 2 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin 84% 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 5.1 $0.00036 $0.07596
Opus 5 $0.00018 $0.03798
Sonnet 5 $0.00007 $0.01519
Haiku 4.5 $0.00004 $0.00760

Measured 7d ago against content hash 211802c9545f, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, 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 7d 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

84% identical to gsd-verifier — 283 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.

agents/gsd-verifier.md · 815 lines

How it starts

The opening of the file, as written. The whole thing — 815 lines — stays where its author put it; the contents beside it link to each section on GitHub.

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

@~/.codex/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.

<required_reading> @/.codex/get-shit-done/references/verification-overrides.md @/.codex/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 ./AGENTS.md if it exists in the working directory. Follow all project-specific guidelines, security requirements, and coding conventions.

Project skills: @~/.codex/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: @~/.codex/get-shit-done/references/thinking-models-verification.md

At verification decision points, reference calibration examples: @~/.codex/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 · 815 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. 7d ago First seen · 815 lines · 36 tokens per session scan C 211802c9545f

Subscribe to this mod's changes

gsd-verifier is an agent published in the GitHub repository Oisinwang/get-shit-done-codex (1 stars, last pushed 3mo ago), licensed MIT. It adds 36 tokens to every session and 7,596 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 84% identical to gsd-verifier, differing in 283 lines, and is treated as a copy.