agentmods.dev

goal-engineering: Skill for Claude Code

.grok/skills/goal-verifier/SKILL.md

goal-verifier is a skill for Claude Code, Codex from cobusgreyling/goal-engineering. It costs 71 tokens per session (447 once invoked), scanned A, original, MIT.

A reviewer workflow that checks whether a Grok Build goal is genuinely finished. It reads the goal's completion criteria, gathers evidence, and runs the project's tests.

In plain words
What is it for?
Use it before marking a goal complete, especially when checking tests, required files, acceptance criteria, regression fixes, or refactors.
Why use it?
It catches incomplete work that may appear done but does not meet every stated condition.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: mentions subagents; mentions AGENTS.md.

This is cobusgreyling/goal-engineering's own configuration. It tells Claude Code and Codex how to work on goal-engineering itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything goal-engineering configures →

not rated 51repo 4mo ago A scan 71 tokens original MIT
View source ↗ cobusgreyling/goal-engineering cobusgreyling.github.io
Reuse

Borrowing it

Nothing to install: this file belongs to cobusgreyling/goal-engineering. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/cobusgreyling/goal-engineering/main/.grok/skills/goal-verifier/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/cobusgreyling/goal-engineering

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 goal-verifier

README.md
[![agentmods](https://agentmods.dev/badge/skills/cobusgreyling/goal-engineering/goal-verifier/github.svg)](https://agentmods.dev/skills/cobusgreyling/goal-engineering/goal-verifier)
Your own site
<a href="https://agentmods.dev/skills/cobusgreyling/goal-engineering/goal-verifier"><img src="https://agentmods.dev/badge/skills/cobusgreyling/goal-engineering/goal-verifier/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 goal-verifier

Your own site · 80×15
<a href="https://agentmods.dev/skills/cobusgreyling/goal-engineering/goal-verifier"><img src="https://agentmods.dev/badge/skills/cobusgreyling/goal-engineering/goal-verifier.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 71 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 447 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 $0.00071 $0.00447
Opus 5.5 $0.00028 $0.00179
Sonnet 5.5 $0.00014 $0.00089
Haiku 4.5 $0.00007 $0.00045

Measured 2mo ago against content hash df1efb5e52b9, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

goal-verifier 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 2mo 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.

.grok/skills/goal-verifier/SKILL.md · 52 lines

What it actually says

Goal Verifier

You are the checker — not the implementer. Your job is to prove the goal is done or explain precisely what is not.

Steps

  1. Read GOAL.md — objective, done condition checklist, deny list.
  2. For each done-condition item, gather evidence (test output, grep, file existence).
  3. Run the project's test command from AGENTS.md or package.json / pyproject.toml.
  4. If any checklist item fails → REJECT with specific gaps.
  5. If all pass → PASS with evidence summary (test command, key metrics).

Output Format

VERDICT: PASS | REJECT

Evidence:
- [item]: [proof]

Gaps (if REJECT):
- [what remains]

Pattern-specific checks

If the active goal matches a pattern, apply extra gates:

Pattern Extra verifier step
migrate-module rg '<legacy-path>' src/ tests/ must be empty
coverage-target Parse coverage report; reject hollow tests
fix-bug Repro steps fail; regression test file exists
refactor-safely Full suite green; no weakened test assertions
implement-feature Each acceptance criterion has evidence; no scope creep

Starters ship tailored verifier skills under starters/<pattern>/.grok/skills/goal-verifier/.

Rules

  • Do not implement fixes — only verify.
  • Do not trust the implementer's summary without running checks.
  • PASS only when every checkbox in GOAL.md Done Condition is objectively met.
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. 2mo ago First seen · 52 lines · 71 tokens per session scan A df1efb5e52b9

Subscribe to this mod's changes

goal-verifier is a skill published in the GitHub repository cobusgreyling/goal-engineering (51 stars, last pushed 4mo ago), licensed MIT. It adds 71 tokens to every session and 447 once invoked, about $0.0003 per session on Opus 5.5. 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.

Building agentsai-agentsautomationgoal-engineeringgrokgrok-buildverifier-skills
Related

goal-verifier compared with skills from other repositories

goal-verifier next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
goal-verifiercobusgreyling/goal-engineeringSkill514mo agoMITA71Claude Code, Codex
grok-subagentWalvez/grok-subagentSkill53mo agoMITA112Codex
delegate-to-grokSunwood-ai-labs/delegate-to-grok-skillSkill22mo agoMITA74Codex
grok-promptingdavit-khaburdzania/grok-plugin-ccSkill12mo agoApache-2.0A31Claude Code
grok-bridgeconrad85/grok-bridgeSkill02mo agoMITA90Codex
nexfadeNexFade/nexfade-grok-pluginSkill02mo agoMITA26Claude Code
readiness-scorercobusgreyling/grok-build-showcaseSkill25mo agoMITA98Claude Code