goal-verifier

A verification process that checks whether an implementation actually meets its stated goals. It examines whether the result exists, contains real substance, is connected to the project, and works through its data flow.

In plain words
What is it for?
Use it after implementation plans, tests, or feature work to require fresh evidence before accepting the result.
Why use it?
It prevents a task from being called complete merely because code compiles or someone says it should work.

Skill for Claude CodeCodex

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 skills/random6913/claude-code-superkit/goal-verifier
Any agent
npx skills add RaNDoM6913/claude-code-superkit --skill goal-verifier
Clone the repo
git clone --depth 1 https://github.com/RaNDoM6913/claude-code-superkit

Made for: Claude Code, Codex.

Per session 31 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 725 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00031 $0.00725
Opus 5 $0.00015 $0.00362
Sonnet 5 $0.00006 $0.00145
Haiku 4.5 $0.00003 $0.00072

Measured 2d ago against content hash 3044bc74523e, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, 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 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.

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.

packages/codex/skills/goal-verifier/SKILL.md · 83 lines

How it starts

The opening of the file, as written. The whole thing — 83 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Goal Verifier

Validates that implementation RESULTS match stated GOALS. Works backward from goals to code. Complements code reviewers (which check code quality) — this checks: does it actually work?

Phase 0: Load Project Context

Read if exists:

  1. AGENTS.md or CLAUDE.md — project conventions
  2. The implementation plan/spec that was executed
  3. git log --oneline -10 — recent commits

Verification Discipline

  • No approval without fresh evidence. A claim of "done/fixed/passing" requires fresh command output (test/build/run) printed in this turn — not a description, not "should work".
  • Hedge words auto-reject. If the work is justified with "should", "probably", "seems to", "I believe", or "appears to" instead of evidence, mark it NOT verified.
  • Verification is a separate pass from the one that authored the change — re-derive the result, don't trust the author's summary.
  • Work is done when verification passes — not when it compiles. A missing "yes" means "no".

When to Use

  • After Phase 5 (Test) in dev-orchestrator — before review
  • After completing an implementation plan
  • As part of the review-orchestrator pipeline for feature branches

4-Level Substantiation

For each stated goal, verify through 4 levels:

Level 1: EXISTS

Does the artifact exist?

  • Check files present: test -f "path/to/file"
  • Check functions exist: grep -n "func HandleX" file.go

Level 2: SUBSTANTIVE

Is it real implementation, not a stub?

  • Check for TODO/panic/NotImplemented/placeholder/lorem
  • Verify function has real logic (>5 lines, calls dependencies)
  • Check components render real content

Level 3: WIRED

Is it connected to the system?

  • Routes registered in router
  • Services injected via constructor
  • Components imported and rendered
  • Migrations in sequence

Level 4: DATA-FLOW

Does real data flow through?

  • Handler reads from request (json.Decode, chi.URLParam)
  • Service calls repo methods
  • Repo executes real SQL (INSERT, SELECT, not hardcoded)
  • Frontend calls real API (requestJSON, useQuery — not mock)

Read the full file on GitHub · 83 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 · 83 lines · 31 tokens per session scan A 3044bc74523e

Subscribe to this mod's changes

goal-verifier is a skill published in the GitHub repository RaNDoM6913/claude-code-superkit (2 stars, last pushed 1mo ago), licensed MIT. It adds 31 tokens to every session and 725 once invoked, about $0.0002 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 skills, from other repositories

apm-review-panel

Use this skill to run a multi-persona expert advisory review on a labelled pull request in microsoft/apm. The panel fans out to five mandatory specialists plus a test-coverage specialist (active on every PR that touches src/) plus three conditional specialists (auth, doc-writer, performance-expert), all running in…

microsoft/apm · 178 tokens

batch-bug-shepherd

Use this skill to drive a batch of suspected bugs in microsoft/apm from raw issue list to mergeable PR queue. Fan out one triage subagent per issue (LEGIT / UNCLEAR / FIXED-AT-HEAD), gate every legit bug against PRINCIPLES.md via an apm-ceo strategic-alignment pass, cross-reference legit issues against open PRs, then…

microsoft/apm · 227 tokens

apm-issue-autopilot

Use this skill to drive any open microsoft/apm issue (bug, feature, docs, refactor, perf) from raw intake to a mergeable PR with triage as the central, paramount gate. Run the apm-triage-panel rubric per issue first, then present ONE consolidated triage review for the whole batch and escalate to the maintainer BY…

microsoft/apm · 238 tokens

apm-spec-guardian

Use this skill to run a four-panel adversarial advisory review on any pull request that touches the OpenAPM specification artifact (docs/src/content/docs/specs/openapm-.md), its inline / sidecar JSON Schemas (docs/src/content/docs/specs/schemas/.schema.json), or the conformance fixture seed…

microsoft/apm · 215 tokens

apm-triage-panel

Use this skill to triage one microsoft/apm issue selected by the daily sweep, the status/needs-triage fast path, or manual dispatch. Emit one synthesized comment with a decision, label set, exact milestone, and suggested next action.

microsoft/apm · 59 tokens

cli-logging-ux

Use this skill when editing or creating CLI output, logging, warnings, error messages, progress indicators, or diagnostic summaries in the APM codebase. Activate whenever code touches console helpers (richsuccess, richwarning, richerror, richinfo, richecho), DiagnosticCollector, STATUSSYMBOLS, CommandLogger, or any…

microsoft/apm · 94 tokens