Getting it into your agent
This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.
/plugin marketplace add SyloRei/claude-godmode/plugin install claude-godmodeWrote 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.
[](https://agentmods.dev/skills/sylorei/claude-godmode/verify)<a href="https://agentmods.dev/skills/sylorei/claude-godmode/verify"><img src="https://agentmods.dev/badge/skills/sylorei/claude-godmode/verify.svg" alt="Measured on agentmods" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00058 | $0.06303 |
| Opus 5 | $0.00029 | $0.03152 |
| Sonnet 5 | $0.00012 | $0.01261 |
| Haiku 4.5 | $0.00006 | $0.00630 |
Grade A, and why
verify 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 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.
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.
How it starts
The opening of the file, as written. The whole thing — 380 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Verify
Decide what is truly done for roadmap unit $N by working goal-backward: start from the brief's acceptance criteria, not from the diff. For each criterion, return a verdict — COVERED / PARTIAL / MISSING — backed by concrete evidence (a file:line, a passing test name, or command output). A diff can look big and still miss a goal; only the goals decide the verdict.
Run after /build N has produced commits. Verify is the gate before shipping: if every criterion is COVERED, the unit is ready for /ship. This is the fifth step of the spine: /mission → /brief N → /plan N → /build N → /verify N → /ship.
This is a read-only operation. You inspect files, search the codebase, read the unit's diff, run the project's test command, and dispatch review lenses that themselves only read. You do not write or edit source — your only writes are workflow-state updates via bin/godmode-state and findings persistence via bin/godmode-findings. /verify only ever calls godmode-findings init, reconcile, and list — it never calls transition or waive and never auto-closes a finding. The open→fixed transition is /build's job; a finding that no lens re-reports this run stays open and is reported as stale.
Auto Mode
When ## Auto Mode Active is present in context: do not ask clarifying questions. Locate the brief and plan for unit $N, run the project's test command yourself to gather evidence, classify every criterion, and report. Treat user course-corrections as normal input.
When Auto Mode is absent, still avoid an interview — verification is mechanical. Ask only if you genuinely cannot find the brief or determine the project's test command.
Strictness — the core rule
Never report PARTIAL as COVERED. "Claimed" is not "verified".
- COVERED — you have concrete evidence the criterion is met: a
file:linethat implements it, a named test that exercises it and passes, or command output that demonstrates the observable result the brief asked for. No evidence → not COVERED. - PARTIAL — the criterion is partly met: some of the behavior exists, or it exists but a sub-condition or edge case from the criterion is unmet or unproven. Say exactly what is missing.
- MISSING — no evidence the criterion is met, or evidence that it is not.
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 7d ago First seen · 380 lines · 58 tokens per session scan A 9df0bbff43e2
verify is a skill published in the GitHub repository SyloRei/claude-godmode (3 stars, last pushed 3mo ago), licensed MIT. It adds 58 tokens to every session and 6,303 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.
Other skills, from other repositories
figma-verification
Extract Figma design specs before implementing UI components. Use depth 5, cache to disk, extract ALL properties, map to design system tokens.
interaction-design
Use when designing how a UI feels to use. Covers audience dimensions, discoverability, mode communication, keyboard-first UX, feedback timing, empty states, and information density. Includes WCAG 2.1 AA compliance audit. Companion to visual-design.
browser-testing
Adversarial browser testing. Use when testing UI behavior, verifying network requests, checking console errors, filling forms, or handling dialogs. The goal is finding bugs, not confirming happy paths.
debugging-protocol
Systematic protocol for diagnosing broken behavior and making recurrence structurally impossible. Schema mismatch causes 80% of bugs. Use when something isn't showing, isn't working, or is still broken after a fix attempt.
plan-mode
CEO and engineering review after spec-writing. Auto-selects weight class from the spec format (skip for task-mode, eng-only for routine, full CEO+eng for high-risk). Run /spec-writing first.
pr-review
Use when reviewing a PR or responding to review comments on your own PR. Detects authorship automatically and runs the correct mode. Never makes code changes when reviewing someone else's work.