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/plan)<a href="https://agentmods.dev/skills/sylorei/claude-godmode/plan"><img src="https://agentmods.dev/badge/skills/sylorei/claude-godmode/plan.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 | $0.00048 | $0.03381 |
| Opus 5 | $0.00024 | $0.01690 |
| Sonnet 5 | $0.00010 | $0.00676 |
| Haiku 4.5 | $0.00005 | $0.00338 |
Grade A, and why
plan 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 — 221 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Plan
Break the brief for roadmap unit $N into a tactical plan that makes building mechanical: ordered steps, an explicit dependency relationship per step (so /build can group steps into parallel waves), and a verification plan that covers every acceptance criterion from the brief.
Run after /brief N has captured the why + what + spec. The plan is the contract /build N executes against and /verify N checks. This is the third step of the spine: /mission → /brief N → /plan N → /build N → /verify N → /ship.
The artifact lives in the consumer's repo, alongside the brief it reads:
- Reads
.planning/missions/<mission_id>/briefs/NN-name/BRIEF.md— the brief for roadmap unit$N(mission_id=$("$gm/godmode-state" get mission_id); see the helper-resolution note in Process). - Writes
.planning/missions/<mission_id>/briefs/NN-name/PLAN.md— the single tactical plan for that unit.
Exactly two artifact files per work unit: BRIEF.md + PLAN.md. Do NOT introduce a third file — no EXECUTE.md, no separate execution-log file. The git log is the execution log. Write PLAN.md and nothing else.
Auto Mode
Auto Mode suppresses confirmation prompts, not the clarifying questions that decide the shape of the plan. In either mode:
- Ask the consequential questions — a genuinely ambiguous step ordering, an unstated constraint, a design fork where the options diverge materially — when the brief,
.planning/PROJECT.md, and the repo can't settle it. Guessing here produces a plan that builds the wrong thing efficiently. - Assume the trivial — for low-stakes judgment calls, pick a sensible default and record it under an Assumptions heading rather than asking.
- Don't re-ask what the brief already decided. Treat user course-corrections as normal input. A plan is a breakdown, not an interview — but the few questions that change the breakdown are worth asking in either mode.
Recommendation convention (godmode:recommend-convention). When you do ask, follow the shared convention in rules/godmode-recommend.md: lead with a Recommended option carrying a visible one-line rationale, then let the user override — never a flat menu of equal choices:
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 · 221 lines · 48 tokens per session scan A 2aa3bc3b26d3
plan is a skill published in the GitHub repository SyloRei/claude-godmode (3 stars, last pushed 3mo ago), licensed MIT. It adds 48 tokens to every session and 3,381 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.
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.