goga-prototype-plan-verification

goga-prototype-plan-verification is a skill for Claude Code, Codex from qarium/goga. It costs 17 tokens per session (964 once invoked), scanned A, original, BSD-3-Clause.

A verification step that checks an assembled architecture plan against a project's design language and records the results.

In plain words
What is it for?
Use it to run the defined checks, fix failures in the plan, and produce a verification report with evidence for each result.
Why use it?
It finds inconsistencies in the planned files, dependencies, naming, syntax, and implementation order before the plan is used.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it to run the defined checks, fix failures in the plan, and produce a verification report with evidence for each result.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/qarium/goga/goga-prototype-plan-verification
View source ↗ qarium/goga
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.

Any agent
npx skills add qarium/goga --skill goga-prototype-plan-verification
Clone the repo
git clone --depth 1 https://github.com/qarium/goga

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 goga-prototype-plan-verification

README.md
[![agentmods](https://agentmods.dev/badge/skills/qarium/goga/goga-prototype-plan-verification/github.svg)](https://agentmods.dev/skills/qarium/goga/goga-prototype-plan-verification)
Your own site
<a href="https://agentmods.dev/skills/qarium/goga/goga-prototype-plan-verification"><img src="https://agentmods.dev/badge/skills/qarium/goga/goga-prototype-plan-verification/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 goga-prototype-plan-verification

Your own site · 80×15
<a href="https://agentmods.dev/skills/qarium/goga/goga-prototype-plan-verification"><img src="https://agentmods.dev/badge/skills/qarium/goga/goga-prototype-plan-verification.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 17 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 964 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 $0.00017 $0.00964
Opus 5.5 $0.00007 $0.00386
Sonnet 5.5 $0.00003 $0.00193
Haiku 4.5 $0.00002 $0.00096

Measured 14d ago against content hash 7be22a44f109, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

goga-prototype-plan-verification 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 14d 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.

goga/assets/skills/goga-prototype-plan-verification/SKILL.md · 99 lines

How it starts

The opening of the file, as written. The whole thing — 99 lines — stays where its author put it; the contents beside it link to each section on GitHub.

goga-prototype-plan-verification

Identity

You are responsible for verifying the created architecture plan and fixing the issues found.

Context

Use these skills for verification:

  • goga-cell and goga-cookbook — DSL validation (syntax, directives, design principles).
  • goga-codemanifest-base — base usages/annotations compliance.
  • goga-lang-disp — language correctness (naming, location file names).

Use this artifact for its specific purpose:

  • [ARCHITECTURE_PLAN] (at the path printed by goga history path -f arch.md) — use it as the object of verification: its implementation order, per-cell CODEMANIFESTs and .usages/ files, dependency map, and verification checklist, against which the DSL checks are run, failures are fixed in place, and the report is produced.

Workflow

Phase 1. Run all verification checks

Run every check in Verification Checks below. For each, record PASS/FAIL with evidence.

Phase 2. Fix failures

For each FAIL — fix the issue in the plan file and re-check.

Phase 3. Produce the report

Produce the [VERIFICATION_REPORT] (see Output Format).

WAIT

Present the final (fixed) plan and the [VERIFICATION_REPORT] to the user and obtain final confirmation before the pipeline concludes.

  • Confirmed → the pipeline is complete
  • User requests changes → address the feedback, re-verify, and present again

Verification Checks

  1. Completeness — every type, method, property from the approved solution is present in the plan
  2. DSL correctness — all CODEMANIFESTs syntactically correct (keys, signatures, document structure)
  3. Inter-cell consistency — Imports reference existing cells, types match
  4. Implementation order — each cell created after all cells it depends on
  5. No placeholders — no TBD, TODO, or incomplete descriptions in the plan's CODEMANIFEST files
  6. Usage of Imports.Types — every imported type is used in the body (signatures, mutations, embeddings, annotations)
  7. Usage of Imports.Usages — every imported practice is mentioned in at least one annotation
  8. Usage of Usages — every practice declared in the Usages header is mentioned in at least one annotation
  9. Algorithms in annotations — annotations for routines and methods describe the operation algorithm if achievable
  10. Annotation wording — annotations do not contain technical implementation details
  11. Resolvability of references in annotations — every backtick reference resolves (signature variable, imported/declared type, Usages/Imports practice)
  12. Location restrictions — every location value is a file name with extension only, no directories, no escaping the current level
  13. Absence of cross-imports — if cell A imports from cell B, cell B does not import from cell A
  14. Embedding from Imports — every embedded type (via ->) is available through Imports
  15. Mutations from available types — base types in mutations (Object::Target) are available (imported or declared)
  16. Entity / Routine correctness — types with methods/properties are Entities; types without are Routines and lack these sections
  17. Base usages from configuration — each base practice is included in Usages of all CODEMANIFESTs and referenced in at least one annotation
  18. Base annotations from configuration — base annotations are included in Annotations of all CODEMANIFESTs and contracts comply with them
  19. Language correctness — type/method/property names comply with target-language conventions; location values have correct file names for the target language

Read the full file on GitHub · 99 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. 14d ago First seen · 99 lines · 17 tokens per session scan A 7be22a44f109

Subscribe to this mod's changes

goga-prototype-plan-verification is a skill published in the GitHub repository qarium/goga (43 stars, last pushed today), licensed BSD-3-Clause. It adds 17 tokens to every session and 964 once invoked, about $0.0001 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 2026-10-02.

Related

Other skills, from other repositories

ci-troubleshoot

Diagnose failed GitHub Actions runs for pi-agent-dashboard: the 11-file workflow taxonomy, affected-test selection, the release pipeline, known failure modes, and how to read gh run logs and retrigger jobs. Use when a CI run is red, a release is stuck, a workflow won't dispatch, or you need to know which workflow does…

BlackBeltTechnology/pi-agent-dashboard · 97 tokens

node-inspect-debugger

See runtime state a console.log cannot reach — set real breakpoints, step, and dump the scope chain of a paused Node/TypeScript process. Use on "set a breakpoint", "inspect runtime state", "console.log isn't enough", "step through this", "what's in this closure at runtime", "attach a debugger". Not a logging or…

BlackBeltTechnology/pi-agent-dashboard · 83 tokens

performance-optimization

Measure-first performance work. Use on triggers like "it's slow", "profile this", "optimize perf", "fix the bottleneck", "improve load time / Core Web Vitals", or when a measured regression needs fixing. Enforces measure-before-optimize. Fills a perf gap not covered by existing project skills. Not a build/ship…

BlackBeltTechnology/pi-agent-dashboard · 77 tokens

systematic-debugging

Root-cause a bug already in front of you, instead of guessing at fixes. Use on triggers like "root cause this", "why is this failing", "debug systematically", "this test is flaky", "it works locally but not in CI", or when a fix attempt has already failed once. Enforces a phased evidence-first process before any code…

BlackBeltTechnology/pi-agent-dashboard · 86 tokens

debug-dashboard

Diagnose problems in the running pi-agent-dashboard system: server.log, /api/health, bridge WebSocket connectivity, vitest triage, known-issue FAQ entries. Routes UI/visual issues to the browser skill. Use when the server seems hung, a pi session won't connect, tests fail mysteriously, the dashboard shows a blank…

BlackBeltTechnology/pi-agent-dashboard · 89 tokens

canvas-webapp

Render a React/Vite (or any bundled) web app on the pi-dashboard canvas, which loads loopback URLs in a sandboxed opaque-origin iframe. Use when a canvas(target:{kind:"url"|"server"}) target shows up blank white, an empty surface, or a /live/ 500 ECONNREFUSED. Covers why Vite dev servers and non-CORS static servers…

BlackBeltTechnology/pi-agent-dashboard · 99 tokens