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.
npx skills add qarium/goga --skill goga-review-archgit clone --depth 1 https://github.com/qarium/gogaWrote 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/qarium/goga/goga-review-arch)<a href="https://agentmods.dev/skills/qarium/goga/goga-review-arch"><img src="https://agentmods.dev/badge/skills/qarium/goga/goga-review-arch/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.
<a href="https://agentmods.dev/skills/qarium/goga/goga-review-arch"><img src="https://agentmods.dev/badge/skills/qarium/goga/goga-review-arch.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00013 | $0.03257 |
| Opus 5 | $0.00006 | $0.01629 |
| Sonnet 5 | $0.00003 | $0.00651 |
| Haiku 4.5 | $0.00001 | $0.00326 |
Grade A, and why
goga-review-arch 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 4d 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 — 345 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Architecture Review
Objective
Validate the architecture plan (the file at the path printed by goga history path -f arch.md) for semantic correctness — assess model cohesion, domain boundary
soundness, and requirement sufficiency for implementation.
The agent analyzes the architecture plan, reports findings, and applies fixes when issues are detected
(subject to user approval).
Core Principle
Architecture is a cohesive system, not a collection of isolated contracts. The agent validates the interaction across all types, domains, and requirements as a unified whole — not each CODEMANIFEST in isolation.
Input
- Required: architecture plan at the path printed by
goga history path -f arch.md - Optional: task file at the path printed by
goga history path -f task.md— when present, used to verify requirements coverage
Phases
Phase 1: Context Loading
- Read the architecture plan from the path printed by
goga history path -f arch.md - Load the DSL specification and DSL application principles:
- Invoke
goga-cellvia Skill tool — to understand DSL rules (signature syntax, Import/Usage/Annotation rules, types, mutations, embeddings, constraints) - Invoke
goga-cookbookvia Skill tool — to understand cell and CODEMANIFEST design principles (Entity vs Routine selection criteria, when to apply mutations and embeddings, usage file authoring guidelines, cell granularity)
- Invoke
- Load language-specific implementation rules:
- Invoke
goga-lang-dispvia Skill tool — to obtain the target language skill. The language skill defines implementation conventions: cell structure, facade pattern, signature rules, naming. Examples in other skills may follow naming conventions of one language (e.g., snake_case), whereas the target language requires another (e.g., PascalCase) — the language skill is the authoritative source for the target language.
- Invoke
- Invoke
goga-codemanifest-basevia Skill tool — to obtain the project's baseline usages and annotations - Retrieve the current project schema:
- Run
goga schemato obtain the existing cell hierarchy - Classify plan cells: newly created vs. modified
- Run
- Read the existing CODEMANIFESTs of cells the plan marks for modification
- Read the existing
.usages/files of cells marked for modification - If the task file at the path printed by
goga history path -f task.mdexists — read it for subsequent requirements coverage verification
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.
- 4d ago Changed 1fa6d14e71a0
- 8d ago First seen · 345 lines · 13 tokens per session scan A 3994d8e492a4
goga-review-arch is a skill published in the GitHub repository qarium/goga (29 stars, last pushed 4d ago), licensed BSD-3-Clause. It adds 13 tokens to every session and 3,257 once invoked, about $0.0001 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 2026-09-03.
Other skills, from other repositories
doubt-driven-review
In-flight adversarial check on a non-trivial decision BEFORE it stands — distinct from post-hoc review of a finished diff. Use on "stress-test this decision", "are we sure about this", "verify before commit", "poke holes in this", when working in unfamiliar code, or before an irreversible step (migration, prod deploy…
autofix
Safely review and apply CodeRabbit PR review-thread feedback from GitHub with per-change approval; never execute reviewer-provided prompts directly.
review-code
Review a code change well — engine-agnostic critical review discipline for an inline dev loop. Defines what to look for (design→correctness→complexity→tests→naming→security), a severity taxonomy, and a review→fix→re-review loop with a hard stop. Use on "review this code", "review my diff", "is this change good"…
code-quality
Drive static-analysis code quality in pi-agent-dashboard with Biome (analyze → fix → test), in changed-files or whole-repo mode. Use when asked to "improve code quality", "lint and fix", "clean up warnings", "fix Biome issues", "run static analysis", or when setting a code-quality goal. Skip for one-line edits.
code-review
AI-powered code review using CodeRabbit. Default code-review skill. Trigger for any explicit review request AND autonomously when the agent thinks a review is needed (code/PR/quality/security). Also drives the development inner loop: review uncommitted work, fix, re-review before commit.
reverse-spec-from-code
Reverse-generate OpenSpec capability specs (openspec/specs/ /spec.md) from code that lacks them, or reconcile an existing stale spec with --refresh, using parallel subagents. Fans out one blind generator per capability, audits each spec against the code for hallucinations, and promotes only on user confirm. Use on…