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-brainstormgit 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-brainstorm)<a href="https://agentmods.dev/skills/qarium/goga/goga-brainstorm"><img src="https://agentmods.dev/badge/skills/qarium/goga/goga-brainstorm/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-brainstorm"><img src="https://agentmods.dev/badge/skills/qarium/goga/goga-brainstorm.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high System Prompt Leakage · line 166 Skill contains instructions that could directly expose system prompts, internal rules, or hidden instructions to users or external parties.Fix: Remove any instructions that reveal, print, or output system prompts or internal rules. System instructions should never be exposed to end users.
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 | $0.00014 | $0.02118 |
| Opus 5 | $0.00007 | $0.01059 |
| Sonnet 5 | $0.00003 | $0.00424 |
| Haiku 4.5 | $0.00001 | $0.00212 |
Grade A, and why
goga-brainstorm 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.
How it starts
The opening of the file, as written. The whole thing — 191 lines — stays where its author put it; the contents beside it link to each section on GitHub.
goga-brainstorm
Identity
You are the primary orchestration skill for the cells architecture brainstorm pipeline. You coordinate sub-skills in strict order, never performing design work yourself — each stage is delegated to the sub-skill responsible for it.
Mission
Produce an architecture plan (at the path printed by goga history path -f arch.md) describing which cells, CODEMANIFEST files, and .usages/ files
need to be created and in what order — designed collaboratively with the user through exploration, discussion, and
refinement.
Arguments
Arguments: $ARGUMENTS
Retain the original arguments for the duration of the session.
Pre-check: goga availability
Before starting work, execute:
goga --help
If the command is not found, STOP and warn the user.
Context Initialization
Load these skills via the Skill tool before starting the pipeline.
goga-cell— DSL specification: cell and CODEMANIFEST structure, directives, and syntax.goga-cookbook— DSL application principles: when and how to apply cells, types, usages, and annotations.goga-lang-disp— language implementation rules: naming, signatures, andlocationfor the target language (routes to the per-language skill).goga-codemanifest-base— the project's base usages and annotations from.goga/config.yml.
Actively use these skills during design and analysis. Proceed to Pipeline Phase 1.
Requirements
- [DESIGN PRINCIPLE]:
First design types and their interactions without cell boundaries, then group types into cells.
This lets the agent see all connections between types before cell boundaries hide them. The pipeline enforces this
order: types are mapped (Phase 4) and detailed (Phase 5) before they are distributed across cells (Phase 6). Use
goga-cellandgoga-cookbookto verify design decisions throughout. - [SKILL AUTHORITY]: When designing cells, CODEMANIFESTs, and
.usages/files, derive every decision from the loaded skills — they are the authoritative source for HOW to design.goga-cell— DSL specification (dsl.md):- Cell structure — what a cell consists of (CODEMANIFEST,
.usages/), how the document is organized (header, body, footer) - CODEMANIFEST directive purposes — what
Imports,Usages,Annotations, types, mutations, embeddings are responsible for - Syntactic correctness — key casing, signature rules,
locationrestrictions, declaration structure
- Cell structure — what a cell consists of (CODEMANIFEST,
goga-cookbook— DSL application principles:- When to create a cell — when to extract a separate cell, and when to extend an existing one
- Entity vs Routine — when a type should have
methods/properties, and when it is a single operation - Granularity — how large or small a cell should be, signs of too fine or coarse splitting
- Usages connection form — file, inline, or URL, in which cases each form is appropriate
- Design order — design cells from leaves to root, starting with cells without dependencies
- When to use mutations (
Object::Target) and embeddings (->Entity: {}), and whenImportsare sufficient - Writing usage files in
<cell_path>/.usages/— structure, content, quality recommendations
goga-lang-disp— language implementation rules (routes to the target language skill):- Implementation conventions: cell structure, facade, signature rules, naming
- Examples in other skills may use naming from one language (e.g., snake_case), while the target language requires another (e.g., PascalCase) — the language skill is authoritative for the target language
goga-codemanifest-base— base usages and annotations from.goga/config.yml, mandatory when designing all CODEMANIFEST files in the plan
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.
- 2d ago Changed 36b018fc0219
- 10d ago First seen · 191 lines · 14 tokens per session scan A 2b003e34f04b
goga-brainstorm is a skill published in the GitHub repository qarium/goga (25 stars, last pushed 2d ago), licensed BSD-3-Clause. It adds 14 tokens to every session and 2,118 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 2026-08-30.
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…
release-cut
Cut a new pi-agent-dashboard release: promote ## [Unreleased] in CHANGELOG.md, bump every workspace package.json per SemVer, commit, tag v , and push — triggering the Release workflow that publishes every non-private workspace, builds the Electron artifacts, and creates a GitHub Release. Use on "cut a release"…
ship-it
Worktree-side implementation orchestrator for an OpenSpec change. Idempotent: gates automated scenarios on filesystem reality, owns the red-test fix loop, runs the docker harness with always-teardown, then drives ship-change inline. Escape hatch writes SHIPITBLOCKED.md. Runnable headless. Triggers: "ship it", "build…
spec-coherence-check
Sweep all active OpenSpec proposals for staleness, conflicts, and obsolescence against the current codebase and archived changes. Use when proposals may be outdated, when checking cross-proposal conflicts, or before starting a batch of implementations. Produces a gap-analysis report, updates a priority queue file, and…
faq-mine
Mine docs/faq.md from README.md, docs/.md, and the pi-hermes memory stores. Dispatches @fast subagents per source, dedupes against the existing FAQ, and merges entries in caveman style. Use when asked to "build / regenerate / extend the FAQ", "mine docs into FAQ", "mine hermes memory into FAQ", "surface runtime…
session-to-guideline
Turn a pi session into a Markdown "how-we-did-it" collaboration guideline: reads the session's JSONL transcript and synthesizes a reusable playbook of which prompts worked, what had to be steered, and how to reproduce the result faster. Use when: "document this session", "write up how we did X with the AI", "make a…