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-task-by-specifyinggit 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-task-by-specifying)<a href="https://agentmods.dev/skills/qarium/goga/goga-task-by-specifying"><img src="https://agentmods.dev/badge/skills/qarium/goga/goga-task-by-specifying/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-task-by-specifying"><img src="https://agentmods.dev/badge/skills/qarium/goga/goga-task-by-specifying.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 | $0.00014 | $0.02179 |
| Opus 5.5 | $0.00006 | $0.00872 |
| Sonnet 5.5 | $0.00003 | $0.00436 |
| Haiku 4.5 | $0.00001 | $0.00218 |
Grade A, and why
goga-task-by-specifying 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.
How it starts
The opening of the file, as written. The whole thing — 222 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Task Formulation
Purpose
Transforms a raw user request (e.g., "add authorization") into a formulated task — a structured document containing
the description, technology stack, dependencies, and scope estimate. The output is persisted at the path printed by
goga history path -f task.md (run goga history ensure first if the topic directory does not exist)
and serves as input for the goga-prototype skill.
When the request decomposes into several subtasks, the main task (the first subtask) is persisted as described above;
each additional subtask becomes a separate topic via goga topics create <branch-name> --todo with its full task
document piped via stdin.
Dialogue Rules
-
Drive the conversation through hypotheses. Present concrete options rather than open-ended questions.
-
Ask one question per message. Deliver a single focused question with 2-4 answer options.
-
Structure every response. This discipline prevents unstructured discussion.
Phase 1: Input Collection
Accept the user's description of the desired outcome.
The description may be:
- Brief — a single sentence or feature name
- Detailed — a complete specification with requirements
If the description is brief, do not request clarifications yet. Phase 3 will resolve missing details. Retain the original description throughout the session.
Phase 2: Context Loading
Step 1: Load the DSL specification
Invoke goga-cell via the Skill tool.
Purpose:
- Understand cell and CODEMANIFEST terminology for analyzing the existing architecture
Step 2: Load DSL application principles
Invoke goga-cookbook via the Skill tool.
Purpose:
- Understand the two-level usages model (project-level
.goga/usages/and cell-level<cell_path>/.usages/) - Learn usage file authoring principles for creating
.goga/usages/cooks/
Step 3: Retrieve the project schema
Run goga schema to obtain the cell hierarchy.
If the project lacks an existing architecture, record this as a known fact.
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.
- 14d ago First seen · 222 lines · 14 tokens per session scan A 557c785ca344
goga-task-by-specifying is a skill published in the GitHub repository qarium/goga (43 stars, last pushed today), licensed BSD-3-Clause. It adds 14 tokens to every session and 2,179 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.
Other skills, from other repositories
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…
kano-backlog
Prioritize and refine a GitHub Issues backlog with the Kano model — categorize every open issue as Must-be, Performance, Attractive, Indifferent, or Reverse, apply Kano + priority labels back to GitHub automatically, and recommend the single best next issue to pick up. Use this whenever the user wants to triage…
send-feedback
Explicit Codex workflow: Collect reviewed, sanitized rn-dev-agent feedback and create a GitHub issue only with user confirmation.
babysit-babysitter-issues
This skill should be used when the user asks to "babysit issues", "work on assigned issues", "check a5c-agent issues", "process babysitter issues", or wants to find and work on open GitHub issues assigned to a5c-agent in the babysitter repo.
cog-meeting-processing
Process meeting recordings and transcripts into decisions, action items, and team dynamics.
cog-team-intelligence
Cross-reference GitHub, Linear, Slack, and PostHog with bidirectional sync for team briefs.