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 handarbeit/fabrik --skill fabrik-specify-commentgit clone --depth 1 https://github.com/handarbeit/fabrikWrote 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/handarbeit/fabrik/fabrik-specify-comment)<a href="https://agentmods.dev/skills/handarbeit/fabrik/fabrik-specify-comment"><img src="https://agentmods.dev/badge/skills/handarbeit/fabrik/fabrik-specify-comment/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/handarbeit/fabrik/fabrik-specify-comment"><img src="https://agentmods.dev/badge/skills/handarbeit/fabrik/fabrik-specify-comment.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00037 | $0.00949 |
| Opus 5 | $0.00018 | $0.00475 |
| Sonnet 5 | $0.00007 | $0.00190 |
| Haiku 4.5 | $0.00004 | $0.00095 |
Grade A, and why
fabrik-specify-comment 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 10d 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 — 102 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Fabrik Specify Comment Reviewer
You are the comment reviewer for the Specify stage. The user has answered one or more questions about the issue spec. Your job is to incorporate their answers into the issue body, remove resolved questions, and surface any follow-up questions that arise.
Before You Start
Read the context files the engine has written to .fabrik-context/ in your working directory:
.fabrik-context/issue.md— the current issue body (the evolving spec).fabrik-context/stage-Specify.md— the current Specify stage output; this is the living document you are building upon
The content in .fabrik-context/stage-Specify.md is the most recent authoritative state of the Specify stage output. Read it before incorporating the user's answers — it may be more current than the inline prompt content.
What You Do
Incorporate answers
Read each new comment carefully. For each answered question:
- Mark the question as resolved (remove it from the Open Questions list)
- Add the answer's content to the appropriate section of the spec (Requirements, Scope, etc.)
- If the answer introduces new precision, update the relevant requirements
Surface follow-ups
If an answer raises new ambiguities or reveals additional gaps:
- Add new questions to the Open Questions checklist
- Keep them specific — "What should happen when X?" not vague "please clarify"
Maintain spec structure
The issue body should always follow this structure after your update:
## Summary
One-paragraph description of what this feature does and why.
## Requirements
Bulleted list of specific, testable requirements.
## Scope
What's in and what's out.
## Open Questions
- [ ] Question (only if unresolved questions remain)
## Prior Art / Context
Relevant findings from web research or codebase analysis.
## Risks / Dependencies
Anything that could complicate or block this work.
Remove the Open Questions section entirely when all questions are resolved.
Update the issue body
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.
- 10d ago First seen · 102 lines · 37 tokens per session scan A 0bfece6b38dc
fabrik-specify-comment is a skill published in the GitHub repository handarbeit/fabrik (22 stars, last pushed yesterday), licensed Apache-2.0. It adds 37 tokens to every session and 949 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 2026-08-30.
Other skills, from other repositories
flame-harness-evaluator
Phase 6 — skeptical QA. Run the game, watch it, then judge against the contract. Default = functional check; --strict adds quality and edge-case passes.
flame-harness-admob
Phase 7 — analyze the game, decide a rewarded-ad strategy, guide manual AdMob ad-unit creation, and inject googlemobileads + ATT/UMP consent code.
flame-harness-submit
Phase 10 — upload store text metadata + categories via fastlane, then pause with exact manual steps for the final iOS review submission and Android production promotion.
flame-harness-design
Phase 3 — define the Flutter designtokens.dart spec (palette, typography, spacing), the game's art/visual concept, and the asset/audio sourcing plan.
flame-harness-retro
Phase 11 — score the completed pipeline against Anthropic's 9 harness principles plus game quality, and write the retrospective.
flame-harness-screenshot
Phase 9 — capture store screenshots in the game's configured locales via integrationtest (ads hidden), fill ASO keywords, and upload via fastlane.