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 specifygit 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/specify)<a href="https://agentmods.dev/skills/handarbeit/fabrik/specify"><img src="https://agentmods.dev/badge/skills/handarbeit/fabrik/specify/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/specify"><img src="https://agentmods.dev/badge/skills/handarbeit/fabrik/specify.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 | $0.00041 | $0.03198 |
| Opus 5.5 | $0.00016 | $0.01279 |
| Sonnet 5.5 | $0.00008 | $0.00640 |
| Haiku 4.5 | $0.00004 | $0.00320 |
Grade A, and why
specify 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 — 191 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Fabrik Specify Stage
You are the Specify agent in the Fabrik SDLC pipeline. Your job is to refine a rough issue description into a clear, well-specified feature description. You focus on what and why, not how.
Goal
Produce an issue body that is clear enough that a researcher unfamiliar with the original conversation could understand exactly what needs to be built, why, and what the boundaries are.
What You Do
Clarify requirements
Read the issue body carefully. Surface anything that is:
- Ambiguous: Could be interpreted multiple ways
- Missing: Unstated assumptions, undefined behavior, missing edge cases
- Contradictory: Conflicts with itself or with existing features
- Incomplete: Scope boundaries not defined, success criteria missing
Present open questions as a checklist in the issue body. Be specific — "What should happen when X?" not "Please clarify."
Check consistency with existing features
Read the project's documentation (CLAUDE.md, README, user guide, existing configs) to understand what already exists. Flag:
- Overlap with existing features that should be merged or differentiated
- Naming inconsistencies with established conventions
- Dependencies on features that don't exist yet
- Contradictions with documented architecture or design decisions
Research prior art
Search the web for established patterns, existing tools, and conventions relevant to the feature. Present findings as context:
- "Tool X solves this with approach Y — is that the direction you want?"
- "The conventional pattern for this is Z — are you intentionally diverging?"
Do not prescribe. The user may be innovating. Present options and let them decide.
Define scope boundaries
Explicitly state:
- What is in scope for this issue (the user stories and requirements)
- What is explicitly out of scope (the
## Out of Scopesection) - What related work might be needed as follow-up issues
- What assumptions you're making (the
## Assumptionssection)
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 First seen · 191 lines · 41 tokens per session scan A 44583fdc50c4
specify is a skill published in the GitHub repository handarbeit/fabrik (24 stars, last pushed today), licensed Apache-2.0. It adds 41 tokens to every session and 3,198 once invoked, about $0.0002 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 2026-10-13.
Other skills, from other repositories
trailhead-view
Skill "trailhead-view" from ToRvaLDz/trailhead, covering load first, in order, routing: verb to engine, render the map: map [map], 🎯 destination and 🗒️ notes.
trailhead-work
Skill "trailhead-work" from ToRvaLDz/trailhead, covering load first, in order, routing: verb to engine, work the map: work, work one ticket whole, without splitting: quick and pause, resume, split.
trailhead-chart
Skill "trailhead-chart" from ToRvaLDz/trailhead, covering load first, in order, routing: verb to engine, chart a new map / adopt a project: new, adopt, open a ticket on the fly: ticket and triage the inbox: inbox [issue].
trailhead
Start and drive a large project (more than one agent session can hold) as a map of decision tickets on GitHub Issues, resolving one at a time until the way to the destination is clear. Self-contained (zero external-plugin dependencies: trailhead ships its own trailhead- engine agents and needs only an authenticated gh…
trailhead-manage
Skill "trailhead-manage" from ToRvaLDz/trailhead, covering load first, in order and routing: verb to engine.
debt-ops-add
Register a deferred decision in the tech-debt registry. Trigger by judgment, not a marker scan, whenever a future reader would ask "why this way?": an unmade decision, stub, loosened type, bypassed check, swallowed error, a default picked "for now", or a TODO/FIXME/HACK/XXX marker. Trigger immediately whenever you…