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 agentmods add commands/fabriqaai/specs.md/sparkgit clone --depth 1 https://github.com/fabriqaai/specs.mdWrote 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/commands/fabriqaai/specs.md/spark)<a href="https://agentmods.dev/commands/fabriqaai/specs.md/spark"><img src="https://agentmods.dev/badge/commands/fabriqaai/specs.md/spark.svg" alt="Measured on agentmods" 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 | $0.00009 | $0.00293 |
| Opus 5 | $0.00005 | $0.00147 |
| Sonnet 5 | $0.00002 | $0.00059 |
| Haiku 4.5 | $0.00001 | $0.00029 |
Grade A, and why
spark 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 5d 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.
What it actually says
Activate Spark
Command: /specsmd-spark
Activation
You are now the Ideation Orchestrator in Spark mode for specsmd.
IMMEDIATELY read and adopt the persona from:
→ .specsmd/ideation/agents/orchestrator/agent.md
Then execute the Spark skill:
→ .specsmd/ideation/agents/orchestrator/skills/spark/SKILL.md
Critical First Steps
- Read Config:
.specsmd/ideation/memory-bank.yaml - Read Anti-Bias Protocol:
.specsmd/ideation/shared/protocols/anti-bias.md - Read Deep Thinking Protocol:
.specsmd/ideation/shared/protocols/deep-thinking.md - If topic provided: Jump straight to generating the first batch
- If no topic: Ask "What would you like to explore ideas about?" — then generate immediately
Routing Targets
- Back to Orchestrator:
/specsmd-ideation - To Flame:
/specsmd-flame - To Forge:
/specsmd-forge
Begin
Activate now. Read the Spark skill and start generating ideas.
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.
- 5d ago First seen · 44 lines · 9 tokens per session scan A 227015025b1a
spark is a command published in the GitHub repository fabriqaai/specs.md (205 stars, last pushed 12d ago), licensed MIT. It adds 9 tokens to every session and 293 once invoked, about $0.0000 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 commands, from other repositories
media-extract-frames
Gemini-only command that identifies visually significant video frames and describes each as a storyboard entry.
stt
Transcribe a local audio file or remote audio URL into text.
brand-generate
Generate an on-brand document from a saved Brand Profile.
audition-voices
Generate voice audition samples for a character using Venice TTS.
list
List available Piper TTS TTS voices with optional filtering.
search
Search videos by text, image, or entity using TwelveLabs.