flame

A command for reviewing ideas from several viewpoints and assigning scores to them. It is part of the specsmd idea-development workflow.

In plain words
What is it for?
Evaluate ideas supplied directly or stored in the Spark Bank, follow the project’s review rules, and route the work to related idea-generation or development stages.
Why use it?
It gives an idea a structured review instead of leaving evaluation to one unexamined opinion. The command also checks the project’s idea bank and configuration before starting.

Command

Install

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.

agentmods
npx agentmods add commands/fabriqaai/specs.md/flame
Clone the repo
git clone --depth 1 https://github.com/fabriqaai/specs.md
Per session 10 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 274 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00010 $0.00274
Opus 5 $0.00005 $0.00137
Sonnet 5 $0.00002 $0.00055
Haiku 4.5 $0.00001 $0.00027

Measured 3d ago against content hash 7956c7a3eca7, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

flame 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 3d 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.

src/flows/ideation/commands/flame.md · 44 lines

What it actually says

Activate Flame

Command: /specsmd-flame


Activation

You are now the Ideation Orchestrator in Flame mode for specsmd.

IMMEDIATELY read and adopt the persona from: → .specsmd/ideation/agents/orchestrator/agent.md

Then execute the Flame skill: → .specsmd/ideation/agents/orchestrator/skills/flame/SKILL.md


Critical First Steps

  1. Read Config: .specsmd/ideation/memory-bank.yaml
  2. Read Interaction Protocol: .specsmd/ideation/shared/protocols/interaction-adaptation.md
  3. If Spark Bank exists: Load it and begin evaluation
  4. If ideas provided directly: Accept them and begin evaluation
  5. If nothing: Ask "Which ideas would you like to evaluate?"

Routing Targets

  • Back to Orchestrator: /specsmd-ideation
  • To Spark: /specsmd-spark
  • To Forge: /specsmd-forge

Begin

Activate now. Read the Flame skill and start evaluating ideas.

Changes

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.

  1. 3d ago First seen · 44 lines · 10 tokens per session scan A 7956c7a3eca7

Subscribe to this mod's changes

flame is a command published in the GitHub repository fabriqaai/specs.md (205 stars, last pushed 10d ago), licensed MIT. It adds 10 tokens to every session and 274 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.