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/thierryn/fire-flow/fire-setupgit clone --depth 1 https://github.com/ThierryN/fire-flowWhat 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 | $0.00012 | $0.02650 |
| Opus 5 | $0.00006 | $0.01325 |
| Sonnet 5 | $0.00002 | $0.00530 |
| Haiku 4.5 | $0.00001 | $0.00265 |
Grade B, and why
fire-setup scanned grade B with 1 finding 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 2d 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.
Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
cat > ~/.claude/developer-profile.md << 'EOF' How it starts
The opening of the file, as written. The whole thing — 360 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/fire-setup
Configure your Dominion Flow developer profile — answer 8 questions, unlock personalized wizard behavior
Purpose
Run once (or re-run to update preferences). Writes a ~/.claude/developer-profile.md
file that all Dominion Flow wizards read automatically, eliminating repetitive
onboarding questions across projects.
Before this command: Every new project starts from scratch — stack choices, convention preferences, tool habits are re-asked from zero.
After this command: Wizards skip questions already answered in your profile.
/fire-1a-new pre-selects your preferred stack. /fire-add-new-skill pre-fills
your most-used category. /fire-1d-discuss knows your expertise areas.
Arguments
arguments: none
optional_flags:
--update: "Re-run only the sections you want to change"
--view: "Show current profile without editing"
--reset: "Clear profile and start fresh"
Wizard Step Sequence
graph LR
S0[0: Check Existing] --> S1[1: Stack Preferences]
S1 --> S2[2: Expertise Areas]
S2 --> S3[3: Convention Defaults]
S3 --> S4[4: Tool Preferences]
S4 --> S5[5: Workflow Style]
S5 --> S6[6: Project Hints Config]
S6 --> S7[7: Review + Save]
S7 --> S8[8: Test Profile]
Process
Step 0: Check Existing Profile
test -f ~/.claude/developer-profile.md && echo "EXISTS" || echo "NEW"
If profile exists and --update not specified:
Your developer profile was last updated on {date}.
[View profile] [Update sections] [Reset and re-run]
If new or --reset: Begin from Step 1.
Step 1: Stack Preferences
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
DOMINION FLOW ► DEVELOPER PROFILE SETUP
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
Step 1 of 7 — Your Preferred Tech Stack
──────────────────────────────────────────────────────
This profile saves you from answering the same questions on every project.
These are defaults — you can always override per-project.
Frontend framework:
1. React (Vite) 2. React (Next.js) 3. Vue
4. Svelte 5. Vanilla JS 6. No preference
> [User selection]
Backend runtime:
1. Node.js (Express) 2. Node.js (Fastify) 3. Bun
4. Python (FastAPI) 5. Python (Django) 6. No preference
> [User selection]
Preferred database:
1. PostgreSQL (Supabase) 2. PostgreSQL (direct) 3. MySQL
4. SQLite 5. No preference
> [User selection]
ORM/Query builder:
1. Prisma 2. Drizzle 3. Knex 4. Raw SQL 5. No preference
> [User selection]
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.
- 2d ago First seen · 360 lines · 12 tokens per session scan B 008d4c0b5a6c
fire-setup is a command published in the GitHub repository ThierryN/fire-flow (77 stars, last pushed 20d ago), licensed MIT. It adds 12 tokens to every session and 2,650 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other commands, from other repositories
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.
implement
Execute the implementation plan by processing and executing all tasks defined in tasks.md.