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-resurrectgit clone --depth 1 https://github.com/ThierryN/fire-flowWrote 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/thierryn/fire-flow/fire-resurrect)<a href="https://agentmods.dev/commands/thierryn/fire-flow/fire-resurrect"><img src="https://agentmods.dev/badge/commands/thierryn/fire-flow/fire-resurrect.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 | $0.00018 | $0.07848 |
| Opus 5 | $0.00009 | $0.03924 |
| Sonnet 5 | $0.00004 | $0.01570 |
| Haiku 4.5 | $0.00002 | $0.00785 |
Grade A, and why
fire-resurrect 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.
How it starts
The opening of the file, as written. The whole thing — 860 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/fire-resurrect
Burn the Frankenstein. Rise production-ready. Reverse-engineer INTENT from messy code, ask clarifying questions, then rebuild clean in a new folder.
Purpose
Take a messy "vibe coded" project and autonomously rebuild it into a clean, production-quality application. The source folder is never modified — the rebuild happens in a new target folder using the full Dominion Flow pipeline.
What makes this different from refactoring: Refactoring improves code incrementally. Resurrection Mode burns the old code entirely and rebuilds from extracted INTENT. The result carries the knowledge but none of the accidental complexity.
Reference: @skills-library/_general/methodology/PHOENIX_REBUILD_METHODOLOGY.md
Core pipeline:
AUTOPSY → DATABASE → INTENT → CLARIFY → VISION → REBUILD → COMPARISON
Arguments
arguments:
--source:
type: path
required: true
description: "Path to the messy source project"
example: "/fire-resurrect --source C:/Projects/my-app"
--target:
type: path
required: false
default: "{source}-phoenix"
description: "Path for the clean rebuild output"
example: "/fire-resurrect --source ./app --target ./app-v2"
--migrate:
type: boolean
default: false
description: "Enable stack migration mode (propose alternative tech stacks)"
--dry-run:
type: boolean
default: false
description: "Run Phases 1-4 only (autopsy + database + intent + clarify). No rebuild."
--focus:
type: string
required: false
description: "Limit analysis to a specific subsystem"
example: "/fire-resurrect --source ./app --focus auth"
--db-strategy:
type: string
required: false
default: "auto"
description: "Database continuity strategy: 'auto' (detect best), 'reuse' (point to existing), 'clone' (dump+restore), 'fresh' (new empty DB with migrations only), 'skip' (no database)"
example: "/fire-resurrect --source ./app --db-strategy clone"
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.
- 3d ago First seen · 860 lines · 18 tokens per session scan A 86d6d027ceb5
fire-resurrect is a command published in the GitHub repository ThierryN/fire-flow (77 stars, last pushed 21d ago), licensed MIT. It adds 18 tokens to every session and 7,848 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.
Other commands, from other repositories
git
Git operations with intelligent commit messages and workflow optimization.
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.