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-searchgit 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-search)<a href="https://agentmods.dev/commands/thierryn/fire-flow/fire-search"><img src="https://agentmods.dev/badge/commands/thierryn/fire-flow/fire-search.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 | $0.00015 | $0.01954 |
| Opus 5 | $0.00008 | $0.00977 |
| Sonnet 5 | $0.00003 | $0.00391 |
| Haiku 4.5 | $0.00002 | $0.00195 |
Grade A, and why
power-search 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 — 330 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/fire-search - Skills Library Search
Search across 172 skills in 15 categories to find proven solutions and patterns.
Purpose
Find relevant skills from the Dominion Flow skills library to:
- Apply proven patterns to current tasks
- Avoid reinventing solutions
- Learn from past project successes
- Speed up development with tested approaches
Arguments
| Argument | Required | Description |
|---|---|---|
query |
Yes | Search term: keyword, category, tag, or problem description |
Usage Examples
# Search by keyword
/fire-search "database performance"
/fire-search "authentication"
/fire-search "pagination"
# Search by category
/fire-search "category:security"
/fire-search "category:api-patterns"
# Search by tag
/fire-search "tag:prisma"
/fire-search "tag:react"
# Search by problem description
/fire-search "slow queries taking too long"
/fire-search "how to handle API errors"
Process
Analyze the query to determine search type:
- Keyword search: Match against skill names, descriptions, and content
- Category filter:
category:Xsearches within specific category - Tag filter:
tag:Xsearches by skill tags - Problem description: Natural language matching against problem/solution sections
Query: "{query}"
Type: [keyword | category | tag | problem]
Search across all skill files in:
~/.claude/plugins/dominion-flow/skills-library/
Categories to search (15 total):
database-solutions/- Database patterns, queries, optimizationapi-patterns/- REST, GraphQL, versioning, error handlingsecurity/- Auth, validation, encryption, OWASPperformance/- Caching, optimization, bundle sizefrontend/- React, Vue, state management, CSStesting/- Unit, integration, E2E, mockinginfrastructure/- Docker, CI/CD, deploymentform-solutions/- Validation, multi-step, file uploadsecommerce/- Payments, cart, inventoryvideo-media/- Streaming, processing, uploadsdocument-processing/- PDF, parsing, generationintegrations/- Third-party APIs, webhooksautomation/- Scripts, scheduled tasks, workflowspatterns-standards/- Design patterns, code standardsmethodology/- Process, planning, review patterns
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 · 330 lines · 15 tokens per session scan A 8d46743c6f7d
power-search is a command published in the GitHub repository ThierryN/fire-flow (77 stars, last pushed 21d ago), licensed MIT. It adds 15 tokens to every session and 1,954 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
awesome-chatgpt
Search awesome-ChatGPT-repositories for open-source GitHub repositories related to ChatGPT and LLMs.
init
Scaffold a new MindBase project (v2 layout). Usage: /mb:init [template] [-- mission ...].
commit
智能生成 Git 提交信息并提交.
doctor.es
Diagnostica problemas de inferencia LLM en Mac: asiai doctor verifica el estado de los motores, conflictos de puertos, carga de modelos y estado de la GPU.
requirement-review
需求文档多角色评审（requirement-review）：需求文档 → 7-Agent 并行评审 → 重构高质量需求文档（Runtime 受控流程，0-7 阶段状态机）.
claude-request
Send a prompt to Claude Code via the LLM gateway with session tracking.