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.
git clone --depth 1 https://github.com/imgompanda/fireautoWrote 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/imgompanda/fireauto/memory-install)<a href="https://agentmods.dev/commands/imgompanda/fireauto/memory-install"><img src="https://agentmods.dev/badge/commands/imgompanda/fireauto/memory-install/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/commands/imgompanda/fireauto/memory-install"><img src="https://agentmods.dev/badge/commands/imgompanda/fireauto/memory-install.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00048 | $0.01398 |
| Opus 5.5 | $0.00019 | $0.00559 |
| Sonnet 5.5 | $0.00010 | $0.00280 |
| Haiku 4.5 | $0.00005 | $0.00140 |
Grade B, and why
memory-install 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 1mo 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.
`~/.claude/settings.json`을 읽고, `mcpServers` 필드에 `fireauto-mem`을 추가하세요. How it starts
The opening of the file, as written. The whole thing — 193 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/memory-install — fireauto 메모리 설치
fireauto 메모리 시스템을 원클릭으로 설치합니다.
설치 항목
- 의존성 설치 (sql.js, express, @modelcontextprotocol/sdk)
- 데이터베이스 초기화
- MCP 서버 등록
- Hook 스크립트 설정
- 설치 확인
실행 순서
Step 1: 환경 확인
Node.js 버전을 확인하세요:
node --version
- Node.js 18 이상이면 다음 단계로 진행하세요.
- Node.js가 없거나 18 미만이면 아래 메시지를 출력하고 중단하세요:
Node.js 18 이상이 필요해요.
설치: https://nodejs.org 에서 LTS 버전을 받아주세요.
환경 확인이 끝나면 유저에게 알려주세요:
fireauto 메모리 설치를 시작할게요.
Step 1/5 — Node.js {버전} 확인됨
Step 2: 의존성 설치
~/.fireauto-mem/ 디렉토리를 만들고 의존성을 설치하세요.
- 디렉토리 생성:
mkdir -p ~/.fireauto-mem
-
플러그인 루트의
plugin/scripts/mem/package.json을~/.fireauto-mem/에 복사하세요.{PLUGIN_ROOT}는 이 플러그인의 실제 절대 경로로 대체하세요. -
~/.fireauto-mem디렉토리에서npm install을 실행하세요.
- 설치에 성공하면 다음 단계로 진행하세요.
- 설치에 실패하면 에러 메시지를 보여주고 중단하세요:
의존성 설치에 실패했어요.
에러: {npm 에러 메시지}
네트워크 연결을 확인하고 다시 시도해주세요.
성공 시 유저에게 알려주세요:
Step 2/5 — 의존성 설치 완료 (sql.js, express, MCP SDK)
Step 3: 데이터베이스 초기화
db.cjs의 initDb()를 호출해서 스키마를 생성하세요.
환경변수 설정:
DB_PATH:~/.fireauto-mem/fireauto-mem.dbNODE_PATH:~/.fireauto-mem/node_modules
node로 {PLUGIN_ROOT}/scripts/mem/db.cjs를 require한 뒤 initDb()를 호출하고, DB를 close하세요.
~/.fireauto-mem/fireauto-mem.db파일이 이미 존재하면 이 단계를 스킵하고 유저에게 알려주세요:
Step 3/5 — 데이터베이스가 이미 존재해요 (스킵)
- 새로 생성했으면:
Step 3/5 — 데이터베이스 초기화 완료
Step 4: MCP 서버 등록
~/.claude/settings.json을 읽고, mcpServers 필드에 fireauto-mem을 추가하세요.
추가할 설정:
{
"mcpServers": {
"fireauto-mem": {
"command": "node",
"args": ["{PLUGIN_ROOT}/scripts/mem/mcp-server.cjs"],
"env": {
"NODE_PATH": "~/.fireauto-mem/node_modules",
"DB_PATH": "~/.fireauto-mem/fireauto-mem.db"
}
}
}
}
{PLUGIN_ROOT}는 실제 절대 경로로 대체하세요.
주의사항:
settings.json을 수정할 때 반드시 기존 설정을 보존하세요. 덮어쓰기 금지!- 이미
mcpServers에fireauto-mem이 있으면 스킵하세요:
Step 4/5 — MCP 서버가 이미 등록되어 있어요 (스킵)
- 새로 등록했으면:
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.
- 1mo ago First seen · 193 lines · 48 tokens per session scan B 7deb0a667403
memory-install is a command published in the GitHub repository imgompanda/fireauto (140 stars, last pushed 6mo ago), licensed MIT. It adds 48 tokens to every session and 1,398 once invoked, about $0.0002 per session on Opus 5.5. 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
audit
Audit .flow/memory/ entries against the current codebase — Keep / Update / Consolidate / Replace / Delete / Harden per entry.
memory-migrate
Migrate legacy .flow/memory/{pitfalls,conventions,decisions}.md flat files into the categorized YAML schema — host agent classifies each entry directly.
memory
USE WHEN recalling past decisions, storing new insights, forgetting stale memories, linking memories, or reviewing pending memory proposals. Groups recall | learn (with optional --save-context) | forget | relate | propose.
analyze-context
USE WHEN you want to analyze project context before starting work on a task. Calls context + recall, then synthesizes goals, decisions, gotchas, and relevant memories into a pre-task brief.
prime
Prime context for fresh session: /prime [task hint] [--quick] [--verbose].
warden-select
Measure pending token-warden candidate rules for an agent on the golden suite, evict or activate them, and recompile the agent's memory.