discord-agent-fleet
디스코드에 상주하는 대화형 AI 봇을 여러 개 만들고 운영한다. 상시 구동 머신에서 겪는 함정(절전 모드, 설정파일 자동로딩, 사용량 한도)을 함께 정리했다.
Supply asset profile
Coding and developer agents
Code review, repo analysis, testing, CI, GitHub, DevOps, and developer workflow skills.
Scenario
Database and SQL
I need my agent to inspect database schemas, write SQL, and explain query results.
Agent fit
Claude Code + OpenAI Agents + CLI
Codex, Claude Code, Cursor, CLI, or custom agents.
Install
Ready
npx skills add bam-bam-2/solo-skills --skill discord-agent-fleet
Maintenance
fresh
1d since push
Risk
Needs review
Dependency or permission surface needs review
GitHub quality
11
57/100 Quality · 59/100 Trust
Coverage tags
Review notes
Dependency or permission surface needs review · Permission surface may require sandboxing
Agent adoption scorecard
Trust, audit, and install readiness at a glance
These scores combine public repository metadata, OpenAgentSkill review signals, maintenance freshness, and install readiness. They are a shortlist signal, not a replacement for human review.
Quality
PromisingUseful candidate, but compare it with alternatives before adopting.
Trust
Do not auto-installTrust Score v5 found insufficient evidence for agent installation. Treat this as discovery material, not an executable recommendation.
Audit
Needs reviewA machine-readable review of install readiness, security metadata, maintenance, and adoption risk.
OpenAgentSkill Trust Score v5
Sandbox only
Choose a stronger alternative or inspect the source manually before any install attempt.
Stars
11 GitHub stars
Repo activity
11 stars, 4 forks
Maintenance
1d since push
License
MIT
Install
npx skills add bam-bam-2/solo-skills --skill discord-agent-fleet
Install safety
standard package or runtime install path
Permission surface
secrets or environment access, shell or command execution
Agent outcomes
No agent outcome data yet
Docs
Usable metadata, review docs
Risk summary
Review before production
- The skill is highly specific to the author's personal environment (project names, server IDs, user IDs, remote host alias), which may limit direct reuse by others without adaptation.
- Low GitHub adoption signal
- Quality score needs review
- Permission surface needs review: secrets or environment access, shell or command execution
Install readiness
Install path available
- Install path is available
- Repository evidence is available
- License is declared
- No Agent Proven outcome evidence yet
Agent-readable metadata
Machine-readable decision data for this skill.
Use this block or the embedded JSON to decide whether an agent should install this skill, choose an alternative, or ask for human review first.
Suited tasks
- Local desktop workflows
- Claude Code teams
- builders willing to evaluate younger projects
- Navigate local resources
Suited agents
Install decision
- Command
- npx skills add bam-bam-2/solo-skills --skill discord-agent-fleet
- Policy
- block
- Human review
- yes
Trust and risk
- Trust
- 51/100
- Audit
- 69/100
- Risk level
- Needs review
Outcome loop
- Endpoint
- /api/agent/outcome
- Event ID
- resolve
- Outcomes
- 5
Install command
npx skills add bam-bam-2/solo-skills --skill discord-agent-fleetDo not use when
- teams that need a vendor-supported SLA
- production agents without a repository review
- Low GitHub adoption signal
- The skill is highly specific to the author's personal environment (project names, server IDs, user IDs, remote host alias), which may limit direct reuse by others without adaptation.
- No OpenAgentSkill engagement data yet
Agent safety v2
25/100 · Avoid automatic install
This skill should not be selected by an agent without explicit human security review.
Do not auto-install. Inspect the source, dependencies, and permission surface first.
high
Shell or command execution
Skill metadata references terminal, CLI, shell, subprocess, or command execution workflows.
medium
Network access
Skill likely fetches remote pages, APIs, repositories, or external services.
medium
Filesystem access
Skill may read or write project files, documents, generated artifacts, or local workspace state.
high
Secrets or environment access
Skill metadata references credentials, tokens, environment variables, or secret-bearing workflows.
- High-risk permission hints: Shell or command execution, Secrets or environment access
- Dependency or permission surface needs review
Install targets
Install this skill in your agent workflow
Use the public install endpoint to fetch the command, safety checklist, target prompts, and canonical links for this skill.
OpenAgentSkill CLI
Resolve policy, run the source installer safely, and report a verified install receipt.
$ npx --yes https://github.com/Leon-Drq/openagentskill/releases/download/cli-v0.2.1/openagentskill-0.2.1.tgz install bam-bam-2-discord-agent-fleetAgent resolve plan
Let an agent verify fit before installing.
The Resolve API returns the selected skill, alternatives, safety policy, audit notes, install target, and copy-paste prompt an agent can follow without scraping this page.
Open JSON
/api/agent/resolve?task=Use%20discord-agent-fleet%20for%20an%20agent%20workflow&agent=codex&max_risk=medium
Resolve text
/api/agent/resolve?task=Use%20discord-agent-fleet%20for%20an%20agent%20workflow&agent=codex&max_risk=medium&format=text
Install handoff
/api/skills/bam-bam-2-discord-agent-fleet/install
Agent should check
- Task fit and alternatives from Resolve API.
- Audit score, trust score, and safety policy warnings.
- Install target compatibility for Codex, Claude Code, Cursor, or CLI.
Copy prompt
Task: Use discord-agent-fleet in this workspace.
Resolve first: https://www.openagentskill.com/api/agent/resolve?task=Use%20discord-agent-fleet%20for%20an%20agent%20workflow&agent=codex&max_risk=medium
Review install handoff: https://www.openagentskill.com/api/skills/bam-bam-2-discord-agent-fleet/install
Install command: npx skills add bam-bam-2/solo-skills --skill discord-agent-fleet
Before running it, summarize audit warnings, required permissions, and the fallback skill if install is risky.Agent handoff
Give an agent the install path, not another directory page.
Use the public install endpoint to fetch the command, safety checklist, target prompts, and canonical links for this skill.
Install handoff
/api/skills/bam-bam-2-discord-agent-fleet/install
LLM text format
/api/skills/bam-bam-2-discord-agent-fleet/install?format=text
Find alternatives
/api/skills/search?q=discord-agent-fleet&limit=3
Agent prompt
Use discord-agent-fleet for this task. Review https://www.openagentskill.com/api/skills/bam-bam-2-discord-agent-fleet/install, then install with: npx skills add bam-bam-2/solo-skills --skill discord-agent-fleetRegistry metadata
Agent-readable profile for automatic skill selection.
This page exposes the same decision, trust, audit, use-case, and install signals through the Registry API, so agents can rank this skill without scraping the UI.
Manifest
/api/registry/manifest/bam-bam-2-discord-agent-fleet
LLM text
/api/registry/manifest/bam-bam-2-discord-agent-fleet?format=text
Install alias
/api/registry/install/bam-bam-2-discord-agent-fleet
Recommend
/api/registry/recommend?task=Use%20discord-agent-fleet%20in%20an%20agent%20workflow&limit=3
Agent fit
Local desktop
Use-case tags
Platforms
Claude Code, OpenAI Agents
Audit report
Needs review · 69/100
A machine-readable review of install readiness, security metadata, maintenance, and adoption risk.
Agent decision cockpit
Needs validation for Local desktop
Do a manual repository review before adding this to an agent workflow.
Role in stack
Needs validation
Primary fit
Local desktop
Trust label
Needs manual review
Install path
Command ready
Use when
- Local desktop workflows
- Claude Code teams
- builders willing to evaluate younger projects
Evidence
- recent repository activity
- install command or GitHub repo available
- 57/100 quality profile
review first
- Low GitHub adoption signal
- The skill is highly specific to the author's personal environment (project names, server IDs, user IDs, remote host alias), which may limit direct reuse by others without adaptation.
- No OpenAgentSkill engagement data yet
Implementation path
- 1Install it in a sandbox agent and run one Local desktop task end to end.
- 2Compare output quality, latency, and failure behavior against at least one alternative.
- 3Promote it into production only after reviewing repository permissions, license, and maintenance signals.
Trust profile
Do not auto-install
Trust Score v5 found insufficient evidence for agent installation. Treat this as discovery material, not an executable recommendation.
GitHub adoption
FIX11 GitHub stars
Stars/forks activity
FIX11 stars, 4 forks; issue activity unavailable in current metadata
Recent maintenance
PASS1d since push
License clarity
PASSMIT
Good signals
- AI review approved
- Install path is available
- Repository evidence is available
- Recently maintained repository
- Install command has no obvious high-risk pattern
- Outcome loop is ready but needs first real agent run
Review before install
- The skill is highly specific to the author's personal environment (project names, server IDs, user IDs, remote host alias), which may limit direct reuse by others without adaptation.
- Low GitHub adoption signal
- Quality score needs review
- Permission surface needs review: secrets or environment access, shell or command execution
- GitHub adoption: 11 GitHub stars
- Stars/forks activity: 11 stars, 4 forks; issue activity unavailable in current metadata
- Dependency/runtime risk: command execution surface, credential or environment access
- Permission surface: secrets or environment access, shell or command execution
- No real agent outcome reports yet
- Human review required before unattended installation
Recommended action
Choose a stronger alternative or inspect the source manually before any install attempt.
Quality profile
Promising candidate for agent workflows
Useful candidate, but compare it with alternatives before adopting.
Workflow fit
Use this skill in these scenarios
Operate local tools
Local desktop
I need my agent to operate local files and desktop apps in a repeatable workflow.
Operate web apps
Browser automation
I need my agent to control a browser, fill forms, and verify web app workflows.
Automate repeated work
Workflow automation
I need my agent to automate a repeated workflow across tools and files.
Workflow fit
Add it to a complete workflow
Operate and verify web apps
Browser QA agent
A workflow for agents that navigate products, fill forms, take screenshots, and verify real user flows across web applications.
Turn skills into distribution
Content growth agent
A workflow for turning newly indexed skills into SEO briefs, social drafts, comparison pages, and reusable publishing workflows.
Inspect, patch, and verify code
Coding review agent
A workflow for software agents that inspect repositories, review pull requests, generate tests, and turn findings into shippable patches.
Alternative shortlist
Compare before you install
Similar skills that may fit this task.
UI-TARS Desktop
Run multimodal agents that operate desktop interfaces
MoneyPrinterTurbo
利用AI大模型,一键生成高清短视频 Generate short videos with one click using AI LLM.
Cua
Open-source infrastructure for Computer-Use Agents. Sandboxes, SDKs, and benchmarks to train and evaluate AI agents that can control full desktops (macOS, Linux, Windows).
Overview
--- name: discord-agent-fleet description: "디스코드에 상주하는 대화형 AI 봇을 여러 개 만들고 운영한다. 상시 구동 머신에서 겪는 함정(절전 모드, 설정파일 자동로딩, 사용량 한도)을 함께 정리했다." ---
# 원격 머신 에이전트 무리
사용자의 원격 머신(`ssh remote-host`)에 대화형 디스코드 봇이 셋 상주한다. 전부 같은 뼈대를 쓴다.
| 봇 | 폴더 | 아는 것 | launchd | |---|---|---|---| | 지식봇 | `~/Projects/<프로젝트>/` | 지식봇 8기수 기록 + 원자료 55개 | `com.bambam.daolab-agent` | | 스터디봇 | `~/Projects/<프로젝트>/` | 지피터스 글 2,000건 + 지난 아티클 + 사용자 스킬·메모리 | `com.bambam.gpters-agent` | | 커뮤니티봇 | `~/Projects/<프로젝트>/discord_bot/` | 커뮤니티 커뮤니티 운영(길드·슬래시명령 등) | `com.getback.bamnyangi` |
파이썬은 셋 다 `~/Projects/<프로젝트>/.venv/bin/python` 를 공유한다. 서버는 **ai공작실**(`1492202577700458797`) 하나. 허용 계정은 사용자 `483902030243692546`, 커뮤니티 `1407565803242520586`.
## 공통 뼈대
- `bot.py` — 디스코드 게이트웨이. DM은 전체 지식, 공개 채널은 멘션받을 때만 - `answer.py` — 인격+기억+자료를 조립해 LLM 호출 - `store.py` — 단기 대화를 SQLite 에 영구 저장 (재시작·재부팅에도 유지) - `persona.md` — 인격·말투. **매 응답마다 읽으므로 고치면 재시작 없이 반영** - `memory.md` — 장기기억. 응답에 `MEMORY:` 줄을 쓰면 자동 적립
기억이 두 층이라는 게 핵심이다. 단기(대명사 받기) + 장기(세션 끊어도 남는 사실). `초기화`는 단기만 끊고 장기는 남긴다.
## ⚠️ 이 기기의 함정 세 가지
### 1. 저전력 모드가 KeepAlive 자동 재시작을 막는다
원격 머신에 `lowpowermode = 1` 이 켜져 있으면, 프로세스가 죽어도 launchd 가 되살리지 않는다.
``` state = not running pended nondemand spawn = inefficient ```
"요청 없이 스스로 재기동하는 건 비효율적"이라며 **무기한 보류**한다. plist 에 `KeepAlive` 가 제대로 있어도 소용없고 `ProcessType` 을 바꿔도 안 통한다. 40초를 기다려도 안 풀리는 걸 실측했다.
- **배포·재시작할 때는 항상 `launchctl kickstart -k` 를 명시적으로 쓴다.** `bootstrap` 만으로는 프로세스가 안 뜬다. kickstart 는 명시적 요청이라 보류 정책을 우회한다. - 근본 해결은 `sudo pmset -a lowpowermode 0` 인데 비번 없는 sudo 가 안 걸려 있어 SSH 로는 못 한다. 사용자가 직접 쳐야 한다. - 이건 지식봇만의 문제가 아니라 **이 기기의 모든 launchd 상주 작업에 적용된다.**
### 2. CLAUDE.md 가 모든 CLI 호출에 자동으로 딸려간다
`claude` CLI 는 실행 디렉터리에 `CLAUDE.md` 가 없으면 **상위 폴더로 거슬러 올라가며 찾아서** 프롬프트에 넣는다.
커뮤니티봇가 호출당 14만 토큰을 쓰던 원인이 이거였다. 밤집사가 실제로 만드는 프롬프트는 4,766자인데, `discord_bot/` 한 칸 위의 `~/Projects/<프로젝트>/CLAUDE.md`(당시 170KB)가 매번 통째로 붙고 있었다. 2026-08-16 에 밤알바생·옛 작업이력을 `docs/CLAUDE-archive-*.md` 로 옮겨 **1만 4천 자(92% 감소)** 로 줄였다.
- 새 봇을 만들 때는 `subprocess` 에 **`cwd` 를 그 봇 폴더로 고정**하고, 그 폴더에 큰 `CLAUDE.md` 를 두지 않는다 - 토큰이 예상보다 크면 **프롬프트 코드부터 의심하지 말고 상위 폴더의 CLAUDE.md 크기를 먼저 재라** - `~/.claude/CLAUDE.md`(전역, 약 5KB)는 항상 붙는다. 이건 어쩔 수 없다
### 3. launchd PATH 에는 homebrew 가 없다 — 절대경로만으론 부족하다
launchd 는 PATH 를 `/usr/bin:/bin:/usr/sbin:/sbin` 으로만 준다. 그래서 CLI 를 절대경로로 불러도, **그 CLI 자체가 node 스크립트면 죽는다.**
``` Codex rc=127: env: node: No such file or directory ```
`codex` 는 `/opt/homebrew/lib/node_modules/@openai/codex/bin/codex.js` 로 가는 심링크이고 셔뱅이 `#!/usr/bin/env node` 다. PATH 에 `/opt/homebrew/bin` 이 없으면 node 를 못 찾는다. `claude` 는 네이티브 Mach-O 바이너리라 이 문제가 없다 — **그래서 claude 는 멀쩡한데 codex 폴백만 조용히 죽어 있는 상태가 만들어진다.** 2026-08-16 프로젝트 조사봇이 주간 한도에 걸렸을 때 폴백도 같이 실패해 15시간 리포트가 끊긴 원인이 이거였다.
두 겹으로 막는다.
1. **plist 에 PATH 를 박는다** (근본) ```xml <key>EnvironmentVariables</key> <dict> <key>PATH</key> <string>/opt/homebrew/bin:/usr/local/bin:/usr/bin:/bin:/usr/sbin:/sbin</string> </dict> ``` 2. **스크립트에서도 env 를 보강한다** (수동 실행 대비). `subprocess.run(..., env=_tool_env())` 로 `/opt/homebrew/bin` 을 PATH 앞에 끼운다.
**진단 코드도 같이 봐라.** `subprocess.run` 은 셔뱅 실패(rc=127)에 예외를 안 던진다. `try/except` 만으로 점검하면 **죽은 CLI 를 OK 로 찍는다.** 프로젝트 조사봇 `--check` 가 정확히 이 버그였고, 그래서 폴백이 몇 달 고장난 걸 아무도 몰랐다. 반드시 `returncode` 를 확인할 것.
검증은 launchd 환경을 재현해서 한다. ```bash ssh remote-host 'cd ~/ops/<봇> && env -i HOME=$HOME PATH=/usr/bin:/bin:/usr/sbin:/sbin /opt/homebrew/bin/python3 followup.py --check' ```
## LLM 호출은 구독으로만
**API 키(`ANTHROPIC_API_KEY`)를 쓰지 않는다.** 사용자가 명시적으로 금지했다. `~/Projects/<프로젝트>/agents/llm_cli.py` 가 공용 호출 모듈이다. `claude -p --output-format text` 를 stdin 으로 부르고, `CLAUDE_CODE_OAUTH_TOKEN` 을 넘긴다. PATH 가 없는 launchd 환경 대비로 `/opt/homebrew/bin/claude` 하드코딩 폴백이 있다.
사용량 한도(`weekly limit`) 문구가 나올 때만 Codex 로 한 번 재실행한다. 일반 오류로는 넘어가지 않는다. 자세한 규칙은 `claude-codex-fallback` 스킬.
모델은 `--model` 을 안 줘서 CLI 기본값(2026-08 기준 `claude-sonnet-5`)을 쓴다. 고정하려면 `--model sonnet|opus|fable`.
## 자주 하는 일
```bash # 상태 ssh remote-host 'for S in com.bambam.daolab-agent com.bambam.gpters-agent com.getback.bamnyangi; do echo "=== $S ==="; launchctl print gui/$(id -u)/$S 2>/dev/null | grep -iE "^\s+(state|pid) "; done'
# 재시작 (kickstart 필수) ssh remote-host 'launchctl kickstart -k gui/$(id -u)/com.bambam.daolab-agent'
# 로그 — 실제 로그는 bot.error.log 에 쌓인다 (bot.log 는 비어있는 경우가 많다) ssh remote-host 'tail -30 ~/Projects/<프로젝트>/bot.error.log'
# 디스코드 안 거치고 답변 엔진만 시험 ssh remote-host 'cd ~/Projects/<프로젝트> && set -a && . ./.env && set +a && ~/Projects/<프로젝트>/.venv/bin/python answer.py "질문"' ```
**코드는 로컬에서 쓰고 `scp` 로 보낸다.** 히어독으로 원격에 파이썬을 직접 쓰면 따옴표·한글 이스케이프가 깨진다(실제로 깨졌다).
## 새 봇을 만들 때
`daolab-agent` 를 통째로 복사하고 `answer.py` 의 지식 소스만 바꾸는 게 가장 빠르다. `store.py`·`bot.py`·`persona.md` 는 거의 그대로 간다.
만들기 전에 확인할 것: - **어느 계정으로 DM 하는가** — 봇은 자기와 같은 서버에 있는 사람하고만 DM 이 열린다 - **공개 채널에도 둘 것인가** — 그렇다면 지식 범위를 나눈다. 지식봇은 DM 에선 사용자판(대외비 포함), 채널에선 지식봇판(내부 데이터 없음)을 쓴다. 규칙으로 막지 말고 **자료를 안 주는 방식**으로 분리한다 - **봇끼리 무한루프** — 사람이 안 끼어든 연속 봇 응답이 3회 넘으면 침묵하게 한다 - 응답에 식별 접두어를 붙인다(`📓 [지식봇]` 등) - `allowed_mentions=discord.AllowedMentions.none()` 로 멘션 사고를 막는다
Technical details
- Version
- 1.0.0
- License
- MIT
- Last updated
- Aug 22, 2026
- Published
- Aug 22, 2026
Decision snapshot
Needs validation
recent repository activity
Audit
Install review
Install and adoption review
- Security
- 68/100
- Maintenance
- 100/100
- Install
- 92/100
Agent-proven evidence
Agent-proven evidence
Outcome reports after resolve, review, install, and one narrow run.
- Success rate
- —
- Recent failure
- —
- Outcomes
- 0
- Output quality
- —
- Failed
- 0
- Not relevant
- 0
- Installs
- 0
- Risk blocked
- 0
- Setup needed
- 0
- Production
- 0
No agent outcome data yet. The first agent run can report success, setup needs, risk blocks, failure, or not-relevant through /api/agent/outcome.
Install
Add to agent workflow
Free and open source. Review the report before installing into production agents.
Growth loop
Share kit
Scenario-led draft for discord-agent-fleet, ready for a manual X post.
Before you hand an agent a repeatable workflow, give it a repeatable starting point. discord-agent-fleet: 디스코드에 상주하는 대화형 AI 봇을 여러 개 만들고 운영한다. 상시 구동 머신에서 겪는 함정(절전 모드, 설정파일 자동로딩, 사용량 한도)을 함께 정리했다. 11 stars https://www.openagentskill.com/skills/bam-bam-2-discord-agent-fleet?ref=x
Optional reply with install command
Listing + install path for discord-agent-fleet: https://www.openagentskill.com/skills/bam-bam-2-discord-agent-fleet?ref=x Install: npx skills add bam-bam-2/solo-skills --skill discord-agent-fleet
Listing source
Registry indexed
This listing was indexed from public sources and is not marked official until a maintainer claim is approved.
- Creator
- bam-bam-2
- Source
- bam-bam-2/solo-skills
- Indexed by
- OpenAgentSkill community index
Attribution links to the public repository or creator profile. Creators can claim the listing to update ownership signals.
Claim this skillOwner claim
Claim this skill listing
This Registry indexed listing is attributed to bam-bam-2 but is not marked official yet. Claim it to add a verified owner signal and make future launch, install, and audit updates easier to trust.
Creator backlink kit
Add the evidence badges to your README
Show the canonical listing, current trust and audit signals, and real Agent-Proven evidence where developers evaluate the repository.
[](https://www.openagentskill.com/skills/bam-bam-2-discord-agent-fleet)
[](https://www.openagentskill.com/skills/bam-bam-2-discord-agent-fleet)
[](https://www.openagentskill.com/skills/bam-bam-2-discord-agent-fleet/audit)
[](https://www.openagentskill.com/skills/bam-bam-2-discord-agent-fleet)Author
bam-bam-2
@bam-bam-2
Tags
Platform fit
Health signals
- GitHub stars
- 11
- Quality score
- 30/100
- Last GitHub push
- Aug 22, 2026
- Framework hints
- Unknown
- OpenAgentSkill views
- 0
- Install copies
- 0
- Outbound clicks
- 0
Community signal
Share whether this skill looks useful for your agent workflow. Aggregated feedback improves rankings over time.
Trust & safety
Do not auto-install
- GitHub adoption11 GitHub starsFIX
- Stars/forks activity11 stars, 4 forks; issue activity unavailable in current metadataFIX
- Recent maintenance1d since pushPASS
- License clarityMITPASS
- README/SKILL.md completenessPublic metadata needs stronger README/SKILL.md contextINFO
- Dependency/runtime riskcommand execution surface, credential or environment accessFIX
Related skills
UI-TARS Desktop
Run multimodal agents that operate desktop interfaces
37.0K StarsMoneyPrinterTurbo
利用AI大模型,一键生成高清短视频 Generate short videos with one click using AI LLM.
88.5K StarsCua
Open-source infrastructure for Computer-Use Agents. Sandboxes, SDKs, and benchmarks to train and evaluate AI agents that can control full desktops (macOS, Linux, Windows).
21.4K Stars