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 skills/humanerd-drew/opencode-drewgent/drewgent-runtime-checkupnpx skills add humanerd-drew/opencode-drewgent --skill drewgent-runtime-checkupgit clone --depth 1 https://github.com/humanerd-drew/opencode-drewgentWrote 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/skills/humanerd-drew/opencode-drewgent/drewgent-runtime-checkup)<a href="https://agentmods.dev/skills/humanerd-drew/opencode-drewgent/drewgent-runtime-checkup"><img src="https://agentmods.dev/badge/skills/humanerd-drew/opencode-drewgent/drewgent-runtime-checkup.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 | $0.00000 | $0.07617 |
| Opus 5 | $0.00000 | $0.03809 |
| Sonnet 5 | $0.00000 | $0.01523 |
| Haiku 4.5 | $0.00000 | $0.00762 |
Grade A, and why
{{AGENT_NAME_LOWER}}-runtime-checkup scanned grade A with 2 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
4. **Example 6/10 F2**: "kanban-dashboard port 5555 HTTP 000" → re-verified: actual port is 8765, `curl http://localhost:8765/kanban` returns 200. No fix needed. Reported as "False alarm: wrong port number in checkup." Runs shell commandslowCapability
Expected in a hook, worth knowing in a rule or an instructions file.
grep -A 10 "subprocess.Popen" ~/.{{AGENT_NAME_LOWER}}/scripts/dispatch_once_default.py How it starts
The opening of the file, as written. The whole thing — 490 lines — stays where its author put it; the contents beside it link to each section on GitHub.
{{AGENT_NAME}} Runtime Checkup
{{AGENT_NAME}} 코어 시스템의 "기본기"를 점검할 때 사용하는 표준 절차. 핵심 철학: "docs에서 Done이라고 한 것 ≠ 실제 구현". 항상 filesystem ground truth 로 verify.
When to Use
- "기본기 점검해줘", "코어 시스템 확인", "이거 진짜 작동해?" 류 요청
- P0/P1 review 문서가 "✅ Done"이라 한 항목 의심될 때
- Cron job / dispatcher / worker 가 silent failure 중인지 확인할 때
- Major refactor 후 회귀 점검
- 새 모델 / 새 환경에서 {{AGENT_NAME}} 설치 직후 sanity check
6-Phase Checkup (in order)
Workdir 주의
터미널 workdir 는 turn 사이에서 휘발됨. 모든 명령은 cd ~/.{{AGENT_NAME_LOWER}}/source/{{AGENT_NAME_LOWER}}-agent && prefix 필수. 절대 workdir 에 의존하지 말 것.
Phase 1 — Core Imports (1분)
AIAgent, signal_processor, context_compressor, brain_signals, event_bus 모두 import. import 실패 = P0 즉시 보고.
cd ~/.{{AGENT_NAME_LOWER}}/source/{{AGENT_NAME_LOWER}}-agent && source .venv/bin/activate
python3 -c "
from run_agent import AIAgent
from agent.signal_processor import get_signal_processor
from agent.context_compressor import ContextCompressor
from agent.brain_signals import get_signal_emitter
print('OK')
"
Phase 2 — Persistent State Health (1분)
SQLite DB 무결성. FK ON. Status 분포.
python3 -c "
import sqlite3
conn = sqlite3.connect('P2-hippocampus/kanban/state/{{AGENT_NAME_LOWER}}_tasks.db')
conn.execute('PRAGMA foreign_keys = ON')
for r in conn.execute('SELECT status, COUNT(*) FROM tasks GROUP BY status'):
print(r)
print('integrity:', conn.execute('PRAGMA integrity_check').fetchone())
"
기대값: FK violations 0, status 7종 (todo/ready/in_progress/blocked/completed/cancelled).
Phase 3 — Brain Signal Accumulation (1분)
signal_processor 인스턴스 state 확인.
python3 -c "
from agent.signal_processor import get_signal_processor
sp = get_signal_processor()
print('violations:', len(sp._violation_history))
print('dangerous_ops:', len(sp._dangerous_ops_history))
print('workflows:', len(sp._workflow_history))
"
기대값: violation ≥ 1, dangerous_ops ≥ 0 (사용 패턴에 따라 다름). 0/0/0이면 signal event bus wiring 끊긴 것.
Phase 4 — Dispatcher End-to-End (1분)
Cron이 1분마다 도는 dispatcher 직접 실행. ready task 없으면 0/0/0/0 정상.
What ships with it
4 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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 · 490 lines · 0 tokens per session scan A 37c289d4173f
{{AGENT_NAME_LOWER}}-runtime-checkup is a skill published in the GitHub repository humanerd-drew/opencode-drewgent (2 stars, last pushed 1mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 7,617 tokens. A static security scan graded it A with 2 findings (makes network calls, runs shell commands). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
chronicle
Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…
imagegen
Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…