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/daily-retronpx skills add humanerd-drew/opencode-drewgent --skill daily-retrogit 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/daily-retro)<a href="https://agentmods.dev/skills/humanerd-drew/opencode-drewgent/daily-retro"><img src="https://agentmods.dev/badge/skills/humanerd-drew/opencode-drewgent/daily-retro.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 5.1 | $0.00000 | $0.01314 |
| Opus 5 | $0.00000 | $0.00657 |
| Sonnet 5 | $0.00000 | $0.00263 |
| Haiku 4.5 | $0.00000 | $0.00131 |
Grade A, and why
daily-retro 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 5d 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 — 168 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Daily Retro — 30% Human Zone
Concept
From the "How to Be a 30x AI Engineer with a Taste" framework: the 30% of work that humans should do directly is the part where quality judgment matters most. The daily retro is that 30% applied to reflection and direction-setting.
The agent handles the mechanical part (summarizing the day, sending prompts, storing results). The human handles the judgment part (evaluating decisions, setting direction, identifying what matters).
Architecture
cron job (daily at scheduled time)
↓
Phase 1: Agent gathers today's work summary from kanban + recent sessions
↓ Discord deliver
User reads summary + answers 3 reflection questions in Discord
↓ Discord reply
Phase 2: Agent structures answers into vault, links to related tasks
↓
P2-hippocampus/retro/YYYY-MM-DD.md (wikilink chain)
Phase 1 — Daily Cron Job
Channel
- Discord channel:
#growth(ID:1492431680269713558) - 설정:
deliver="discord:1492431680269713558"
Setup
cronjob(
action="create",
name="daily-retro",
schedule="0 20 * * *", # daily at 20:00 KST
prompt="""Run the daily retro workflow:
1. Query kanban for tasks completed today (status='done')
2. Check recent session activity
3. Format a concise work summary
4. Send the retro prompt with 3 questions to the user""",
skills=["daily-retro"],
deliver="discord:<channel-id>",
)
What the message includes
━━━ 오늘 작업 요약 ━━━
• [task 1] — completed
• [task 2] — completed
• [key decision] — made
━━━ 오늘의 회고 ━━━
1. 오늘 가장 taste가 필요했던 결정은?
2. 내가(agent) 개선할 점이나 다르게 했으면 하는 것은?
3. 내일 집중할 한 가지는?
3 default questions
- Taste decision: "오늘 가장 taste가 필요했던 결정은?"
- Agent improvement: "내가(agent) 개선할 점이나 다르게 했으면 하는 것은?"
- Focus: "내일 집중할 한 가지는?"
These can be customized per user preference. Store custom questions in memory.
Phase 2 — Processing the Reply
When the user replies in Discord, the agent receives it in a normal session and must:
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.
- 5d ago First seen · 168 lines · 0 tokens per session scan A 31aedb518a67
daily-retro 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 1,314 tokens. 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 2026-08-31.
Other skills, from other repositories
orbit-notion
Open Orbit briefing skill — selected by the Orbit pipeline when Notion is the user's only connected connector, or when the user explicitly scopes their daily digest to Notion. Pulls the past 24 hours of document edits, comments, mentions, and database row changes from the user's authenticated Notion connection and…
Cortex
Operate Cortex, the LifeOS memory system — the typed Knowledge Archive (People, Companies, Ideas, Research with typed related: links) plus recall of prior work sessions, ISAs, and conversations. Search, add, harvest, develop, ingest, distill, graph-navigate, recall. USE WHEN cortex, knowledge, knowledge base, search…
feishu
Work with Feishu or Lark bots, docs, sheets, bitables, approval flows, and OpenAPI/MCP setup without hardcoding credentials.
pinchtab-mcp
Use this skill when a task requires browser automation through PinchTab's MCP server connected to a remote browser instance. Covers navigation, element interaction, data extraction, form filling, multi-step flows, and session management via MCP tools.
peekaboo
Capture and automate macOS UI with the Peekaboo CLI.
mochi-remind
Handle due reminders — notify the user with natural language and mark them done.