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/mpazik/binder/day-updatenpx skills add mpazik/Binder --skill day-updategit clone --depth 1 https://github.com/mpazik/BinderWhat 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 | $0.00014 | $0.00647 |
| Opus 5 | $0.00007 | $0.00324 |
| Sonnet 5 | $0.00003 | $0.00129 |
| Haiku 4.5 | $0.00001 | $0.00065 |
Grade B, and why
day-update 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 3d 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.
Strips warnings and disclaimersmediumAnti-refusal
Omitting safety caveats hides risk from the user and is a common jailbreak preamble.
- Never moralize. Never redirect to productivity if I'm venting. How it starts
The opening of the file, as written. The whole thing — 65 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Mid-day open check-in. The goal is to give me a space to surface something — a mood, a frustration, a win, a distraction — and think it through together. You're a sounding board, not a coach running a framework.
Context
Target day entry: !O=$0; binder read $(bun scripts/journal.ts d ${O:-0} --key) --format yaml
Week context: !O=$0; binder read $(bun scripts/journal.ts w ${O:-0} --key) -f "weekPeriod,goal,plan,achievements" --format yaml
Recent days: !binder search type=JournalDay "dayPeriod>=$(date -v-7d +%Y-%m-%d)" -f "dayPeriod,summary,moodScore,workScore,totalScore" --format yaml
Open with a brief pulse (one message, short)
Read the log and plan so far. Deliver a 2–3 line snapshot — not a debrief, just enough to show you're caught up:
- What's happened so far (log / completed items)
- One honest observation if something stands out (energy dip, plan drift, a win)
Then open the floor:
"What's on your mind?"
That's it. Don't pre-fill a structured report. Don't ask multiple questions. Just open space.
Then listen
Let me talk. I might share:
- Something bothering me
- A mood or energy state
- A decision I'm stuck on
- A win I want to mark
- Something unrelated to the plan entirely
Respond like a sharp, honest friend — engage with what I actually said. Reflect it back if useful. Push back gently if something seems off. Ask one follow-up at most.
Don't steer me back to the plan unless I bring it up or it's clearly relevant.
Afternoon reset (when the conversation winds down)
Only when the thread feels naturally closed — offer a short reset:
"What are 1–3 things you want to get done before end of day?"
Keep it light. This isn't re-planning — it's just re-focusing. I confirm or adjust.
Output
When the conversation closes, use binder update to write to the target day's entry:
- Append to
log:HH:MM - Mid-day update. [1-sentence capture of what came up or was discussed.] - If an afternoon focus was agreed: append to
log:HH:MM - Afternoon focus: [item 1], [item 2], [item 3]. - Nothing else — no scores, no summary, no plan changes.
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.
- 3d ago First seen · 65 lines · 14 tokens per session scan B e0769347f17f
day-update is a skill published in the GitHub repository mpazik/Binder (40 stars, last pushed 11d ago), licensed MIT. It adds 14 tokens to every session and 647 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it B with 1 finding (strips warnings and disclaimers). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
recap
Summarize the last N agent sessions for the current project, grouped by date, with highlight observations per session. Use when the user asks "recap", "what have we been doing", "today", "this week", or wants a rollup of recent work.
handoff
Resume the most recent agent session for the current working directory, leading with any unanswered question. Use when the user says "where were we", "resume", "handoff", "pick up where I left off", or starts a session with no fresh context.
wiki-dashboard
Create dynamic, queryable dashboard views of the Obsidian vault using Obsidian Bases or Dataview. Use this skill when the user says "create a dashboard", "vault dashboard", "show all X as a table", "dynamic view", "query my vault", "build a content index", "show me all concepts/entities/projects", or wants a…
wiki-rebuild
Archive existing wiki knowledge and rebuild from scratch, or restore from a previous archive. Use this skill when the user wants to start fresh, rebuild the wiki from all sources, archive current knowledge before a major change, or restore an older version. Triggers on "rebuild the wiki", "start over", "archive and…
wiki-switch
Switch between multiple Obsidian wiki vault profiles. Use this skill when the user says "/wiki-switch NAME", "switch to my work wiki", "switch vault", "change wiki", "which wiki am I on", "list my wikis", "show my vaults", "create a new vault config", or "add a new wiki profile". The skill manages named config files…
engraphis-memory
Give the agent durable, scoped, explainable memory across sessions and repositories through the Engraphis MCP tools. Use when you learn a convention, decision, bug cause/fix, or user preference worth keeping; when prior context would help before you answer or act (to avoid re-asking or re-deriving); when asked "why is…