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/period-summarynpx skills add mpazik/Binder --skill period-summarygit clone --depth 1 https://github.com/mpazik/BinderWrote 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/mpazik/binder/period-summary)<a href="https://agentmods.dev/skills/mpazik/binder/period-summary"><img src="https://agentmods.dev/badge/skills/mpazik/binder/period-summary.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 | $0.00024 | $0.01715 |
| Opus 5 | $0.00012 | $0.00857 |
| Sonnet 5 | $0.00005 | $0.00343 |
| Haiku 4.5 | $0.00002 | $0.00171 |
Grade A, and why
period-summary 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 — 138 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Summarize the target period.
Context
Offset controls direction: default (0) = current period, negative = past period (e.g. -1 for previous). Use actual period dates from entries below — do NOT assume "current."
Assume the most common case: the last child may still be open. Treat this as normal. The period summary is still final.
Target period with children (created if missing): !G=$0; O=$1; binder read $(bun scripts/journal.ts ${G:-w} ${O:-0} --key) -f "goal,plan,achievements,events,learnings,summary,totalScore,parent(key,goal,plan,achievements,events,learnings),children(key,goal,plan,achievements,events,learnings,summary,moodScore,sleepScore,foodScore,workScore,fitnessScore,totalScore,log)" --format yaml
Previous period: !G=$0; O=$1; binder read $(bun scripts/journal.ts ${G:-w} $(( ${O:-0} - 1 )) --key) -f "goal,plan,achievements,events,learnings,summary,totalScore,moodScore,sleepScore,foodScore,workScore,fitnessScore" --format yaml
Next period's key: !G=$0; O=$1; bun scripts/journal.ts ${G:-w} $(( ${O:-0} + 1 )) --key
Deliver one message (shallow → deep)
1. Metrics overview
Aggregate data from children:
For weeks (children are days):
- Average scores across the week (mood, sleep, food, work, fitness) + trend arrows (↑↓→) vs previous period
- Days with gym, no-YT streaks, etc.
- Total hours wasted (if tracked)
- Completion rate (achievements vs plan items across all days)
For months+ (children are larger periods):
- Goal completion across children
- Key wins and recurring blockers
- Score trends if available
Present as a compact block:
Scores avg: Mood 6.2, Work 5.8↓, Fitness 7.5↑ Achieved: 22 of 35 plan items across the period Streaks: Gym 4 of 7 days Top achievements: Shipped frontmatter parser, new OHP PR Notable events: NZ trip (unplanned), Valentine's Day, urgent planning meeting on Wed
2. Goal review
Compare the period's goal against what actually happened (from children summaries):
- Which goals saw real progress? State concretely what was done.
- Which goals stalled? Name them without judgment.
- Any unexpected wins or directions?
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 · 138 lines · 24 tokens per session scan A 626b33ac43cc
period-summary is a skill published in the GitHub repository mpazik/Binder (40 stars, last pushed 13d ago), licensed MIT. It adds 24 tokens to every session and 1,715 once invoked, about $0.0001 per session on Opus 5. 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 2026-08-30.
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.
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…
update-changelog
Update Starcat changelog documents in supports/starcat-pro/ by reading ALL git commits from the main Starcat project and generating categorized release notes in both English and Chinese. Use this skill whenever the user wants to update changelog, release notes, update records, or sync the changelog with recent…
pages
List or open distilled Wenlan pages from Codex by delegating to the local wenlan pages CLI. Invoked as /pages [query].
anyr
Use when reading, searching, creating, or updating Anytype documents (objects, spaces, types, properties, files, chats) from the command line with the configured anyr CLI, including JSON output patterns for scripting.