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 skills add synthesisengineering/synthesis-skills --skill synthesis-catchup-ledgergit clone --depth 1 https://github.com/synthesisengineering/synthesis-skillsWrote 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/synthesisengineering/synthesis-skills/synthesis-catchup-ledger)<a href="https://agentmods.dev/skills/synthesisengineering/synthesis-skills/synthesis-catchup-ledger"><img src="https://agentmods.dev/badge/skills/synthesisengineering/synthesis-skills/synthesis-catchup-ledger/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/synthesisengineering/synthesis-skills/synthesis-catchup-ledger"><img src="https://agentmods.dev/badge/skills/synthesisengineering/synthesis-skills/synthesis-catchup-ledger.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00116 | $0.02580 |
| Opus 5 | $0.00058 | $0.01290 |
| Sonnet 5 | $0.00023 | $0.00516 |
| Haiku 4.5 | $0.00012 | $0.00258 |
Grade A, and why
synthesis-catchup-ledger 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 12d 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 — 153 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Synthesis Catch-up Ledger
Version 0.3.0 (2026-08-14)
Consumer note (v0.2.0): synthesis-console v0.14+ renders ledgers live at
/ledger— it classifies H2 sections by the heading keywords used in this skill's output sections ("Do now", "Verify before re-adding", "Done late", "Expired", "Released") and reads per-row state from aStatetable column when present. Ledger files live at<knowledge-root>/catchup-ledgers/YYYY-MM-DD.md. If this skill's section vocabulary or table shapes change, update the console'ssrc/parsers/ledger.ts+docs/cockpit-design.mdin the same session — producer and consumer must change together.
The problem
Falling behind is part of life. Travel, family visits, illness, and crunch weeks interrupt the daily-ritual cadence, and the interruption itself is never the failure. The failure mode is silent: commitments made before the gap decay invisibly, because every existing artifact is scoped to a unit of time that assumes continuity. Daily plans capture one day's intent. Weekly loose-ends reviews (synthesis-daily-rituals v2.8.0) assume Fridays happen. Project CONTEXT files capture project state, not personal commitments. When the cadence breaks, nothing reconciles what was promised against what happened.
The result, observed repeatedly in practice: items survive as anxiety rather than as records. The person knows they're behind but not on what, so the backlog feels larger than it is, and genuinely-expired items consume attention that live items need.
What this skill produces
A catch-up ledger: one dated markdown document that reconciles an arbitrary look-back window (2 weeks, 6 weeks, a quarter) into classified, routed, honest state. The ledger is the accounting close for a period of interrupted attention. After reading it, the person knows: what still needs doing (prioritized), what got done late (credit recorded), what died (with the lesson extracted), and what was never theirs to carry (released).
What ships with it
2 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.
- 12d ago First seen · 153 lines · 116 tokens per session scan A 4bd4e09b627b
synthesis-catchup-ledger is a skill published in the GitHub repository synthesisengineering/synthesis-skills (19 stars, last pushed today), licensed Apache-2.0. It adds 116 tokens to every session and 2,580 once invoked, about $0.0006 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
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…
agentmail
Use your assigned AgentMail inbox to read email tasks, explicitly send or reply, and check delivery. Provided automatically by your inbox assignment.
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…
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.
feishu
Work with Feishu or Lark bots, docs, sheets, bitables, approval flows, and OpenAPI/MCP setup without hardcoding credentials.
peekaboo
Capture and automate macOS UI with the Peekaboo CLI.