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 jesseposner/metacraft --skill gathergit clone --depth 1 https://github.com/jesseposner/metacraftWrote 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/jesseposner/metacraft/gather)<a href="https://agentmods.dev/skills/jesseposner/metacraft/gather"><img src="https://agentmods.dev/badge/skills/jesseposner/metacraft/gather/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/jesseposner/metacraft/gather"><img src="https://agentmods.dev/badge/skills/jesseposner/metacraft/gather.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00020 | $0.00423 |
| Opus 5.5 | $0.00008 | $0.00169 |
| Sonnet 5.5 | $0.00004 | $0.00085 |
| Haiku 4.5 | $0.00002 | $0.00042 |
Grade A, and why
gather 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 2mo 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.
What it actually says
Gather
Pause and reset. Gather what's scattered, commit what's ready, and prepare for what's next.
What this is
A mid-session meditation. Pause the forward motion, collect everything that's scattered, and lay a clean foundation for the next push. This isn't closing. It's composting.
When to use it
- When a session has accumulated uncaptured decisions, insights, or state changes
- Before a context switch or handoff
- When momentum has outrun bookkeeping
- When you feel the itch to start something new but the ground isn't clean
The pattern
-
Mine the conversation. Review the session so far for uncaptured items: decisions made but not recorded, insights worth preserving, things said that should be written down. Surface anything found before filing it.
-
Tend the memory. Check if any stable patterns, corrections, or lessons emerged that belong in project memory or persistent files. Update as needed.
-
Update project notes. If the project has a journal, changelog, or session log, ensure it covers what happened. Name the arc if there is one. Note what's still open.
-
Persist the work. Stage changes, write a clear commit message, sync with the remote if appropriate. The goal is a clean, resumable state.
-
Report. Confirm what was captured, what was persisted, and what the ground looks like now. Brief, not exhaustive. The audience is the next session, not a stakeholder.
Anti-patterns
- Manufacturing ceremony. If the session has been light, keep it proportional. Don't invent work to justify the pause.
- Leaving things unnamed. If something feels unfinished but can't be resolved now, name it explicitly. Unfinished is fine. Untracked is not.
- Treating this as a status report. The goal is to leave nothing behind that matters and nothing in the way that doesn't.
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.
- 2mo ago First seen · 38 lines · 20 tokens per session scan A d590e97e693b
gather is a skill published in the GitHub repository jesseposner/metacraft (11 stars, last pushed 8mo ago), licensed Apache-2.0. It adds 20 tokens to every session and 423 once invoked, about $0.0001 per session on Opus 5.5. 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
LifeOS memory, prior-session recall, and learning capture. USE WHEN capture this learning, document this learning, what did we learn recently, recent learnings, cortex, knowledge, knowledge base, search knowledge, what do we know about, archive, harvest, knowledge status, develop note, add to knowledge, add a people…
rowboat-spaces
How to work as a member of Rowboat Spaces, the team chat where people and agents work together. Load it once per session, before acting on any request that reaches you from Rowboat; it covers your setup, mentions and hand-offs, the tools, and files.
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.