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/eigenwise/eigenwise-toolshed/resupplynpx skills add Eigenwise/eigenwise-toolshed --skill resupplygit clone --depth 1 https://github.com/Eigenwise/eigenwise-toolshedWrote 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/eigenwise/eigenwise-toolshed/resupply)<a href="https://agentmods.dev/skills/eigenwise/eigenwise-toolshed/resupply"><img src="https://agentmods.dev/badge/skills/eigenwise/eigenwise-toolshed/resupply.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 | $0.00222 | $0.03954 |
| Opus 5 | $0.00111 | $0.01977 |
| Sonnet 5 | $0.00044 | $0.00791 |
| Haiku 4.5 | $0.00022 | $0.00395 |
Grade A, and why
resupply 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 — 301 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Quartermaster resupply
One question drives this skill: what is this workspace short of that would make the user's work easier? Then get that one thing, with their approval.
A local script does the mining and hands you a bounded aggregate. Never open raw transcripts yourself: they run to tens of megabytes, and the aggregate already carries what matters.
Why capability and not friction
The obvious way to do this is to hunt for what went wrong: denials, corrections, interrupts, commands retyped by hand. That is worth doing, and it is the last thing on the list here, because removing friction returns the user to par while adding capability moves par.
The improvements that matter most tend to leave no friction trace at all. When someone needs a measurement that does not exist yet, nothing errors, nothing gets denied, nobody gets corrected, and it happens exactly once, so every repetition threshold misses it. A pass that only counts pain is structurally blind to the most valuable thing it could find.
So lead with what the user was trying to do, and treat the friction counts as one input to that question rather than the question itself.
Process
If the user declines a SessionStart nudge or Stop-time offer before the round starts, record that whole-round decline, then stop. Run:
node "${CLAUDE_PLUGIN_ROOT}/bin/quartermaster.js" decline-resupply --project "${CLAUDE_PROJECT_DIR}"
It resets the evidence window, so another offer waits for new sessions or friction to accumulate.
1. Mine
node "${CLAUDE_PLUGIN_ROOT}/bin/quartermaster.js" mine --project "${CLAUDE_PROJECT_DIR}"
Default window is 30 days / 40 sessions. Add --all-projects only if the user asks for a global
pass (much slower). Everything below reads from this one output.
2. Read what the work was for
The aggregate tells you this directly, so do not open with an interview. Each entry in sessions
carries title (the session's own one-line summary), openingAsk (its first real prompt), goal
(an explicit /goal with whether it was ever met), and humanDriven. purpose.goals totals the
goals set and met, and purpose.areasTop shows which parts of the tree the work landed in.
What ships with it
1 file 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.
- 5d ago First seen · 301 lines · 222 tokens per session scan A 67a392b477a0
resupply is a skill published in the GitHub repository Eigenwise/eigenwise-toolshed (37 stars, last pushed yesterday), licensed MIT. It adds 222 tokens to every session and 3,954 once invoked, about $0.0011 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…
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.
mochi-remind
Handle due reminders — notify the user with natural language and mark them done.