resupply

resupply is a skill for Claude Code, Codex from Eigenwise/eigenwise-toolshed. It costs 222 tokens per session (3,954 once invoked), scanned A, original, MIT.

A workspace review that looks for one missing capability, measurement, piece of reusable knowledge, or setup improvement. It reads recent session summaries to understand what the user has been trying to accomplish, then proposes one item at a time for approval.

In plain words
What is it for?
Use it to identify a missing workspace tool, automation, measurement, or reusable knowledge that would make ongoing work easier.
Why use it?
It helps find useful improvements that repeated mistakes or errors may not reveal, while keeping the review bounded and requiring approval before obtaining anything.

Skill for Claude CodeCodex

Installs and runs on its own, but its text points at files inside its plugin — anything it tells you to read at a ${CLAUDE_PLUGIN_ROOT} path is only there once the plugin is installed. Installing the plugin gets both.

Part of the quartermaster plugin — 4 skills shipped together

Install

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.

agentmods
npx agentmods add skills/eigenwise/eigenwise-toolshed/resupply
Any agent
npx skills add Eigenwise/eigenwise-toolshed --skill resupply
Clone the repo
git clone --depth 1 https://github.com/Eigenwise/eigenwise-toolshed

Made for: Claude Code, Codex.

Or install quartermaster, the plugin that ships this one along with the rest of its 4 skills.

Wrote 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.

agentmods badge for resupply

README.md
[![agentmods](https://agentmods.dev/badge/skills/eigenwise/eigenwise-toolshed/resupply.svg)](https://agentmods.dev/skills/eigenwise/eigenwise-toolshed/resupply)
Your own site
<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>
Per session 222 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,954 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce 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

Measured 5d ago against content hash 67a392b477a0, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

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.

plugins/quartermaster/skills/resupply/SKILL.md · 301 lines

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.

Read the full file on GitHub · 301 lines

Files

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.

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.

  1. 5d ago First seen · 301 lines · 222 tokens per session scan A 67a392b477a0

Subscribe to this mod's changes

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.