A tool for collecting selected knowledge notes so they can be moved to another learning-loop setup you own. It removes content that matches a configured list of private or restricted information.

Use it to create a reviewed bundle of portable insights, then import that bundle elsewhere.

Moving notes between setups can accidentally expose private information. This limits the export to notes explicitly marked as portable and lets you review what remains.

harvest — Skill for Claude Code and Codex by robinslange: A tool for collecting selected knowledge notes so they…

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/robinslange/learning-loop/harvest

Any agent

npx skills add robinslange/learning-loop --skill harvest

Clone the repo

git clone --depth 1 https://github.com/robinslange/learning-loop

Made for: Claude Code, Codex.

Or install learning-loop, the plugin that ships this one along with the rest of its 24 skills, 20 agents, 6 hooks.

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/robinslange/learning-loop/harvest.svg)](https://agentmods.dev/skills/robinslange/learning-loop/harvest)

Your own site

<a href="https://agentmods.dev/skills/robinslange/learning-loop/harvest"><img src="https://agentmods.dev/badge/skills/robinslange/learning-loop/harvest.svg" alt="Measured on agentmods" height="20"></a>

Per session 86 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,355 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.

Model	Per session	Once invoked
Fable 5	$0.00086	$0.01355
Opus 5	$0.00043	$0.00678
Sonnet 5	$0.00017	$0.00271
Haiku 4.5	$0.00009	$0.00136

Measured 3d ago against content hash 3bf7f2e2eb67, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

harvest 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 3d 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.

plugin/skills/harvest/SKILL.md · 69 lines

How it starts

The opening of the file, as written. The whole thing — 69 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Harvest portable insights

Collects notes/memories marked portable: true, scrubs them against this instance's IP deny-list, lets you review survivors, and emits a harvest-bundle-<date>/ to carry home and absorb with /learning-loop:ingest bundle <path>.

Invariants (do not violate)

Whitelist only: only portable: true. Never harvest by visibility, tag, or inference. The gate matches the exact literal lowercase true — portable: True, yes, or 1 are silently excluded (fail-closed, no leak), so if an operator expected a note to carry and it didn't, check the marker is exactly portable: true.
Mechanical gate: the deny-list block is authoritative. You may drop MORE in review; you may never un-block or add a note the gate excluded.

Paths

Resolve PLUGIN_DATA, VAULT, and the plugin root per ${CLAUDE_PLUGIN_ROOT}/skills-shared/paths-preamble.md (read it and apply). The deny-list file and dedup log are resolved mechanically, NOT hardcoded:

deny-list: node -e "import('${CLAUDE_PLUGIN_ROOT}/scripts/lib/paths.mjs').then(m=>console.log(m.DATA_FILES.harvestDenylist(process.argv[1])))" PLUGIN_DATA
dedup log: same with DATA_FILES.harvestedLog. The memory dir: node -e "import('${CLAUDE_PLUGIN_ROOT}/scripts/lib/memory-paths.mjs').then(m=>console.log(m.resolveMemoryDir(process.env.CLAUDE_PROJECT_DIR)))".

Process

1. Collect (mechanical whitelist)

Pass DIRECTORIES — the script walks them; do not enumerate files yourself:

node ${CLAUDE_PLUGIN_ROOT}/scripts/harvest-collect.mjs "<VAULT>" "<memDir>"

prints the paths with portable: true. These are the ONLY candidates. Capture them to a temp file for the next steps.

2. Dedup

node ${CLAUDE_PLUGIN_ROOT}/scripts/harvest-dedup.mjs "<dedupLog>" [--all] < candidates.txt

(CLI reads candidate paths on stdin, one per line; --all ignores the log.) Use the printed filtered list going forward.

3. Federation guard (mechanical, warn-not-block)

node ${CLAUDE_PLUGIN_ROOT}/scripts/federation-active.mjs "<PLUGIN_DATA>"

If it prints FEDERATED, show this before review: "⚠ this instance is federated — confirm each note is yours to carry, not company IP." Friction, not a block.

Read the full file on GitHub · 69 lines

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.

3d ago First seen · 69 lines · 86 tokens per session scan A 3bf7f2e2eb67

Subscribe to this mod's changes

harvest is a skill published in the GitHub repository robinslange/learning-loop (11 stars, last pushed 12d ago), licensed Apache-2.0. It adds 86 tokens to every session and 1,355 once invoked, about $0.0004 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.

Memory and context

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

brainstorming

You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.

obra/superpowers · 37 tokens

auto-perf-optimize

Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.

microsoft/vscode · 62 tokens

chat-perf

Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.

microsoft/vscode · 51 tokens

chat-pet-sprite-creation

Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.

microsoft/vscode · 53 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens