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/robinslange/learning-loop/federationnpx skills add robinslange/learning-loop --skill federationgit clone --depth 1 https://github.com/robinslange/learning-loopWhat 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 | $0.00056 | $0.02670 |
| Opus 5 | $0.00028 | $0.01335 |
| Sonnet 5 | $0.00011 | $0.00534 |
| Haiku 4.5 | $0.00006 | $0.00267 |
Grade B, and why
federation scanned grade B with 3 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 2d 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.
Sends data to an external URLmediumData exfiltration
A POST to an outside endpoint may be telemetry or may be exfiltration; either way the mod talks to somewhere, and you should know where.
const res = await fetch('https://interchange.live/api/redeem', { method: 'POST', Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
Check for Tailscale. If not installed, guide installation (brew for macOS, curl for Linux). Run: Runs shell commandslowCapability
Expected in a hook, worth knowing in a rule or an instructions file.
const { spawn } = await import('node:child_process'); How it starts
The opening of the file, as written. The whole thing — 204 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Federation Setup
Federation lets you share vault notes with other learning-loop users via interchange.live. The setup is non-trivial because it spans cryptography (Ed25519 keypair), single-use redemption tokens, an overlay network (Tailscale via headscale), and a hub round-trip that must succeed before any config is written.
This skill is invoked from /init Phase 4 when the user opts in, but is safe to run standalone any time you have a token from robin.
Paths
Resolve PLUGIN_DATA, VAULT, and the plugin root per ${CLAUDE_PLUGIN_ROOT}/skills-shared/paths-preamble.md (read it and apply).
Process
Detect, then walk the steps in order. Do not write the federation config until the sync test in step F succeeds: failed runs leave nothing on disk so re-running starts fresh.
A: Detect
If PLUGIN_DATA/federation/config.json already exists, report identity and peer count, and ask: "Federation is already configured. Re-run setup anyway?" Default no. If the user says no, exit cleanly.
B: Token
Ask: "Do you have an invite token?"
If no:
You'll need an invitation to join the federation. Apply at:
https://interchange.live/apply
Once your application is approved, you'll receive a redeem URL.
Re-run /learning-loop:federation when you have it.
Exit cleanly.
If yes: proceed to identity setup.
C: Identity
The identity is an Ed25519 seed managed by the ll-search binary's seed store. Backends in priority order: the OS keyring (macOS Keychain / Linux Secret Service / Windows Credential Manager), then an encrypted-at-rest file under PLUGIN_DATA/federation/ (machine-derived key, used where no keyring daemon runs). A plaintext PLUGIN_DATA/federation/.seed file is a pre-v1.18 legacy format: still readable as a migration source, never created by the binary. On a fresh install no .seed file will exist — that is normal, not an error.
Plugin-root migration check (before running identity): if a legacy plaintext seed exists at ${CLAUDE_PLUGIN_ROOT}/federation/.seed (very old installs; that location gets wiped on reinstall):
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.
- 2d ago First seen · 204 lines · 56 tokens per session scan B cbd041ffba52
federation is a skill published in the GitHub repository robinslange/learning-loop (11 stars, last pushed 10d ago), licensed Apache-2.0. It adds 56 tokens to every session and 2,670 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it B with 3 findings (sends data to an external url, makes network calls, runs shell commands). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
babysit-pr
Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…
imagegen
Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…
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…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…