agentmods.dev

federation

federation is a skill for Claude Code from robinslange/learning-loop. It costs 58 tokens per session (4,289 once invoked), scanned A, original, Apache-2.0.

A setup tool for sharing knowledge notes between learning-loop users through a private network and an exchange service.

In plain words
What is it for?
Use it to join or repair a shared knowledge network, create or rotate an identity, set sharing rules, or test synchronization.
Why use it?
Sharing across separate setups requires identity keys, invitations, network access, visibility rules, and a working sync test. This guides those steps and avoids saving incomplete settings.

Skill for Claude Code

Written for Claude Code: ${CLAUDE_PLUGIN_ROOT} variable.

Runs only inside its plugin — its command needs a path that Claude Code sets for a plugin’s own hooks and for nothing else. Install the plugin, not this.

Part of the learning-loop plugin — 24 skills, 20 agents, 7 hooks shipped together

not rated 13repo changed 1mo ago A scan 58 tokens original Apache-2.0

Good fit Use it to join or repair a shared knowledge network, create or rotate an identity, set sharing rules, or test synchronization.

Compare 6 skills from other repositories ↓
View source ↗ robinslange/learning-loop
Install

Getting it into your agent

This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.

Claude Code
/plugin marketplace add robinslange/learning-loop
Claude Code
/plugin install learning-loop

Made for: Claude Code.

Or install learning-loop, the plugin that ships this one along with the rest of its 24 skills, 20 agents, 7 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.

agentmods badge for federation

README.md
[![agentmods](https://agentmods.dev/badge/skills/robinslange/learning-loop/federation/github.svg)](https://agentmods.dev/skills/robinslange/learning-loop/federation)
Your own site
<a href="https://agentmods.dev/skills/robinslange/learning-loop/federation"><img src="https://agentmods.dev/badge/skills/robinslange/learning-loop/federation/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.

agentmods 80×15 button for federation

Your own site · 80×15
<a href="https://agentmods.dev/skills/robinslange/learning-loop/federation"><img src="https://agentmods.dev/badge/skills/robinslange/learning-loop/federation.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 58 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 4,289 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00058 $0.04289
Opus 5.5 $0.00023 $0.01716
Sonnet 5.5 $0.00012 $0.00858
Haiku 4.5 $0.00006 $0.00429

Measured 1mo ago against content hash 83d3913082a3, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

federation 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 1mo 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/federation/SKILL.md · 408 lines

How it starts

The opening of the file, as written. The whole thing — 408 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Federation Setup

Federation is three nouns. A key is a principal — a person or a machine. The key is the identifier: there is no registry and no name to allocate. A vault is a corpus with an owning key and a visibility policy; one key may own several. A grant is a signed statement by one key about another — follow (read a vault), link (these machines are the same person), assoc (these identities are the same human, no authority), peer (two hubs bridge).

A hub decides who may connect. It never decides trust between keys: every grant is signed by the key that made it and verifies offline against nothing but the bytes and that key's public half.

This skill is invoked from /init Phase 4 when the user opts in, and is safe to run standalone.

Paths

Resolve PLUGIN_DATA, VAULT, and the plugin root per ${CLAUDE_PLUGIN_ROOT}/skills-shared/paths-preamble.md (read it and apply).

ll-search writes everything federation owns under a config dir. For a single-vault install that is PLUGIN_DATA itself, and --config-dir $PLUGIN_DATA is what every command below passes. For a multi-vault install each vault has its own config dir under PLUGIN_DATA, listed by ll-search vault list.

ll-search sync also takes the search index as its first positional. That is VAULT/.vault-search/vault-index.db — the file the watch daemon writes, not anything under the config dir. Pass it in full; a path that does not exist ends the command in a panic rather than a message.

Process

Detect first, then walk the steps in order. Nothing writes config.json until the hub has proved its identity and admitted this key, so a run that dies part-way leaves a directory the next run enters cleanly.

A: Detect

  • If PLUGIN_DATA/vaults.json exists, this is a multi-vault install. Run ll-search vault list and ask which vault this run is about; use that profile's config dir for everything below.
  • Otherwise read PLUGIN_DATA/federation/config.json.

Read the full file on GitHub · 408 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.

  1. 1mo ago Changed · +13 lines 83d3913082a3
  2. 1mo ago Changed · +46 lines 64460b71a58c
  3. 2mo ago Changed · +145 lines · +2 tokens per session scan B → A 0930259c58ce
  4. 2mo ago First seen · 204 lines · 56 tokens per session scan B cbd041ffba52

Subscribe to this mod's changes

federation is a skill published in the GitHub repository robinslange/learning-loop (13 stars, last pushed 4d ago), licensed Apache-2.0. It adds 58 tokens to every session and 4,289 once invoked, about $0.0002 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.

Memory and context
Related

federation compared with skills from other repositories

federation next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
federationrobinslange/learning-loopSkill134d agoApache-2.0A58Claude Code
knowledge-ingestopenclaw/openclawSkill394kyesterdayMITA80Claude Code, Codex
mem0-oss-to-platformmem0ai/mem0Skill68k2d agoApache-2.0A217Claude Code, Codex
forgetasgeirtj/system_prompts_leaksSkill71k2d agoCC0-1.0A74Claude Code, Codex
Cortexdanielmiessler/LifeOSSkill20kyesterdayMITA184Claude Code
memoryopensquilla/opensquillaSkill7.1k6d agoApache-2.0A44Claude Code, Codex
ha-data-storesshiwenwen/hope-agentSkill1.9kyesterdayMITA115Claude Code, Codex