compendium-curate

compendium-curate is a skill for Claude Code from SoliEstre/EstreGenesis. It costs 187 tokens per session (1,504 once invoked), scanned A, original, Apache-2.0.

A system for coordinating several software agents through live messages, shared rooms, and a dashboard. It also keeps room decisions, summaries, and task-board state available to participants.

In plain words
What is it for?
Use it to run multi-agent work, exchange messages, preserve room records, manage staged tasks, and monitor collaboration from a dashboard.
Why use it?
It gives multiple agents a shared place to communicate and track decisions instead of relying on separate conversations. It helps prevent duplicate messages and lost or incomplete transfers.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the compendium plugin — 2 skills shipped together

Good fit Use it to run multi-agent work, exchange messages, preserve room records, manage staged tasks, and monitor collaboration from a dashboard.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/soliestre/estregenesis/compendium-curate
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.

Any agent
npx skills add SoliEstre/EstreGenesis --skill compendium-curate
Clone the repo
git clone --depth 1 https://github.com/SoliEstre/EstreGenesis

Made for: Claude Code.

Or install compendium, the plugin that ships this one along with the rest of its 2 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 compendium-curate

README.md
[![agentmods](https://agentmods.dev/badge/skills/soliestre/estregenesis/compendium-curate/github.svg)](https://agentmods.dev/skills/soliestre/estregenesis/compendium-curate)
Your own site
<a href="https://agentmods.dev/skills/soliestre/estregenesis/compendium-curate"><img src="https://agentmods.dev/badge/skills/soliestre/estregenesis/compendium-curate/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 compendium-curate

Your own site · 80×15
<a href="https://agentmods.dev/skills/soliestre/estregenesis/compendium-curate"><img src="https://agentmods.dev/badge/skills/soliestre/estregenesis/compendium-curate.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 187 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,504 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. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
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 $0.00187 $0.01504
Opus 5 $0.00093 $0.00752
Sonnet 5 $0.00037 $0.00301
Haiku 4.5 $0.00019 $0.00150

Measured 10d ago against content hash 8d1ade8da2e3, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

compendium-curate 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 10d 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/compendium/skills/compendium-curate/SKILL.md · 77 lines

How it starts

The opening of the file, as written. The whole thing — 77 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Compendium Curate — the pointer-not-paraphrase vocabulary discipline

You are about to record vocabulary. A generic note/vault tool will happily let you paraphrase a definition that already lives somewhere authoritative — and that copy will rot the moment the source changes. This skill is the opinion that a generic vault does not have. The store is plain markdown+frontmatter (any viewer reads it); what you are applying is the discipline.

The one rule (the wedge): pointer-not-paraphrase

An internal-register entry — a term whose authoritative definition is owned by some spec/doc — carries a one-line orientation gloss + a pointer to the owner, and never restates the owner's normative content. Restating creates a second source of truth that drifts. Compendium is a source of information, not a source of truth: authority is one-directional, entry → owner_spec.

If you find yourself copying an algorithm, a schema, a score formula, a numbered rule, a payload shape, or a version number — stop. Write a one-line gloss and a pointer instead.

The sole exception: general-register vocabulary that no spec owns (owner_spec: null). For that alone the entry IS the full-definition SSoT (nothing competes, zero conflict).

Dual register — one concept, two glosses

Every entry anchors one concept and carries two glosses so a reader at either altitude is served:

  • expert gloss — dense, jargon-OK, for someone who knows the neighborhood.
  • plain gloss — jargon unpacked, for someone meeting the term cold.

The two glosses describe the same concept; they are not two definitions. (This is the L2.2.2 dual-register convention.)

The frontmatter schema (the governance SSoT)

The frontmatter — not the prose — is the source of truth a tool reads. Minimum shape:

---
id: <kebab-case, == filename>          # immutable; the wikilink target
title: <Human Title>
type: glossary | concept | index
register_class: internal | general     # internal → owner_spec required; general → owner_spec null
owner_spec: <File.md#heading-slug> | null   # the authority pointer (one-directional, may point OUT of the store)
status: active | superseded
superseded_by: <id> | null
aliases: [<other surface forms>]
definition:
  text: "<one register-neutral sentence; ends in 'See owner_spec.' for internal>"
glosses:
  - { register: expert, text: "<dense one-liner>" }
  - { register: plain,  text: "<unpacked one-liner>" }
links: [<peer-ids>]                     # peer relations (term↔term); NOT the authority pointer
audit: { created: <YYYY-MM-DD>, updated: <YYYY-MM-DD> }
---
<body: a thin orientation primer that ENDS in the pointer — never a restatement.>

Read the full file on GitHub · 77 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. 10d ago First seen · 77 lines · 187 tokens per session scan A 8d1ade8da2e3

Subscribe to this mod's changes

compendium-curate is a skill published in the GitHub repository SoliEstre/EstreGenesis (8 stars, last pushed 4d ago), licensed Apache-2.0. It adds 187 tokens to every session and 1,504 once invoked, about $0.0009 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 2026-08-31.

Related

Other skills, from other repositories

update-agent-context

This skill should be used to keep CLAUDE.md, AGENTS.md, and the skill files themselves compact, current, and internally consistent. It runs in three phases: Phase 1 performs a one-time structural refactor of CLAUDE.md using a Karpathy-inspired behavioral scaffold and derives AGENTS.md from it by stripping Claude…

mostlyharmless-ai/watercooler · 203 tokens

watercooler-onboarding

Bootstrap Watercooler memory for a repository by inspecting local code, docs, CI, git history, and existing Watercooler threads, then writing a small set of durable, provenance-backed seed threads that future agents can query and extend. Use when entering a repo for the first time, seeding a repo with Watercooler…

mostlyharmless-ai/watercooler · 79 tokens

recall

Recall project context or answer questions about history and decisions. Use before starting work, when investigating unfamiliar code, or asking "What was decided about X?" / "Why did we choose Y?".

mostlyharmless-ai/watercooler · 41 tokens

wiki

Use this skill when querying workspace knowledge before tasks or running mandatory post-review ingest evaluation and conditional wiki ingestion. Self-learning loop for the workspace.

wcgomes/agents-workspace · 30 tokens

agent-v3-memory-specialist

Agent skill for v3-memory-specialist - invoke with $agent-v3-memory-specialist.

ruvnet/ruflo · 25 tokens

agent-memory-coordinator

Agent skill for memory-coordinator - invoke with $agent-memory-coordinator.

ruvnet/ruflo · 19 tokens