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 skills add SoliEstre/EstreGenesis --skill compendium-curategit clone --depth 1 https://github.com/SoliEstre/EstreGenesisWrote 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.
[](https://agentmods.dev/skills/soliestre/estregenesis/compendium-curate)<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.
<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>- NVIDIA SkillSpector pass
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 5.1 | $0.00187 | $0.01504 |
| Opus 5 | $0.00093 | $0.00752 |
| Sonnet 5 | $0.00037 | $0.00301 |
| Haiku 4.5 | $0.00019 | $0.00150 |
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.
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.>
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.
- 10d ago First seen · 77 lines · 187 tokens per session scan A 8d1ade8da2e3
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.
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…
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…
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?".
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.
agent-v3-memory-specialist
Agent skill for v3-memory-specialist - invoke with $agent-v3-memory-specialist.
agent-memory-coordinator
Agent skill for memory-coordinator - invoke with $agent-memory-coordinator.