Borrowing it
Nothing to install: this file belongs to nacre-work/nacre. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/nacre-work/nacre/main/.claude/skills/open-core-boundary/SKILL.mdgit clone --depth 1 https://github.com/nacre-work/nacreWrote 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/nacre-work/nacre/open-core-boundary)<a href="https://agentmods.dev/skills/nacre-work/nacre/open-core-boundary"><img src="https://agentmods.dev/badge/skills/nacre-work/nacre/open-core-boundary/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/nacre-work/nacre/open-core-boundary"><img src="https://agentmods.dev/badge/skills/nacre-work/nacre/open-core-boundary.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00107 | $0.01069 |
| Opus 5.5 | $0.00043 | $0.00428 |
| Sonnet 5.5 | $0.00021 | $0.00214 |
| Haiku 4.5 | $0.00011 | $0.00107 |
Grade A, and why
open-core-boundary 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 17d 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 — 95 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Where does this code go?
docs/licensing.md has the full split. The decision reduces to one question.
The question
Does a security team pay for it, or a developer?
If a single developer on a laptop needs it, it belongs here, in the Apache 2.0
core. If it exists because a regulated buyer's security or compliance function
requires it, it belongs in nacre-enterprise.
Blurring the line devalues both halves: the core stops being usable on its own, and the commercial half stops being worth buying.
Core, Apache 2.0
Data model · ingest · chunking · embeddings · hybrid search · reranking · the MCP server · the REST API · basic RBAC · a single organization · email and password authentication · Docker Compose · the Helm chart.
Commercial, separate repository
Nine modules: tenancy (suspension, offboarding, quotas) · sso (OIDC sign-in
per organization and SCIM group-membership sync; not SAML, which goes through a
broker) · acl-advanced (issuing document-level grants and deny rules) · ema
(EMA and ID-JAG) · audit (SIEM forwarding) · admin-global (creating
organizations, the default embedding model, platform administrators) · backup
(one encrypted artifact for the whole installation, and restoring it) ·
sign-in-policy (an organization requiring a second factor) · directory
(filtered administration for installations too large to page through).
What sits beside those and is core: one vector collection per organization,
evaluating document grants and deny rules (resolve and buildFilter), and
the access log with GET /v1/audit and its JSONL/CSV export. The airgapped
Compose profile is core too.
The mechanical rule
The core must not know the private repository exists. The boundary job in
CI fails the build if anything under packages/ or services/ references
@nacre.work/enterprise. The reverse direction is fine — over there,
@nacre.work/core is an ordinary dependency.
That job is the only automated part of this. Everything above it is judgement, which is why it is worth stating in the PR rather than assuming.
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.
- 17d ago Changed · +18 lines 29ef9ec82599
- 1mo ago First seen · 77 lines · 107 tokens per session scan A 79884d73aff7
open-core-boundary is a skill published in the GitHub repository nacre-work/nacre (2 stars, last pushed 18d ago), licensed Apache-2.0. It adds 107 tokens to every session and 1,069 once invoked, about $0.0004 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 2026-08-31.
Other skills, from other repositories
chroma
Open-source embedding database for AI applications. Store embeddings and metadata, perform vector and full-text search, filter by metadata. Simple 4-function API. Scales from notebooks to production clusters. Use for semantic search, RAG applications, or document retrieval. Best for local development and open-source…
chroma
Open-source embedding database for AI applications. Store embeddings and metadata, perform vector and full-text search, filter by metadata. Simple 4-function API. Scales from notebooks to production clusters. Use for semantic search, RAG applications, or document retrieval. Best for local development and open-source…
chroma
Open-source embedding database for AI applications. Store embeddings and metadata, perform vector and full-text search, filter by metadata. Simple 4-function API. Scales from notebooks to production clusters. Use for semantic search, RAG applications, or document retrieval. Best for local development and open-source…
chroma
Open-source embedding database for AI applications. Store embeddings and metadata, perform vector and full-text search, filter by metadata. Simple 4-function API. Scales from notebooks to production clusters. Use for semantic search, RAG applications, or document retrieval. Best for local development and open-source…
chroma
Open-source embedding database for AI applications. Store embeddings and metadata, perform vector and full-text search, filter by metadata. Simple 4-function API. Scales from notebooks to production clusters. Use for semantic search, RAG applications, or document retrieval. Best for local development and open-source…
chroma
Open-source embedding database for AI applications. Store embeddings and metadata, perform vector and full-text search, filter by metadata. Simple 4-function API. Scales from notebooks to production clusters. Use for semantic search, RAG applications, or document retrieval. Best for local development and open-source…