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/config-var/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/config-var)<a href="https://agentmods.dev/skills/nacre-work/nacre/config-var"><img src="https://agentmods.dev/badge/skills/nacre-work/nacre/config-var.svg" alt="Measured on agentmods" 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 | $0.00068 | $0.00976 |
| Opus 5 | $0.00034 | $0.00488 |
| Sonnet 5 | $0.00014 | $0.00195 |
| Haiku 4.5 | $0.00007 | $0.00098 |
Grade A, and why
config-var 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 7d 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 — 83 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Adding configuration
Contract: docs/config.md.
Rules
- Prefix
NACRE_. No exceptions, including in the parser sidecar. - Validate the whole configuration at startup and exit if anything required is missing or contradictory. Not on first use — at boot.
- No silent defaults for secrets or URLs. A default that quietly points at
localhost is how a production deployment talks to nothing and reports
success. Defaults are fine for tunables (
NACRE_ACL_CACHE_TTL=60); they are not fine for anything naming a host or carrying a credential. - Secrets are references into a secret store where the platform allows it —
NACRE_JWT_PRIVATE_KEY_REF=file:///run/secrets/…, not the key itself. Plaintext values are for the development profile and nowhere else.
Every new variable touches four places
- the implementation's startup validation
.env.example— development values only, never a real credentialdocs/config.md- the Compose profile, if a service reads it
A variable that exists in code but not in docs/config.md is invisible to the
person deploying this, which for a self-hosted product is the person who
matters most.
And the four have to agree, not merely all exist. lint:config checks
existence and that is not the same thing. NACRE_MCP_CANONICAL_URL was present
in all four and they contradicted each other: docker-compose.yml omitted it
from the mcp service with eleven lines explaining that its absence was the
fix, and .env.example seeded it — and env_file sits on the shared service
anchor, so the value reached the container anyway. Every deployment that started
from cp .env.example .env had the fix silently undone.
So before adding a line to .env.example, ask what happens when a service
deliberately does not set that variable. If the answer is "the seeded value
wins", the variable belongs commented out with the reason, and the reason
belongs in lint:compose rather than only in a comment — a comment does not
travel to the next file.
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.
- 7d ago First seen · 83 lines · 68 tokens per session scan A e1e516fcfb24
config-var is a skill published in the GitHub repository nacre-work/nacre (0 stars, last pushed 9d ago), licensed Apache-2.0. It adds 68 tokens to every session and 976 once invoked, about $0.0003 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
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…