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 agentmods add instructions/niclasolofsson/dbt-core-mcp/memorygit clone --depth 1 https://github.com/NiclasOlofsson/dbt-core-mcpWrote 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/instructions/niclasolofsson/dbt-core-mcp/memory)<a href="https://agentmods.dev/instructions/niclasolofsson/dbt-core-mcp/memory"><img src="https://agentmods.dev/badge/instructions/niclasolofsson/dbt-core-mcp/memory.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 | $0.00978 | $0.00978 |
| Opus 5 | $0.00489 | $0.00489 |
| Sonnet 5 | $0.00196 | $0.00196 |
| Haiku 4.5 | $0.00098 | $0.00098 |
Grade A, and why
dbt-core-mcp memory.instructions.md 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 5d 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 — 81 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Workspace AI Memory
This file contains workspace-specific information for AI conversations.
Universal Laws
-
dbt-core-mcp Pre-Commit Validation Protocol:
- STEP 1: Before staging/committing ANY code changes, run CI validation sequence in order:
- a)
uv run ruff check src tests - b)
uv run ruff format --check src tests - c)
uv run pyright src tests - d)
uv run pytest
- a)
- STEP 2: Verify ALL steps succeed with exit code 0
- STEP 3: If ANY step fails, fix issues and restart from STEP 1
- STEP 4: Restore
.vscode/mcp.jsonto original state (revert_RESTARTcounter changes)- Use
git restore .vscode/mcp.jsonOR manually revert counter - NEVER commit restart counter changes - testing only
- Use
- STEP 5: Only after all checks pass and cleanup complete, proceed with
git add/commit/push - APPLIES TO: All code commits in dbt-core-mcp workspace
- VIOLATION PENALTY: Immediate acknowledgment and restart with correct procedure
- NO EXCEPTIONS
- STEP 1: Before staging/committing ANY code changes, run CI validation sequence in order:
-
Selective Testing Protocol:
- RUN
pytestto validate implementations and verify code works - Tests provide definitive feedback on whether changes are correct
- Use tests during development to catch issues early
- For targeted testing: run specific test files or functions when fixing particular issues
- Pre-commit validation always requires full test suite (Law 1 requirement)
- Let tests decide if implementation works rather than guessing
- For complete validation:
uv run ruff check src tests && uv run ruff format --check src tests && uv run pyright src tests && uv run pytest - NO EXCEPTIONS
- RUN
-
Git Commit Amendment Protocol:
- When fixing issues in the MOST RECENT commit (before anyone else pulls):
- Use
git commit --amend --no-editto fix without creating new commit - Use
git push --forceto rewrite remote history - Keeps git history clean for release notes
- Use
- ONLY amend if commit hasn't been pulled by others
- Examples: formatting fixes, typos, forgot to add files after initial commit
- DO NOT create second commits for fixes to recent work (clutters release notes)
- APPLIES TO: All git operations in dbt-core-mcp workspace
- NO EXCEPTIONS
- When fixing issues in the MOST RECENT commit (before anyone else pulls):
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.
- 5d ago First seen · 81 lines · 978 tokens per session scan A c2f004478192
dbt-core-mcp memory.instructions.md is an instructions file published in the GitHub repository NiclasOlofsson/dbt-core-mcp (15 stars, last pushed 4mo ago), licensed MIT. It adds 978 tokens to every session, about $0.0049 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 2026-08-30.
Other instructions, from other repositories
docglow CLAUDE.md
Instructions for docglow/docglow, covering claude.md — docglow, project, tech stack, build & test and python.
featherspec knowledge-records.instructions.md
FeatherSpec knowledge record rules — observation, rationale, provenance (thin loader).
featherspec memory-bank.instructions.md
FeatherSpec Memory Bank writing rules (thin loader).
dbt-doctor AGENTS.md
Instructions for northgraindata/dbt-doctor, covering dbt-doctor, stack, commands and conventions.
LogseqBrain CLAUDE.md
Instructions for jame581/LogseqBrain, covering claude.md, what this repo is, architecture, shared references (since v0.6.0) and graph path resolution (every skill does this).
sdd-starter AGENTS.md
AGENTS.md instructions for KazukiShinomiya/sdd-starter, covering agents.md - project context (shared memory for ai agents), active tech stack, recent changes and 憲法の扱い（テンプレ本体の開発）.