Borrowing it
Nothing to install: this file belongs to BjornMelin/docmind-ai-llm. 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/BjornMelin/docmind-ai-llm/main/AGENTS.mdgit clone --depth 1 https://github.com/BjornMelin/docmind-ai-llmWrote 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/bjornmelin/docmind-ai-llm/agents-md)<a href="https://agentmods.dev/instructions/bjornmelin/docmind-ai-llm/agents-md"><img src="https://agentmods.dev/badge/instructions/bjornmelin/docmind-ai-llm/agents-md/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/instructions/bjornmelin/docmind-ai-llm/agents-md"><img src="https://agentmods.dev/badge/instructions/bjornmelin/docmind-ai-llm/agents-md.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 | $0.05757 | $0.05757 |
| Opus 5 | $0.02878 | $0.02878 |
| Sonnet 5 | $0.01151 | $0.01151 |
| Haiku 4.5 | $0.00576 | $0.00576 |
Grade A, and why
docmind-ai-llm AGENTS.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 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 — 397 lines — stays where its author put it; the contents beside it link to each section on GitHub.
DocMind AI: Agent instructions
Purpose
Repo guardrails for contributors/automation. Keep aligned with code, pyproject.toml,
and docs under docs/specs/ + docs/developers/adrs/.
Layout
app.py: Streamlit entrypointsrc/app.py: Streamlit app module (imported byapp.py)src/pages/: UI pages (chat/documents/analytics/settings)src/config/: settings + integration wiringsrc/processing/: ingestion, OCR, PDF page exportssrc/retrieval/: router, hybrid retrieval, reranking, GraphRAG helperssrc/agents/: LangGraph coordinator (graph-native supervisor viaStateGraph)src/persistence/: snapshots, hashing, locking, chat DBsrc/telemetry/+src/utils/telemetry.py: OTEL + JSONL eventssrc/prompting/templates/: bundled prompt templates and presetsdocs/specs/+docs/developers/adrs/: specs/ADRs (source-of-truth docs)scripts/+tools/: benchmarks, health checks, documentation gates, and model pull
Quick commands with uv
- Setup:
uv sync && cp .env.example .env - Run:
uv run streamlit run app.py(or./scripts/run_app.sh) - Env: prefer
uv run ...(uses the project env, typically.venv). - Verify (batch): after a batch of edits, run lint/type on touched paths + focused tests.
- Format (all):
uv run ruff format . - Lint (all):
uv run ruff check . - Type (paths):
uv run pyright --threads 4 <paths> - Tools-only (when
tools/changed):uv run pyright --threads 4 tools - Tests (focused):
uv run pytest <tests/...> -vv --no-cov(or-k <expr>for a narrow slice)
- Format (all):
- Verify (final): before finishing the task/prompt, run non-mutating full lint/type
checks, then full tests:
uv run ruff format --check . && uv run ruff check . && uv run pyright --threads 4 && uv run pytest tests/unit tests/integration -q --no-cov - Tests (unit):
uv run pytest tests/unit -q --no-cov - Tests (integration):
uv run pytest tests/integration -q --no-cov - Tests (fast/full):
uv run pytest tests/unit tests/integration -q --no-cov - Tests (GPU):
uv run pytest -m requires_gpu --no-cov - Coverage:
uv run pytest tests/unit tests/integration -q --cov=src --cov-branch --cov-report=term-missing --cov-report=html:htmlcov --cov-report=xml:coverage.xml --cov-report=json:coverage.json --cov-fail-under=80 --junitxml=junit.xml - Coverage report:
uv run python scripts/check_coverage.py --collect --report --html - Parser benchmark:
uv run python scripts/benchmark_parsing.py --generate-minimal-fixtures --output cache/benchmarks/parsing/results.json - GPU check:
uv run python scripts/test_gpu.py --quick - Prefetch default retrieval and Docling layout models:
uv run python tools/models/pull.py --all --cache_dir ./models_cache --parser-defaults --parser-cache-dir ./cache/models; RapidOCR models come from its locked wheel. - spaCy model (opt):
uv run python -m spacy download en_core_web_sm - Review triage:
uv run python scripts/analyze_github_reviews.py --json-file <path>(or setDOCMIND_REVIEW_JSON)
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 · 397 lines · 5,757 tokens per session scan A a1c3cd70a375
docmind-ai-llm AGENTS.md is an instructions file published in the GitHub repository BjornMelin/docmind-ai-llm (151 stars, last pushed 21d ago), licensed MIT. It adds 5,757 tokens to every session, about $0.0288 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
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
deepseek-harness AGENTS.md
AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.