Borrowing it
Nothing to install: this file belongs to gulmezeren2-byte/erp-report-engine. 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/gulmezeren2-byte/erp-report-engine/main/AGENTS.mdgit clone --depth 1 https://github.com/gulmezeren2-byte/erp-report-engineWrote 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/gulmezeren2-byte/erp-report-engine/agents-md)<a href="https://agentmods.dev/instructions/gulmezeren2-byte/erp-report-engine/agents-md"><img src="https://agentmods.dev/badge/instructions/gulmezeren2-byte/erp-report-engine/agents-md.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 | $0.01218 | $0.01218 |
| Opus 5 | $0.00609 | $0.00609 |
| Sonnet 5 | $0.00244 | $0.00244 |
| Haiku 4.5 | $0.00122 | $0.00122 |
Grade A, and why
erp-report-engine AGENTS.md scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 8d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 73 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md — working on this repo with an AI coding agent
Context for coding agents (and fast-moving humans) contributing here.
What this is
A read-only autonomous reporting engine that runs SQL against the database behind an ERP and renders a weekly HTML report. The two things that must survive any change: the read-only guarantee and the report's honesty features (audit trail, reconciliation, data-quality gate, explicit definitions).
Hard invariants — never weaken these
connect.safe_readis the only path to the database. Do not add a second one; route new queries through it.assert_read_onlymust keep rejecting: multiple statements, comments (--,/*), non-SELECT/WITHheads, and the forbidden keyword list (includingINTO,EXEC,CALL). If you touch it, extendtests/test_engine.py::test_guard_blocks_writes_and_tricksfirst.- Profile
{placeholders}accept identifier-safe values only (^[A-Za-z0-9_]{1,16}$). All runtime values (dates, thresholds) travel as bound parameters (:since), never string-formatted into SQL. - Secrets never land in files or code. The config loader's embedded-password refusal stays.
- The report keeps its audit trail, source reconciliation, data-quality section and definitions footer. Features that hide information don't merge.
- Trends plot completed ISO weeks only — never the current partial week.
Layout
erp_report_engine/
errors.py # exception taxonomy with stable exit codes (2/3/4/5)
config.py # YAML config; refuses embedded credentials (make_url parse)
guard.py # THE security layer: 4-layer read-only guard (standalone: re + sqlglot only)
connect.py # engine, safe_read (the only DB path), read-only session, Auditor, retries
semantic.py # profile contracts (canonical entities, REQUIRED_COLUMNS); bundled resolver
week_calendar.py # ISO-week anchor + continuous axis (shared by report and Power BI)
extract.py # extraction + quality gate (dedup once) + COUNT(*) reconciliation
kpi.py # calendar-anchored ISO-week KPIs vs 8-week baseline
insights.py # deterministic findings + driver attribution
state.py # SQLite run memory (decline streaks, ordered by week)
render.py # self-contained HTML via Jinja2 autoescape (inline SVG)
runner.py # orchestration facade (validate / build_report / guarded_query)
export_powerbi.py # star-schema CSV export for the PBIP layer
mcp_server.py # guarded MCP server (FastMCP tools over the same read-only path)
logsetup.py # stderr + JSON-lines logging, run id
cli.py # validate / run / export-powerbi / mcp / init-demo
demo_builder.py # bundled synthetic demo DB builder (seeded, deliberately dirty)
profiles/ # bundled package-data profiles: generic (canonical), logo_tiger (MSSQL)
powerbi/ # PBIP project authored as code (TMDL model + PBIR report)
tools/generate_report_pages.py # PBIR pages are GENERATED - edit specs, rerun, never hand-edit visual.json
demo/ # thin shim -> erp_report_engine.demo_builder (kept for docs)
tests/ # guard, contracts, calendar props, render/XSS, honesty, CLI, MCP, PBIP
pyproject.toml # packaging (hatchling), console script, extras, ruff config
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.
- 8d ago First seen · 73 lines · 1,218 tokens per session scan A 4f4b586e0f48
erp-report-engine AGENTS.md is an instructions file published in the GitHub repository gulmezeren2-byte/erp-report-engine (1 stars, last pushed 1mo ago), licensed MIT. It adds 1,218 tokens to every session, about $0.0061 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 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.
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.