What is 1confdb-knw AGENTS.md?

Repository instructions for coding agents working on 1confdb-knw, a tool that extracts 1C:Enterprise business-automation configurations into a searchable SQLite knowledge base. They describe the project, its limits, layout and commands.

Use them when inspecting, testing or modifying the 1confdb-knw repository, especially its configuration extractor and read-only MCP server.

They give an agent the project-specific facts and restrictions it needs before changing code. This reduces mistakes such as adding unsupported encoding features or using the wrong runtime setup.

How Zom31C/1confdb-knw configures Codex and OpenCode

Reuse

Borrowing it

Nothing to install: this file belongs to Zom31C/1confdb-knw. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/Zom31C/1confdb-knw/main/AGENTS.md

Clone the repo

git clone --depth 1 https://github.com/Zom31C/1confdb-knw

Made for: Codex, OpenCode.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/zom31c/1confdb-knw/agents-md.svg)](https://agentmods.dev/instructions/zom31c/1confdb-knw/agents-md)

Your own site

<a href="https://agentmods.dev/instructions/zom31c/1confdb-knw/agents-md"><img src="https://agentmods.dev/badge/instructions/zom31c/1confdb-knw/agents-md.svg" alt="Measured on agentmods" height="20"></a>

Per session 1,700 This file is loaded in full into every session.

When invoked 1,700 The same file — it is already loaded in full.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

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	$0.01700	$0.01700
Opus 5	$0.00850	$0.00850
Sonnet 5	$0.00340	$0.00340
Haiku 4.5	$0.00170	$0.00170

Measured 7d ago against content hash 5bd5928b0ef9, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

1confdb-knw 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 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.

AGENTS.md · 102 lines

How it starts

The opening of the file, as written. The whole thing — 102 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md — guide for LLM agents working in this repository

What this project is

confdb extracts a 1C:Enterprise 8 configuration (.cf / .cfe / .epf) into a SQLite knowledge base — metadata objects, attributes with resolved types, tabular sections, BSL modules/methods, SKD report queries — and serves it to LLM agents via the MCP server 1confdb-knw (stdio, read-only). The unpack algorithm is a port of v8unpack (MIT; reference copy in _vendor/v8unpack, see NOTICE.md). Decode only — never add encode/pack code.

Domain glossary: 1C = Russian business-automation platform; BSL = its built-in (Russian-keyword) language; Catalog=справочник, Document=документ, (Information/Accumulation)Register=регистр, Enum=перечисление, tabular section=табличная часть (row table of an object).

Hard constraints

Python >= 3.9, runtime stdlib only (pytest is the only dev extra).
Windows-oriented: .bat wrappers in repo root; venv in .venv (MS Store Python: .venv\Scripts\python.exe is a launcher, the real worker is a child process).
Git is available (2.55+); the project root is not a repo — the published repo lives in dist\1confdb-knw (remote Zom31C/1confdb-knw).
Comments, docstrings and user-facing text are in Russian.
The 885 MB test file SmallBusinessKz_3_0_4_4_cf.cf lives in cf/ (or repo root); never commit it; a full extract takes ~2.5 min with --workers 8 — keep it out of unit tests (tests use small synthetic fixtures).
Keep the decoder equivalent to _vendor/v8unpack; comparison helpers in _tmp/.

Layout

src/confdb/extract.py — pipeline stages 0/1/3 (containers → inflate → decode).
src/confdb/__main__.py — CLI: extract, check, 1confdb-knw.
src/confdb/mcp_server.py — MCP server 1confdb-knw <db…> (16 tools, read-only; self-describing: schema primer + glossary + workflow in initialize.instructions). Multi-database: several knowledge bases open at once (main configuration + extensions/data processors), each under an alias; tools take an optional db alias parameter; db_list/db_open/db_use/db_close manage them at runtime. Transports: stdio by default; --port N — HTTP (Streamable HTTP POST /mcp, legacy SSE /sse) for SSH-tunnel access (ssh -L N:127.0.0.1:N).
src/confdb/tui.py — console UI (user chose console over GUI; do not suggest tkinter).
src/confdb/bsl_parser.py — splits BSL modules into procedures/functions.
src/confdb/query_lang.py — 1C query language lexer/parser/semantic validator.
src/confdb/db/writer.py — SQLite schema + dump writer (batched inserts; BSL parsing parallelized via workers).
src/confdb/bench.py — hardware benchmark: non-linear object sample (stride over the whole top-level list + one object of every type) timed through stage 3 + DB write at 1/2/4/8/CPU processes; best workers saved to ~/.confdb/config.json (src/confdb/config.py — shared user config, also used by the TUI).
src/confdb/v8/ — ported unpack core.
tests/ — fast tests (test.bat); _tmp/ — throwaway probes (gitignored).

Read the full file on GitHub · 102 lines

Changes

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 · 102 lines · 1,700 tokens per session scan A 5bd5928b0ef9

Subscribe to this mod's changes

1confdb-knw AGENTS.md is an instructions file published in the GitHub repository Zom31C/1confdb-knw (0 stars, last pushed 7d ago), licensed MIT. It adds 1,700 tokens to every session, about $0.0085 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.

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.

openai/codex · 5,182 tokens

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).

microsoft/vscode · 6,785 tokens

1confdb-knw: Instructions file for Codex