What is killbottleneck AGENTS.md?

Repository instructions for people and coding agents working on killBottleneck, a project and task manager with an AI assistant. They describe the code layout, local setup, tests, conventions, contributions, and licence.

Use them to navigate the project, follow its coding rules, run regression tests, and prepare contributions.

They reduce guesswork when changing this repository by showing where code belongs and how to run and check it.

How tengolabs/killbottleneck configures Codex and OpenCode

Reuse

Borrowing it

Nothing to install: this file belongs to tengolabs/killbottleneck. 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/tengolabs/killbottleneck/main/AGENTS.md

Clone the repo

git clone --depth 1 https://github.com/tengolabs/killbottleneck

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/tengolabs/killbottleneck/agents-md/github.svg)](https://agentmods.dev/instructions/tengolabs/killbottleneck/agents-md)

Your own site

<a href="https://agentmods.dev/instructions/tengolabs/killbottleneck/agents-md"><img src="https://agentmods.dev/badge/instructions/tengolabs/killbottleneck/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.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/tengolabs/killbottleneck/agents-md"><img src="https://agentmods.dev/badge/instructions/tengolabs/killbottleneck/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 839 This file is loaded in full into every session.

When invoked 839 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	$0.00839	$0.00839
Opus 5.5	$0.00336	$0.00336
Sonnet 5.5	$0.00168	$0.00168
Haiku 4.5	$0.00084	$0.00084

Measured today against content hash 48715977b97a, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

killbottleneck 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 today.

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 · 65 lines

How it starts

The opening of the file, as written. The whole thing — 65 lines — stays where its author put it; the contents beside it link to each section on GitHub.

killBottleneck — notes for people and AI agents working in this repository

killBottleneck is a goal-map, project and task manager with an AI assistant, for teams and for AI agents. One Docker container: PocketBase (Go, embedded SQLite, JS hooks) serves the React web client, the REST API and the MCP server's backend.

Layout

Path	What it is
`server/pb_hooks/`	Server logic: PocketBase JS hooks (Goja runtime — no npm, no `async`, CommonJS `require`)
`server/pb_migrations/`	Versioned schema and data migrations; `--automigrate=0`, every change is a file here
`frontend/`	React + Vite web client (`src/`), i18n catalogs in `frontend/src/i18n/{cs,en}/`
`mcp/`	`killbottleneck-mcp` — stdio MCP server talking to an instance's `/api/kb/v1/*`
`tests/`	Regression suites (Node, `_harness.js`); most start a fresh instance from the Docker image
`scripts/`	Repository tooling (third-party license list, help index, …)

Not in this repository: the Windows app (tengolabs/killbottleneck-desktop), the Android shell (ships through the store) and the sources of the documentation website (killbottleneck.com). The help index server/pb_hooks/napoveda-index.js is generated from those sources — do not edit it by hand.

Run it

cp .env.example .env          # optional — defaults work
docker compose up -d --build  # http://localhost:8090

The first account to sign up becomes the instance admin; further people are invited from the app (/api/kb/invite). KB_* variables are documented in .env.example and on the website (Reference → Environment variables).

Tests

docker build -t product-flowmap .                 # the image the suites run against
KB_TEST_IMAGE=product-flowmap node tests/<suite>.js   # one suite (KB_TEST_IMAGE is required)

Suites without Docker (i18n-catalog, licence-soubory, en-first, …) run straight away. A suite must print PASS n / FAIL m through _harness.js; a new suite is picked up by the full regression automatically.

Read the full file on GitHub · 65 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.

today First seen · 65 lines · 839 tokens per session scan A 48715977b97a

Subscribe to this mod's changes

killbottleneck AGENTS.md is an instructions file published in the GitHub repository tengolabs/killbottleneck (11 stars, last pushed today), licensed MIT. It adds 839 tokens to every session, about $0.0034 per session on Opus 5.5. 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 2026-11-07.

Writing and docs ai ai-agents docker goal-tracking kanban-alternative mcp

killbottleneck AGENTS.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
killbottleneck AGENTS.mdtengolabs/killbottleneck	Instructions file	11	today	MIT	A	839	Codex, OpenCode
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	9,719	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	today	MIT	A	7,461	Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	5,516	GitHub Copilot
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	today	MIT	A	4,680	Codex, OpenCode
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	3,093	GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness	Instructions file	275k	3d ago	MIT	A	4,313	Codex, OpenCode

killbottleneck: Instructions file for Codex