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/dhtmlx/gantt/agents-mdgit clone --depth 1 https://github.com/DHTMLX/ganttWhat 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 | $0.00636 | $0.00636 |
| Opus 5 | $0.00318 | $0.00318 |
| Sonnet 5 | $0.00127 | $0.00127 |
| Haiku 4.5 | $0.00064 | $0.00064 |
Grade A, and why
gantt 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 yesterday.
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 — 47 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
Guidance for AI coding agents working in this repository.
What this is
DHTMLX Gantt, MIT edition — an open source JavaScript Gantt chart library. The repository ships library sources, samples, and a smoke test suite. It is generated from an internal source tree on each release (see CONTRIBUTING.md), so structural refactors should stay minimal and focused.
Layout
| Path | Content |
|---|---|
src/dhtmlxgantt.ts |
library entry point |
src/core/ |
core: datastores, task data layer, UI (grid, timeline, lightbox), worktime |
src/core/plugins/ |
always-on plugins (batch update, task types, formatters…) |
src/ext/ |
opt-in extensions activated via gantt.plugins({...}) (tooltip, quick_info, keyboard_navigation…) |
src/css/ |
LESS styles, fonts, skins |
src/locale/ |
locales |
samples/ |
runnable demos; served by npm run start, and the corpus the smoke test loads |
scripts/ |
build/dev/test node scripts, sample-data backend |
codebase/ |
build output (generated; never edit by hand) |
Commands
npm install
npm run build # vite build -> codebase/ + d.ts
npm run start # watch build + backend (:9200) + vite devserver
npm run test # build + smoke test: every sample loads without console errors
npm run test 07_grid # smoke just one samples folder
npm run lint # eslint over src/ (flat config, intentionally lax)
Working on the code
- The build must stay green:
npm run buildafter anysrc/change, andnpm run lintshould pass. npm run testis a smoke pass: it loads every sample headless and fails on a page error orconsole.error. It is the regression net — keep it green aftersrc/changes.- Sample pages reference
../../codebase/dhtmlxgantt.js— run a build before opening them. src/types.d.tsdeclares the compile-time globals (VERSION,LICENSE, …) injected by vitedefine.- Some modules are intentional basic implementations of Pro features (e.g.
src/core/ui/render/dummy_layer.js, re-export shims likesrc/core/ui/grid/resource_grid.js, andsrc/core/worktime/strategy/calendar_strategy.jswhich re-exports the disabledno_work_timestrategy — working-time calendars are out of scope). Do not "complete" them — the Pro feature set is out of scope for this edition (see README).
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.
- yesterday First seen · 47 lines · 636 tokens per session scan A b816f7b7143a
gantt AGENTS.md is an instructions file published in the GitHub repository DHTMLX/gantt (1,841 stars, last pushed 12d ago), licensed MIT. It adds 636 tokens to every session, about $0.0032 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
single-file-wbs CLAUDE.md
Instructions for piguo45/single-file-wbs, covering wbs ツール - claude.md, 製品ビジョン・設計指針(#67), 取り扱いの原則(重要), アーカイブ運用(過去タスクの整理) and 動作環境.
task-cli GEMINI.md
Instructions for sunjiawe/task-cli, covering agentic coding: humans design, agents code!, agentic coding steps, example llm project file structure, pocket flow and core abstraction.
FlowBoard AGENTS.md
Instructions for rasimme/FlowBoard, covering flowboard — agent entry point, start here and where things live.
STAR AGENTS.md
Instructions for wanghao9610/STAR, covering agent instructions, 1. think before coding, 2. simplicity first, 3. surgical changes and 4. goal-driven execution.
AllBeads CLAUDE.md
Instructions for thrashr888/AllBeads, covering claude.md, project overview, what allbeads does, current state (v0.2.0) and rust development commands.
claude-sdd-planner AGENTS.md
AGENTS.md instructions for danweinerdev/claude-sdd-planner, covering sdd planner — agent development guide, what this repository is, build and test, editing rules (the ones that bite) and conventions (single sources of truth).