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/temiroff/blacknode/agents-mdgit clone --depth 1 https://github.com/temiroff/BlacknodeWhat 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 | $0.01885 | $0.01885 |
| Opus 5 | $0.00942 | $0.00942 |
| Sonnet 5 | $0.00377 | $0.00377 |
| Haiku 4.5 | $0.00188 | $0.00188 |
Grade A, and why
Blacknode 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 — 162 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Blacknode Agent Instructions
These instructions apply to the Blacknode core repository. Extension packages
under packages/ are separate Git repositories and carry their own AGENTS.md.
Route the task
- Use
.agents/skills/blacknode-workflow/SKILL.mdwhen the requested result is a workflow graph, template, editor run, replay, validation, or export. - Use
.agents/skills/blacknode-development/SKILL.mdwhen changing Blacknode, adding a reusable node, modifying the editor/runtime/MCP API, or creating an extension package. - When a workflow exposes a missing reusable capability, switch to the development skill, implement and test it, then return to the workflow skill to integrate and validate the graph.
Repository map
| Area | Responsibility |
|---|---|
python/blacknode/ |
Python graph model, runtime, nodes, CLI, packages, exporters, and MCP |
editor-server/ |
FastAPI editor backend, runtime services, sessions, and run replay |
editor/ |
React/TypeScript visual editor |
crates/ |
Rust types, core, runtime, Python bindings, and CLI |
templates/ |
Tracked reusable workflow graphs |
tests/ |
Core Python and integration tests |
packages/ |
Independently versioned extension-package checkouts |
Change rules
- Inspect the live node schema or the node decorator contract before adding or connecting ports. Do not invent port names or persisted runtime fields.
- Keep core broadly useful. Put hardware stacks, large optional dependencies, and domain-specific integrations in extension packages.
- Preserve compatibility for saved workflow node names unless a migration is included. New workflows should use the current generic names.
- Keep templates portable: declare
kind,schema_version, an explicit entrypoint, complete port metadata, and anymetadata.required_packages. - Never commit API keys, run logs, local workflows, editor state, caches, robot calibration data, or generated scratch exports.
- Treat camera, CUDA, ROS, and robot streams as managed services. Do not turn a one-shot cook into a polling loop.
- Keep physical motion disarmed by default. Retain stale-data, joint-limit, and shutdown safeguards in every transport path.
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 · 162 lines · 1,885 tokens per session scan A 1e8e3b5aba9e
Blacknode AGENTS.md is an instructions file published in the GitHub repository temiroff/Blacknode (23 stars, last pushed 2d ago), licensed Apache-2.0. It adds 1,885 tokens to every session, about $0.0094 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
ollama AGENTS.md
Instructions for ollama/ollama, covering agents.md and building.
ollama CLAUDE.md
Instructions for ollama/ollama: See AGENTS.md for the shared agent instructions for this repository.
pocketpaw CLAUDE.md
Instructions for pocketpaw/pocketpaw, covering claude.md, project overview, knowledge base, search the kb from terminal and show a specific module's wiki.
MaxKB CLAUDE.md
Claude Code instructions for 1Panel-dev/MaxKB, covering claude.md, project overview, development commands, database / static and architecture.
workflowbuilder CLAUDE.md
Instructions for synergycodes/workflowbuilder, covering workflow builder, quick reference, agent signals, monorepo structure and per-workspace docs.
codexia AGENTS.md
Instructions for milisp/codexia, covering agents.md, project info, project tech, common commands and project structure.