agentmods.dev

FlowBoard AGENTS.md

Repository instructions for FlowBoard, a local dashboard that coordinates coding work through an HTTP API.

In plain words
What is it for?
Use them to check agent status, load the active project context, read its development rules, and retrieve the current task from the dashboard.
Why use it?
They tell an agent where to find the active project, current tasks, project knowledge, and detailed operating rules instead of relying on outdated assumptions.

Instructions file for CodexOpenCode

94 4d ago A scan 450 tokens original MIT
View the source file rasimme/FlowBoard
Install

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.

agentmods
npx agentmods add instructions/rasimme/flowboard/agents-md
Clone the repo
git clone --depth 1 https://github.com/rasimme/FlowBoard

Made for: Codex, OpenCode.

Per session 450 This file is loaded in full into every session.
When invoked 450 The same file — it is already loaded in full.
Security scan A 1 finding. Scan, not verified.
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.

ModelPer sessionOnce invoked
Fable 5 $0.00450 $0.00450
Opus 5 $0.00225 $0.00225
Sonnet 5 $0.00090 $0.00090
Haiku 4.5 $0.00045 $0.00045

Measured 2d ago against content hash a4a5a7ad0755, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

FlowBoard AGENTS.md scanned grade A with 1 finding 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 2d 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

`http://127.0.0.1:18790`. Use a local-capable tool (exec / curl / node) for
AGENTS.md · 34 lines

What it actually says

FlowBoard — agent entry point

FlowBoard coordinates work through the dashboard API at http://127.0.0.1:18790. Use a local-capable tool (exec / curl / node) for this localhost API — never an external web-fetch/browser. If an API call fails, report the blocker; do not infer state.

This file is only the trigger. Everything else is fetched on demand.

Start here

  1. Check your status: GET /api/status?agentId=<your-id>
  2. If activeProject === null: no project is active — work normally, don't infer state.
  3. If activeProject !== null:
    • Wait for contextReady (details in rules/error-handling).
    • Fetch context: GET /api/projects/<activeProject>/bootstrap. This includes the project's PROJECT.md, which carries project knowledge and the project-specific development rules — read them before changing code.
    • Treat GET /api/projects/<activeProject>/tasks (the Operational Task State) as the only current-task truth — not PROJECT.md.
    • Load rule sections on demand: GET /api/projects/<activeProject>/rules/<section> — commands, api-access, hzl, canvas, files, specify, agent-bridge, error-handling, key-principles, overview.

Where things live

  • Project-specific development rules (how to develop this project): the project's PROJECT.md, served via bootstrap.
  • Repo / product conventions (commit style, English-only UI strings): CONTRIBUTING.md.
  • Task execution & delegation: rules/agent-bridge + rules/api-access. Build spawn prompts with dashboard/hzl-service.js:buildSpawnPrompt() — do not hand-write them.
  • External agents (Codex, Cursor, Claude Code, …): see README § "Using FlowBoard with external agents" and node dashboard/install-trigger.mjs.
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.

  1. 2d ago First seen · 34 lines · 450 tokens per session scan A a4a5a7ad0755

Subscribe to this mod's changes

FlowBoard AGENTS.md is an instructions file published in the GitHub repository rasimme/FlowBoard (94 stars, last pushed 4d ago), licensed MIT. It adds 450 tokens to every session, about $0.0022 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Analytics and metricsBackend and APIsProject ManagementProject managementai-agentskanbanlocal-firstnodejsopenclaw
Related

Other instructions, from other repositories

veritas-kanban AGENTS.md

Instructions for BradGroux/veritas-kanban, covering agents.md — canonical agent instructions for veritas kanban, runtime requirements, repository layout, essential commands and install.

BradGroux/veritas-kanban · 7,081 tokens

veritas-kanban CLAUDE.md

Instructions for BradGroux/veritas-kanban, covering claude.md — claude-specific supplement for veritas kanban, what changed in v2.1, lessons learned (claude-specific), security and architecture.

BradGroux/veritas-kanban · 590 tokens

kaneo CLAUDE.md

Claude Code instructions for usekaneo/kaneo, a project described as: 🎯 All you need. Nothing you don't. Open source project management that works for you, not against you.

usekaneo/kaneo · 24 tokens

jjj CLAUDE.md

Instructions for doug/jjj, covering claude.md, project overview, build commands, rust cli and vs code extension.

doug/jjj · 2,133 tokens

jjj AGENTS.md

Instructions for doug/jjj, covering agent instructions, before you write anything, read this first, house rules and verifying changes to this repository.

doug/jjj · 464 tokens

sideboard CLAUDE.md

Instructions for mmyslin/sideboard: Sideboard's own roadmap lives in GitHub Issues (mmyslin/sideboard). The project is GitHub-only — there is no roadmap.json / local-file mode.

mmyslin/sideboard · 893 tokens