agentmods.dev

planr AGENTS.md

Repository instructions for working on instructa/planr, a local-first planning and execution tool for coding agents. They define the product documents, architecture boundaries, data contracts, and expected workflow.

In plain words
What is it for?
Use them when implementing or documenting Planr features, consulting product and technical plans, following frozen contracts, and preserving map, evidence, approval, and closure rules.
Why use it?
They give agents a consistent source of truth for how Planr should be designed, changed, logged, reviewed, and completed.

Instructions file for CodexOpenCode

71 5d ago A scan 295 tokens original MIT
View the source file instructa/planr
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/instructa/planr/agents-md
Clone the repo
git clone --depth 1 https://github.com/instructa/planr

Made for: Codex, OpenCode.

Per session 295 This file is loaded in full into every session.
When invoked 295 The same file — it is already loaded in full.
Security scan A 0 findings. 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 $0.00295 $0.00295
Opus 5 $0.00148 $0.00148
Sonnet 5 $0.00059 $0.00059
Haiku 4.5 $0.00030 $0.00030

Measured yesterday against content hash 3938baafc6d0, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

planr 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.

AGENTS.md · 23 lines

What it actually says

Planr Agent Instructions

Planr is being shaped into a local-first planning and execution coordination tool for Codex, Claude Code, Cursor, and generic MCP clients.

Use the product plan package in .planr/plans/product/planr/ as the product source of truth for new implementation work:

  • PRODUCT_SPEC.md for scope and non-goals.
  • TECH_ARCHITECTURE.md for ownership boundaries.
  • API_AND_DATA_MODEL.md for project, plan, map, item, log, review, and API contracts.
  • TASKS.md for executable coding-agent tasks.

Frozen contracts live in docs/contracts/.

Core rules:

  • Build Planr as a self-owned product with original implementation, docs, and naming.
  • Use the public product flow: idea -> product plan -> build plan -> map -> pick -> log -> review/evidence -> recovery/package -> close.
  • Keep map graph state authoritative for item status, links, picks, reviews, approvals, and completion.
  • Keep product and build plans first-class for rich scope, ownership, verification, and narrative context.
  • Require log-backed closure: files changed, commands run, tests/review results, and blocked or unverified items.
  • Support Codex, Claude Code, and Cursor as peers through MCP and CLI workflows.
  • Never modify, replace, or re-upload an already published release. Fix release defects only by bumping and publishing a new version.
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. yesterday First seen · 23 lines · 295 tokens per session scan A 3938baafc6d0

Subscribe to this mod's changes

planr AGENTS.md is an instructions file published in the GitHub repository instructa/planr (71 stars, last pushed 5d ago), licensed MIT. It adds 295 tokens to every session, about $0.0015 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.

PlanningProductivityai-agentclaudecodexcursorgraph
Related

Other instructions, from other repositories

awesome-copilot-id AGENTS.md

Instructions for GulajavaMinistudio/awesome-copilot-id, covering communication, explanation and documentation, markdown formatting, user communication style and workflow & methodology.

GulajavaMinistudio/awesome-copilot-id · 7,686 tokens

hiveshare CLAUDE.md

Instructions for KB-perByte/hiveshare, covering hiveshare — claude.md, repo layout, build & run, key env vars (server) and naming: hive vs memory.

KB-perByte/hiveshare · 1,301 tokens

llm-safe-haven CLAUDE.md

Instructions for pleasedodisturb/llm-safe-haven, covering llm safe haven, what this is, project structure, tdd — non-negotiable (adopted 2026-08-17) and the contract.

pleasedodisturb/llm-safe-haven · 1,322 tokens

kleosrules AGENTS.md

Instructions for kleosr/kleosrules, a project described as: Cursor harness pack: user rules, skills, Bash hooks, local HANDOFF memory. macOS, Linux, Windows (WSL).

kleosr/kleosrules · 417 tokens

coding-agent-safety-gate AGENTS.md

Instructions for ASER-ho/coding-agent-safety-gate, covering agents / 代理规则, 仓库类型 / repository type and ai 代理规则 / rules for ai coding agents.

ASER-ho/coding-agent-safety-gate · 589 tokens

data-scientist copilot-instructions.md

Instructions for realnghon/data-scientist, covering github copilot — 项目指令：data scientist 工作流 and 共享核心 — 回答前请阅读.

realnghon/data-scientist · 373 tokens