Borrowing it
Nothing to install: this file belongs to instructa/planr. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/instructa/planr/main/AGENTS.mdgit clone --depth 1 https://github.com/instructa/planrWrote 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.
[](https://agentmods.dev/instructions/instructa/planr/agents-md)<a href="https://agentmods.dev/instructions/instructa/planr/agents-md"><img src="https://agentmods.dev/badge/instructions/instructa/planr/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.
<a href="https://agentmods.dev/instructions/instructa/planr/agents-md"><img src="https://agentmods.dev/badge/instructions/instructa/planr/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00734 | $0.00734 |
| Opus 5.5 | $0.00294 | $0.00294 |
| Sonnet 5.5 | $0.00147 | $0.00147 |
| Haiku 4.5 | $0.00073 | $0.00073 |
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 1mo 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.
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 — 37 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent guidance for planr
planr is a small planning layer for agent-built products: tasks as a Markdown graph in a planning repository, a dependency-free Node CLI, a board (standalone HTML and bb plugin) and one Agent Skill. Building happens elsewhere (for example split-orchestrator). planr says what is next; it never builds, reviews or verifies.
Read docs/contract.md (data and CLI contract) before changing code, and bb-plugin/README.md before changing the plugin.
Hard limits (crossing these needs a maintainer's explicit OK)
- No database, no locks/leases/heartbeats/atomic pick, no daemon, no MCP or HTTP server. Exception:
planr board --serve, a loopback-only file server with live reload. - No per-task gates, evidence system, auto-created fix/review items, or custom benchmark harness.
- No new task statuses. Statuses: open, in-progress, review, blocked, decision, done, dropped.
- Node ≥ 20, no runtime dependencies, no network access.
Stop and ask a maintainer when a change would cross one of these limits, introduces a new persistence mechanism, or makes a dispatcher do more than start threads.
Size orientation (not a gate)
Rough sizes: engine (skills/planr/scripts/) around 800 lines, skill around 60, tests around 150 (graph rules and frontmatter rewriting only, no regression test per bug fix). Format honestly: one statement per line, ≤ 110 characters, never compress code to hit a number. Going over is fine; mention the numbers in the handoff and do not stop work or ask about it.
Conventions
- One owner per rule: readiness, unlocks and validation live only in
skills/planr/scripts/lib/graph.mjs; the board reads derived fields and never recomputes them. - The planning repository is the source of truth. The engine and CLI never write outside it and never commit, push, merge or deploy. Exception: the bb plugin's host entry commits and pushes human board actions (approve goal, close goal, task checked) from its own worktree, as described in
bb-plugin/README.md. - bb plugin (
bb-plugin/): live tests only against an isolated local bb instance, never a bb server used for real work. Installing a development build there needs a maintainer's OK. - Tests run with
node --test. Exercise real planning data only in a throwaway clone, never in a live planning repo. Fixtures stay synthetic. - Keep
artifacts/untracked; it holds local agent run records. - Internal plans, decisions and release notes stay outside this repository.
- English for code, docs and UI labels. Task titles keep the planning repo's language.
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.
- 1mo ago Changed · +14 lines · +439 tokens per session 7604177f4e38
- 2mo ago First seen · 23 lines · 295 tokens per session scan A 3938baafc6d0
planr AGENTS.md is an instructions file published in the GitHub repository instructa/planr (74 stars, last pushed 17d ago), licensed MIT. It adds 734 tokens to every session, about $0.0029 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 2026-08-30.
planr AGENTS.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| planr AGENTS.mdinstructa/planr | Instructions file | 74 | 17d ago | MIT | A | 734 | Codex, OpenCode |
| data-scientist copilot-instructions.mdrealnghon/data-scientist | Instructions file | 2 | 4mo ago | MIT | A | 373 | GitHub Copilot |
| vscode buildNext.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 9,719 | GitHub Copilot |
| next.js AGENTS.mdvercel/next.js | Instructions file | 143k | today | MIT | A | 7,461 | Codex, OpenCode |
| langchain AGENTS.mdlangchain-ai/langchain | Instructions file | 149k | yesterday | MIT | A | 4,680 | Codex, OpenCode |
| vscode oss-third-party-notices.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 5,516 | GitHub Copilot |
| vscode copilot-instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 3,093 | GitHub Copilot |