claude-sdd-planner AGENTS.md

claude-sdd-planner AGENTS.md is an instructions file for Codex, OpenCode from danweinerdev/claude-sdd-planner. It costs 1,601 tokens per session, scanned A, original, MIT.

Repository instructions for an SDD Planner, a toolchain that turns software specifications into work for different coding-agent systems.

In plain words
What is it for?
Use them when modifying planner commands, agent definitions, skills, hooks, generated plugin trees, or the Go-based command-line tool.
Why use it?
They explain which files are the source of truth, which generated files must not be edited directly, and how to build, test, and validate changes.

Instructions file for CodexOpenCode

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/danweinerdev/claude-sdd-planner/agents-md
Clone the repo
git clone --depth 1 https://github.com/danweinerdev/claude-sdd-planner

Made for: Codex, OpenCode.

Wrote 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.

agentmods badge for claude-sdd-planner AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/danweinerdev/claude-sdd-planner/agents-md.svg)](https://agentmods.dev/instructions/danweinerdev/claude-sdd-planner/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/danweinerdev/claude-sdd-planner/agents-md"><img src="https://agentmods.dev/badge/instructions/danweinerdev/claude-sdd-planner/agents-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 1,601 This file is loaded in full into every session.
When invoked 1,601 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 $0.01601 $0.01601
Opus 5 $0.00800 $0.00800
Sonnet 5 $0.00320 $0.00320
Haiku 4.5 $0.00160 $0.00160

Measured 3d ago against content hash c81d2e434660, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

claude-sdd-planner 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 3d 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.

AGENTS.md · 75 lines

How it starts

The opening of the file, as written. The whole thing — 75 lines — stays where its author put it; the contents beside it link to each section on GitHub.

SDD Planner — Agent Development Guide

Runtime-neutral instructions for any coding agent working on this repository. (CLAUDE.md carries the same material with Claude Code specifics; where they disagree, fix both — that is a doc bug.)

What this repository is

A spec-driven development toolchain published to multiple agent harnesses from one source:

  • Repo root — the canonical, hand-edited Claude Code plugin: commands/ (lifecycle skills), agents/ (review/implementation agent definitions), skills/ (model-loaded reference skills), shared/ (conventions + templates), hooks/.
  • .codex-plugin/ and .opencode-plugin/ — GENERATED plugin trees for Codex and OpenCode, identical content, produced by sdd plugin sync. Never edit these by hand — any hand edit is destroyed by the next sync and rejected by the drift gate.
  • cmd/sdd + internal/ — the cross-platform Go binary behind every skill: deterministic validation (sdd validate), artifact writes, lifecycle transitions, hooks, and the portable-tree generator (internal/portable).
  • .plans/ — this repo's own planning artifacts. .plans/Decisions/decisions.md is the decision ledger; its accepted D-NNNN entries are standing constraints on all work here. A change that contradicts one must stop for user reconciliation, never silently proceed. The ledger itself is never edited — for any reason — without the user's explicit approval of the exact, unmodified text of the change, shown in full beforehand.

Build and test

make build          # compile the sdd binary into build/<os>-<arch>-debug/
make test           # THE gate: Go suite + frozen regression corpus + template gate + portable drift/leak gates
make plugins        # regenerate .codex-plugin/ and .opencode-plugin/ (sdd plugin sync)
make plugins-check  # fail if the generated trees are stale
sdd plugin status   # provenance of every portable file (generated / variant / override)

Run make test before claiming any change works. It fails on:

  • unit or regression failures (go test ./..., including the corpus under tools/)
  • templates drifting from the schema (sdd template --check)
  • either generated tree differing from a fresh generation
  • Claude-isms leaking into portable output (sdd-planner:, the Task tool, ~/.claude, …)

Read the full file on GitHub · 75 lines

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. 3d ago First seen · 75 lines · 1,601 tokens per session scan A c81d2e434660

Subscribe to this mod's changes

claude-sdd-planner AGENTS.md is an instructions file published in the GitHub repository danweinerdev/claude-sdd-planner (2 stars, last pushed 5d ago), licensed MIT. It adds 1,601 tokens to every session, about $0.0080 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 2026-08-31.

Related

Other instructions, from other repositories