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/danweinerdev/claude-sdd-planner/agents-mdgit clone --depth 1 https://github.com/danweinerdev/claude-sdd-plannerWrote 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/danweinerdev/claude-sdd-planner/agents-md)<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>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 | $0.01601 | $0.01601 |
| Opus 5 | $0.00800 | $0.00800 |
| Sonnet 5 | $0.00320 | $0.00320 |
| Haiku 4.5 | $0.00160 | $0.00160 |
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.
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 bysdd 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.mdis the decision ledger; itsacceptedD-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 undertools/) - 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, …)
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.
- 3d ago First seen · 75 lines · 1,601 tokens per session scan A c81d2e434660
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.
Other instructions, from other repositories
claude-sdlc CLAUDE.md
Claude Code instructions for lantisprime/claude-sdlc, covering claude.md, what this repo is, design intent — read this before "improving" anything, eat your own dog food and hook strictness philosophy.
harness-forge AGENTS.md
AGENTS.md instructions for ldilov/harness-forge, covering harness forge agent guidance, mode awareness, resolution rule, installed runtime map and language discovery.
harness-forge CLAUDE.md
Claude Code instructions for ldilov/harness-forge, covering harness forge, quick reference, cli commands, essential commands and living loop commands.
pinotator AGENTS.md
AGENTS.md instructions for transcendr/pinotator, covering goal queue prompt routing, goal queue processing and semantics and git tracking rules.
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.