Borrowing it
Nothing to install: this file belongs to trojava/spec-driven-dev-kit. 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/trojava/spec-driven-dev-kit/main/AGENTS.mdgit clone --depth 1 https://github.com/trojava/spec-driven-dev-kitWrote 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/trojava/spec-driven-dev-kit/agents-md)<a href="https://agentmods.dev/instructions/trojava/spec-driven-dev-kit/agents-md"><img src="https://agentmods.dev/badge/instructions/trojava/spec-driven-dev-kit/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/trojava/spec-driven-dev-kit/agents-md"><img src="https://agentmods.dev/badge/instructions/trojava/spec-driven-dev-kit/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 | $0.02941 | $0.02941 |
| Opus 5.5 | $0.01176 | $0.01176 |
| Sonnet 5.5 | $0.00588 | $0.00588 |
| Haiku 4.5 | $0.00294 | $0.00294 |
Grade A, and why
spec-driven-dev-kit 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 — 246 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Gemeinsame Regeln für Coding-Agenten
Diese Regeln gelten unabhängig vom verwendeten Skill. Die konkreten Abläufe
stehen unter .agents/skills/.
Sitzungsbeginn
Deine erste Antwort in einer neuen Sitzung ist die Frage: „Soll ich zuerst den
Projektstatus ermitteln und anzeigen?" Stelle sie mit dem Frage-Werkzeug aus
Rückfragen vor dem Ausfüllen, mit Ja als erster Option. Das gilt auch,
wenn der erste Auftrag bereits einen Skill oder ein Feature nennt. Beginne den
Auftrag erst nach der Antwort. Bei Ja gehst du nach Projektstand ermitteln
vor.
Werkzeugkompatibilität
Die kanonischen Skills liegen unter .agents/skills/ und sind die einzige
maßgebliche Quelle.
- Codex erkennt die Skills dort automatisch.
- Claude Code liest diese Datei über
CLAUDE.mdund findet die Skills über die Adapter unter.claude/skills/. Diese Adapter verweisen nur auf die kanonischeSKILL.mdund enthalten keine fachlichen Inhalte. - OpenCode liest diese Datei direkt und erkennt die Skills unter
.agents/skills/automatisch. Es durchsucht auch.claude/skills/; findet es einen Skill dadurch doppelt, gilt die kanonischeSKILL.md. - Kopiere oder synchronisiere Skill-Inhalte nicht nach
.claude/skills/. - Pflege fachliche Änderungen ausschließlich unter
.agents/skills/. Passe einen Adapter nur an, wenn sichnameoderdescriptionändern oder ein Skill hinzukommt bzw. entfällt.
Dieselbe Regel gilt für die Rollen-Agenten backend-entwickler,
frontend-entwickler und qs-pruefer: kanonisch unter .agents/agents/,
Adapter für Claude Code unter .claude/agents/ und für OpenCode unter
.opencode/agents/. Die Skills $feature-umsetzen und $feature-pruefen
delegieren an diese Rollen, wenn das Werkzeug sie als Subagenten kennt, und
arbeiten sonst selbst nach derselben Rollenbeschreibung.
Referenzen unter .agents/skills/*/references/ sind Arbeitsgrundlage des
jeweiligen Skills, keine verbindliche Quelle. Verbindlich ist nur, was daraus
bestätigt in ein Projektdokument übernommen wurde.
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 · +6 lines · +97 tokens per session 855324cd69f0
- 1mo ago Changed · +83 lines · +1,010 tokens per session 2573266274bf
- 1mo ago Changed · +74 lines · +932 tokens per session 1e0bce5210ba
- 2mo ago First seen · 83 lines · 902 tokens per session scan A d89deda0b81c
spec-driven-dev-kit AGENTS.md is an instructions file published in the GitHub repository trojava/spec-driven-dev-kit (9 stars, last pushed 1mo ago), licensed MIT. It adds 2,941 tokens to every session, about $0.0118 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 2026-08-31.
Other instructions, from other repositories
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).
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
vscode copilot-instructions.md
Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).
deno copilot-instructions.md
Copilot instructions for denoland/deno, covering deno development guide for github copilot, network access, high level overview, key directories and key files to understand first.