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/spineeventengine/config/agents-mdgit clone --depth 1 https://github.com/SpineEventEngine/configWhat 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 | $0.01473 | $0.01473 |
| Opus 5 | $0.00737 | $0.00737 |
| Sonnet 5 | $0.00295 | $0.00295 |
| Haiku 4.5 | $0.00147 | $0.00147 |
Grade A, and why
config 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.
How it starts
The opening of the file, as written. The whole thing — 136 lines — stays where its author put it; the contents beside it link to each section on GitHub.
👋 Welcome, Agents!
Orientation
If .agents/project.md exists in this repository, read it first — it describes
the language, architecture, and role of this specific repo within the Spine SDK
organisation. It is a symlink to docs/project.md; to create one, copy
.agents/guidelines/project.template.md to docs/project.md and fill it in. If it
links to a shared requirements file (e.g. jvm-project.md), read that too.
- Start every session by reading
.agents/guidelines/quick-reference-card.md(if present). - For specific tasks (code review, PR prep, dependency updates, docs, etc.),
prefer the matching skill from
.agents/skills/. - Full standards reference:
.agents/guidelines/_TOC.md(if present) — consult when a skill doesn't cover the needed context.
Shared skills, scripts, and guidelines come from the .agents/shared submodule (the
[agents][agents-repo] repository) exposed via symlinks.
./config/pull initializes and floats them automatically. But a fresh git worktree
(and some shallow clones / cloud checkouts) start with NO submodules checked out, so
those symlinks dangle and no skills are found. Bootstrap such a tree with
./init-submodules — a root script that materializes the missing
config-managed submodules at their pinned commits: config itself, plus every
submodule that declares a tracked branch in .gitmodules (.agents/shared, and
any shared submodule added later) — the same rule ./config/pull uses to decide
what it floats. Submodules the consumer owns (a Hugo theme, a vendored library,
doc-example submodules, …) declare no tracked branch and are left untouched, so the
automatic SessionStart run never tries to clone — or fail on credentials for — a
submodule this project does not manage. It depends on no pre-existing config
submodule, so it works before ./config/pull (which lives inside the config
submodule) can. Claude Code runs it automatically via a SessionStart hook; other
agents and humans run it by hand, then ./config/pull to float the shared submodules
to their branch tips.
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.
- yesterday First seen · 136 lines · 1,473 tokens per session scan A 85b519ef65db
config AGENTS.md is an instructions file published in the GitHub repository SpineEventEngine/config (2 stars, last pushed 2d ago), licensed Apache-2.0. It adds 1,473 tokens to every session, about $0.0074 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
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
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
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, applying the notice (cutover) and fallback chain (never fail the build).
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.
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.