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/citiesskylinesmodding/agents-plugins/agents-mdgit clone --depth 1 https://github.com/CitiesSkylinesModding/agents-pluginsWhat 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 | $0.03456 | $0.03456 |
| Opus 5 | $0.01728 | $0.01728 |
| Sonnet 5 | $0.00691 | $0.00691 |
| Haiku 4.5 | $0.00346 | $0.00346 |
Grade A, and why
agents-plugins 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 2d 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 — 132 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
Project overview
agents-plugins is the CS Modding marketplace (csmodding) of agent plugins for Claude Code and OpenAI Codex CLI.
plugins/coherent-gameface/: flagship plugin. Drives a running Coherent Gameface UI (Cohtml) over a direct CDP WebSocket; TypeScript MCP server (npm@csmodding/gameface-devtools-mcp) + skills.plugins/unity-devtools/: drives a running Unity Mono development build over the Mono Soft Debugger protocol (SDB); C# MCP server + SDB class library.
Both are generic toolkits, developed and verified against Cities: Skylines II as the reference target.
Each plugin documents its own architecture and gotchas in its AGENTS.md (with a CLAUDE.md symlink).
Everything a plugin ships MUST live inside its plugins/<name>/ directory: marketplace installs copy only that subtree.
New plugins get a sibling directory and an entry in both marketplace files.
Tech stack
- mise-en-place: dev tools, env vars and tasks.
- Bun workspaces: the root
package.jsoncarries lint/format tooling (oxfmt.config.ts,oxlint.config.ts), lefthook, and whatscripts/andbench/import; the gamefacemcp/is the only workspace package, andbun.locklives at the root. The root tsconfig types against Node, since the scripts share its program with the mcp;bench/overrides that with its own nested tsconfig typing against Bun, which it runs on exclusively. - .NET 10 SDK: the unity-devtools C# projects, grouped by
agents-plugins.slnxat the repo root.
Repository structure
.claude-plugin/marketplace.jsonand.agents/plugins/marketplace.json: the Claude Code and Codex CLI marketplace files. Both list every plugin..mcp.json(root): LOCAL DEV ONLY, wiring both MCP servers for sessions in this repo (gameface from its committed bundle, unity from sources viadotnet run). Installed users get each plugin's own.mcp.json; keep them in sync when changing server wiring.scripts/:check-plugin-sync.ts(manifest consistency) andcheck-skill-content.ts(thecs2-moddingshipped-prose rules), both part ofmise check;check-skill-changelog.ts(mise skills:check-changelog, network-dependent, not in CI).hook-skill-content.tsis a PostToolUse hook spawning the shipped-prose lint on any edit under that plugin'sskills/, so a broken warning block, link or marker fails at the edit rather than at the commit; it adds no rule of its own..agents/hooks/check-line-length.ts: PostToolUse hook reporting.ts/.cslines over 100 characters. Synced verbatim from thescrollsrepo, which is why oxlint and oxfmt ignore.agents. Markdown is deliberately out of scope: these docs are agent-facing and unwrapped by design.docs/ROADMAP.md: planned facets.docs/solutions/: one file per hard-won problem, linked from where it bites.docs/adr/: numbered decision records.docs/authoring/: standing authoring contracts. The ticket template any spec's tickets take, pointed at fromdocs/agents/cantrips-loop.md's publish-tickets verb; and thecs2-moddingreference pipeline's own — one shape doc per reference family and the reference-ticket protocol — disclosed out of the plugin'sAGENTS.mdbecause only an authoring pass reaches them.check-skill-content.tsenforces both families' prose-line budgets.docs/SOURCES.md: every source thecs2-moddingpipeline may read, what each settles, and how to locate it. Other files point at it; keep it pointing at as few as possible.bench/: the skill-efficacy benchmark, measuring what thecs2-moddingskill is worth against the same model without it. ItsREADME.mdholds the invocation contract and the question-file format;core.tsholds every decision andrun.tsis a thin, deliberately untested shell.docs/research/: thecs2-moddingpipeline's cited stage, sitting outsideplugins/so none of it ships. ItsREADME.mdholds the conventions a research file satisfies; nothing underplugins/may reference it orSOURCES.md, andcheck-skill-content.tsfails any shipped link resolving outside the plugin directory, since existence alone passes one that works here and dead-ends for every installed user.
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.
- 2d ago First seen · 132 lines · 3,456 tokens per session scan A a4e24bf9281a
agents-plugins AGENTS.md is an instructions file published in the GitHub repository CitiesSkylinesModding/agents-plugins (5 stars, last pushed 3d ago), licensed MIT. It adds 3,456 tokens to every session, about $0.0173 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-ai-music-skills CLAUDE.md
Instructions for bitwize-music-studio/claude-ai-music-skills, covering ai music skills - claude instructions, ⚠️ critical: finding albums when user mentions them, configuration & path resolution, mcp server — preferred data access and session start.
odin-claude-plugin AGENTS.md
Instructions for OutlineDriven/odin-claude-plugin, covering output-styles edit rule [default], submodule handling, patch-bump convention, skill frontmatter and skill harness manifest.
moo.md CLAUDE.md
Instructions for saadshahd/moo.md, covering claude.md, what this is, conventions, philosophy and model-judgment boundaries.
automating-mac-apps-plugin AGENTS.md
Instructions for SpillwaveSolutions/automating-mac-apps-plugin, covering agents.md and wikiticket sdd (worklog).
claude-code-plugins AGENTS.md
Instructions for DropFan/claude-code-plugins, covering claude code plugins collection, repository structure, plugin management, development guidelines and adding a self-developed plugin.
automating-mac-apps-plugin CLAUDE.md
Instructions for SpillwaveSolutions/automating-mac-apps-plugin, covering claude.md and wikiticket sdd (worklog).