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 rules/coddy-project/coddy-agent/core-modulesgit clone --depth 1 https://github.com/coddy-project/coddy-agentWhat 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 | $0.00000 | $0.00878 |
| Opus 5 | $0.00000 | $0.00439 |
| Sonnet 5 | $0.00000 | $0.00176 |
| Haiku 4.5 | $0.00000 | $0.00088 |
Grade A, and why
core-modules 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 — 23 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Core modules (sketch)
internal/acp- ACP RPC server, session lifecycle from editors.internal/agent- tool loop and LLM turns.internal/session- session manager and mode (agent/plan).internal/config- YAML and flags.internal/tools- filesystem, shell, todo, MCP merge, etc. Shell also owns the background task family (run_commandbackground: trueplusbackground_list/background_output/background_wait/background_stop), backed byinternal/bgtask. Seedocs/background-tasks.md.internal/mcp- MCP transports (client.go,remote.go,connect.go), the merged server list with scope/origin labels (manage.go), and the workspace trust gate for project-local.coddy/mcp.json(trust.go,gate.go). That file arrives with the checkout, so its declarations are not started or contacted until the operator approves that exact declaration for that workspace: policymcp.project_trust(askdefault /allow/deny), approvals in<home>/mcp-trust.jsonkeyed by canonical workspace + declaration digest. Every connect or probe of a configured server must go throughTrustGate.Connect/TrustGate.Probe(they re-check immediately before the spawn);mcp.Connectdirectly is only for ACP client-supplied servers. Approval surfaces:coddy mcp list|trust|untrust,POST /coddy/mcp/{name}/trust|untrust, Settings → MCP servers. Seedocs/mcp-integration.md.internal/bgtask- process-wide, session-scoped pool for work that outlives a tool call. A task is whatever aRunnerstarts;CommandRunneris the only implementation today andKindAgentis reserved for a future nested-agent runner, so that lands as a secondRunnerrather than a second scheduling mechanism.internal/skills- skill loading, enable/disable (loader.go,disabled.go), and remote install from repos / agents-standard marketplaces (remote.go,manifest.go,plugin.go:Sync/SyncSource(all or one source),AddSource,RemoveRemote/DeleteSkill(delete any on-disk skill; bundled = read-only viaSkillReadonly),ListSources,RemoveSource,CheckUpdates,UpdateSkill; git clone viainternal/gitws.Clone/Pull, materialized into${CODDY_HOME}/skillswith a.remote.jsonlockfile that records each skill's installedversion). Marketplace pluginversion(andSKILL.mdfrontmatterversion) are surfaced byInstalledVersionand drive update detection (compareVersions). Default dirs:~/.agents/skills(global, shared withnpx skills/npx skillsbd),~/.coddy/skills(coddy-specific),${CWD}/.coddy/skills(project-local). Remote sources are listed inskills.sourcesand fetched only on demand. Management parity across the CLI (coddy skills add|sync|remove,coddy plugin marketplace list|add|remove|sync,coddy plugin install|remove|enable|disable), the built-in/pluginchat command (internal/agent/plugin_command.go, deterministic like/compact; shared dispatcherskills.RunPluginCommand/MarketplaceStatusinplugin.go), HTTP (/coddy/skills/*), and the Settings → Skills UI. Seedocs/skills.md.
Prefer extending these over growing cmd/ or duplicating logic in external/.
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 · 23 lines · 0 tokens per session scan A 00779e5d3e47
core-modules is a cursor rule published in the GitHub repository coddy-project/coddy-agent (127 stars, last pushed 3d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 878 tokens. 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 2026-08-30.
Other cursor rules, from other repositories
lean
The smallest working change. Efficiency is not carelessness. Active during delivery in the aiops bundle; off during grill/alignment.
use-bun-instead-of-node-vite-npm-pnpm
../../CLAUDE.md.
angular-20
This rule provides comprehensive best practices and coding standards for Angular development, focusing on modern TypeScript, standalone components, signals, and performance optimizations.
dev-standard
Apache Superset development standards and guidelines for Cursor IDE.
typescript
Changes to these high-fan-out internals can affect every message, delta, element, or rerun. Keep work in them minimal, and benchmark changes with representative stress-test apps.
coolify-ai-docs
Master reference to all Coolify AI documentation in .ai/ directory.