agentmods.dev

silo CLAUDE.md

Project instructions for Claude Code working on Silo, a desktop app for managing coding workspaces across projects.

In plain words
What is it for?
Use them when Claude Code is working on Silo, especially for testing, documentation updates, and modeling the project’s domain concepts.
Why use it?
They explain how Claude Code finds and runs the project’s skills, including the difference between the shared skill files and their Claude Code links. This helps the agent use the repository’s intended workflows.

Instructions file

53 yesterday A scan 401 tokens original MIT
View the source file silo-code/silo
Install

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.

agentmods
npx agentmods add instructions/silo-code/silo/claude-md
Clone the repo
git clone --depth 1 https://github.com/silo-code/silo
Per session 401 This file is loaded in full into every session.
When invoked 401 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00401 $0.00401
Opus 5 $0.00200 $0.00200
Sonnet 5 $0.00080 $0.00080
Haiku 4.5 $0.00040 $0.00040

Measured yesterday against content hash 3bff791bd059, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

silo CLAUDE.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.

CLAUDE.md · 26 lines

What it actually says

@AGENTS.md

Claude Code

  • The workflows referenced above under .agents/skills/*/SKILL.md (silo-testing, silo-docs-sync, silo-domain-modeling) are registered Claude Code skills — invoke them via the Skill tool rather than reading them manually; Claude Code also surfaces them proactively when a task matches their description. Claude Code only discovers skills under .claude/skills/, not the canonical .agents/skills/ (the Codex-native, agentskills.io-spec-aligned location) — each skill's real content lives in .agents/skills/<name>/, and .claude/skills/<name> is a symlink to it, so both tools read the same file with nothing to keep in sync.
  • silo-domain-modeling is a repo-local fork of the personal domain-modeling skill, adapted to this repo's actual doc layout and format (docs/domain-language.md, docs/decisions/, docs/proposals/), rather than that skill's generic CONTEXT.md/docs/adr/ defaults.
  • Other externally-installed skills: improve-codebase-architecture and grill-with-docs (from mattpocock/skills) still hardcode CONTEXT.md and docs/adr/ in their own instructions and have no concept of docs/proposals/ (RFCs). When running them: treat docs/adr/ as docs/decisions/ (read/write there, continuing the existing numbering — never create a separate docs/adr/ directory), and CONTEXT.md as docs/domain-language.md. Don't expect either skill to read or write docs/proposals/.
Changes

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.

  1. yesterday First seen · 26 lines · 401 tokens per session scan A 3bff791bd059

Subscribe to this mod's changes

silo CLAUDE.md is an instructions file published in the GitHub repository silo-code/silo (53 stars, last pushed yesterday), licensed MIT. It adds 401 tokens to every session, about $0.0020 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 2026-08-30.

TestingWriting and docsclaude-codecodexeditorgeminiopencodeterminal
Related

Other instructions, from other repositories

agtx AGENTS.md

Instructions for fynnfluegge/agtx, covering agents.md, what is agtx?, build & test, key architecture and core concepts.

fynnfluegge/agtx · 580 tokens

agtx CLAUDE.md

Instructions for fynnfluegge/agtx, covering agtx - terminal kanban for coding agents, quick start, build, run in a git project directory and or run in dashboard mode (no git project required).

fynnfluegge/agtx · 17,156 tokens

cmux CLAUDE.md

Claude Code instructions for manaflow-ai/cmux, covering cmux agent notes, setup, build and reload, shared mac fleet capacity and tag-bound debug cli.

manaflow-ai/cmux · 4,115 tokens

opencode-bar AGENTS.md

Instructions for opgginc/opencode-bar, covering important restriction, coding rules, branding guides, ui styling rules and explicit 'used' or 'left'.

opgginc/opencode-bar · 11,821 tokens

superset AGENTS.md

AGENTS.md instructions for superset-sh/superset, covering superset monorepo, project structure, exception: shadcn/ui components, database and releases.

superset-sh/superset · 2,316 tokens

cmux AGENTS.md

AGENTS.md instructions for manaflow-ai/cmux, a project described as: Open source Ghostty-based macOS terminal with vertical tabs and notifications for AI coding agents. Built for multitasking, organization, and programmability.

manaflow-ai/cmux · 4 tokens