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/foundry-works/foundry-research/claude-mdgit clone --depth 1 https://github.com/foundry-works/foundry-researchWrote 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/foundry-works/foundry-research/claude-md)<a href="https://agentmods.dev/instructions/foundry-works/foundry-research/claude-md"><img src="https://agentmods.dev/badge/instructions/foundry-works/foundry-research/claude-md.svg" alt="Measured on agentmods" 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 | $0.00396 | $0.00396 |
| Opus 5 | $0.00198 | $0.00198 |
| Sonnet 5 | $0.00079 | $0.00079 |
| Haiku 4.5 | $0.00040 | $0.00040 |
Grade A, and why
foundry-research 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 4d 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.
What it actually says
Foundry Research
Plugin Development
This repo is a Claude Code plugin. Edit files in skills/ and agents/ directly — they are the plugin source.
- Local testing:
claude --plugin-dir .from the repo root - Reload after changes:
/reload-pluginsin the session - Skill invocation:
/foundry-research:deep-research,/foundry-research:reflect,/foundry-research:improve,/foundry-research:deep-research-revision
Plugin Gotchas
- hooks.json uses a nested format. Each event entry wraps commands in a
hooksarray:{"hooks": {"SessionStart": [{"hooks": [{"type": "command", "command": "..."}]}]}}. This differs from.claude/settings.jsonhook format — don't confuse them. - Agent frontmatter cannot include
permissionMode,hooks, ormcpServers. These are blocked for plugin-shipped agents. - Bump
versioninplugin.jsonafter changes. Installed plugins cache by version — edits won't reach users until the version changes. agents,skills, andhooksinplugin.jsonoverride defaults. If omitted, the defaultagents/,skills/, andhooks/hooks.jsonare auto-discovered. Only set them explicitly if you need custom paths. Do not pointhooksathooks/hooks.json— it loads automatically and declaring it again causes a duplicate error.- All paths in
plugin.jsonmust start with./and be relative to the repo root.
Design Principles
Read PRINCIPLES.md before developing new plans or proposing changes to skills and agents. It captures the design philosophy for this project — use it to evaluate whether proposed improvements align with how we build.
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.
- 4d ago First seen · 22 lines · 396 tokens per session scan A a5e8c949d20b
foundry-research CLAUDE.md is an instructions file published in the GitHub repository foundry-works/foundry-research (2 stars, last pushed 4mo ago), licensed MIT. It adds 396 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 2026-08-31.
Other instructions, from other repositories
skills CLAUDE.md
Instructions for ananthanandanan/skills, covering claude.md, what this repo is, install paths (both supported), repo layout (load-bearing) and reference artifact.
team-of-agents CLAUDE.md
Instructions for pranav8494/team-of-agents, covering claude.md, project rules for ai assistants and git commits.
gaia-skill-heaven CLAUDE.md
Claude Code instructions for gaia-research/gaia-skill-heaven, covering claude.md — gaia-skill-heaven, what this is, layout, commands and rule 0 — lifted (owner ruling, 2026-08-19).
recursive-decomposition-skill AGENTS.md
Instructions for massimodeluisa/recursive-decomposition-skill, covering agents: recursive-decomposition skill, read these first (mandatory), language policy, non-negotiables and commands.
lead-dev-os CLAUDE.md
Instructions for CaptainMe-AI/lead-dev-os, covering claude.md, project, terminology, plugin architecture and repository structure.
embedded-systems-architect AGENTS.md
Instructions for Zachariah9420/embedded-systems-architect: This repository ships an agent skill for embedded-systems and edge-AI development work.