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/kastalien-research/thoughtbox/claude-mdgit clone --depth 1 https://github.com/Kastalien-Research/thoughtboxWrote 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/kastalien-research/thoughtbox/claude-md)<a href="https://agentmods.dev/instructions/kastalien-research/thoughtbox/claude-md"><img src="https://agentmods.dev/badge/instructions/kastalien-research/thoughtbox/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 | $0.01297 | $0.01297 |
| Opus 5 | $0.00648 | $0.00648 |
| Sonnet 5 | $0.00259 | $0.00259 |
| Haiku 4.5 | $0.00130 | $0.00130 |
Grade B, and why
thoughtbox CLAUDE.md scanned grade B with 1 finding 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.
Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
Hub coordination (workspaces, problems, proposals, channels) is exposed over MCP as `tb.hub.*` inside `thoughtbox_execute` (SPEC-V1-INITIATIVE Phase 4.1). Call `tb.hub.register({ name })` or `tb.hub.quickJoin({ name, wor How it starts
The opening of the file, as written. The whole thing — 133 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Claude Code Instructions
@AGENTS.md
CRITICAL: Always Verify
NEVER say "probably", "maybe", "might be", "could be", or other conditional hedging.
Before making ANY claim about:
- Whether a file exists
- Whether code is present
- Whether a feature works
- Whether something was done
You MUST verify it first using the appropriate tool (Read, Glob, Grep, Bash, etc.).
Do NOT:
- Assume something exists without checking
- Claim something works without testing
- Say "it should be there" without reading the file
- Trust previous agents' claims without verification
DO:
- Read files before claiming they contain something
- Run tests before claiming they pass
- Check directory contents before claiming files exist
- Verify configurations before claiming they're correct
Commit Message Format (REQUIRED)
This project uses Conventional Commits
When creating commits, you MUST use this format:
<type>[optional scope]: <description>
[optional body]
Quick Reference
Types (use these exactly):
feat: New feature → CHANGELOG Added sectionfix: Bug fix → CHANGELOG Fixed sectionperf: Performance improvement → CHANGELOG Changed sectionrefactor: Code refactor → CHANGELOG Changed sectiondocs: Documentation only → Omitted from CHANGELOGtest: Tests only → Omitted from CHANGELOGchore: Maintenance/tooling → Omitted from CHANGELOGsecurity: Security fix → CHANGELOG Security sectionbreakingor add!: Breaking change → MAJOR version bump
Examples
# New feature
feat(loops): Add OODA loops MCP integration
# Bug fix
fix(analytics): Resolve concurrent write issue in loop-usage.jsonl
# Breaking change (note the !)
feat!: Remove deprecated thoughtbox_v1 tool
# With scope
perf(catalog): Cache hot-loops.json for faster sorting
# Documentation (not in changelog)
docs: Update README with loops documentation
Why This Matters
- Automated changelog: Commits automatically populate CHANGELOG.md
- Semantic versioning: Commit types determine version bumps
- Clear history: Easy to see what changed and why
- PR quality: GitHub Action validates format
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 · 133 lines · 1,297 tokens per session scan B cc55b2dcd345
thoughtbox CLAUDE.md is an instructions file published in the GitHub repository Kastalien-Research/thoughtbox (64 stars, last pushed 1mo ago), licensed MIT. It adds 1,297 tokens to every session, about $0.0065 per session on Opus 5. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.
Other instructions, from other repositories
hop CLAUDE.md
Instructions for danmartuszewski/hop: Use conventional commit format with imperative mood.
room AGENTS.md
Instructions for quoroom-ai/room, covering begin vasily global shortcuts, global shortcut commands (from /cloud/claude.md), keyboard layout recovery, c = commit and push (no build) and cd = commit, push, build (full).
deploystack copilot-instructions.md
Copilot instructions for deploystackio/deploystack, covering github copilot instructions for deploystack, project context, commit message requirements, required scopes and scope selection rules.
drawio-mcp git-style.instructions.md
Instructions for yohasacura/drawio-mcp, covering git style guide, commit messages, structure, type and scope.
mcp-walmart-marketplace AGENTS.md
AGENTS.md instructions for alyiox/mcp-walmart-marketplace, covering agent instructions, commit messages, header, body and release tags.
seekstone CLAUDE.md
Instructions for shaqmughal/seekstone, covering claude.md, what this repo is, commands, the harness itself (run after npm install) and architecture.