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.
git clone --depth 1 https://github.com/neuromechanist/research-skillsWrote 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/commands/neuromechanist/research-skills/init-project)<a href="https://agentmods.dev/commands/neuromechanist/research-skills/init-project"><img src="https://agentmods.dev/badge/commands/neuromechanist/research-skills/init-project/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/commands/neuromechanist/research-skills/init-project"><img src="https://agentmods.dev/badge/commands/neuromechanist/research-skills/init-project.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00011 | $0.00889 |
| Opus 5 | $0.00005 | $0.00445 |
| Sonnet 5 | $0.00002 | $0.00178 |
| Haiku 4.5 | $0.00001 | $0.00089 |
Grade A, and why
init-project 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 10d 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 — 73 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Project Initialization with Vibe Rules
Initialize this project using bundled vibe-rules templates from the init-project plugin.
Setup Process:
1. Analyze Current Project
!echo "Project description: $ARGUMENTS" !pwd !ls -la
2. Copy templates and set up project structure
!project-init-templates .
If the above command failed, report the exact error to the user and stop. Do not proceed with remaining steps.
3. Track agent files in git
AGENTS.md, CLAUDE.md, .rules/, and .context/ (including .context/decisions/) are tracked in git by default. Add to .gitignore only if explicitly requested by the user. The .context/decisions/ directory holds Architecture Decision Records; copy 0000-template.md to start a new ADR.
4. Customize AGENTS.md based on project context
Now analyze the project and customize the AGENTS.md file using the project description provided by the user: $ARGUMENTS
- Replace template placeholders: {{PROJECT_NAME}} with the project name, {{framework}} with the detected framework
- Use
$ARGUMENTSas the project purpose in the "Project Context" section - Add project-specific instructions based on detected language/framework
- Update .rules/ contents to match project needs; remove irrelevant rules
- Update .context/ files with project requirements; keep minimal instructions for unused files
- Keep CLAUDE.md as
@AGENTS.mdfollowed only by Claude Code-specific plugin, skill, command, or MCP instructions - Re-read AGENTS.md and CLAUDE.md to ensure only relevant context and rules are referenced
!if [ -f "package.json" ]; then echo "Detected: Node.js/JavaScript project"; fi !if [ -f "requirements.txt" ] || [ -f "pyproject.toml" ] || [ -f "setup.py" ]; then echo "Detected: Python project"; fi !if [ -f "Cargo.toml" ]; then echo "Detected: Rust project"; fi !if [ -f "go.mod" ]; then echo "Detected: Go project"; fi
5. Cursor setup (optional)
If the user also uses Cursor, offer to set up Cursor templates.
Use project-templates-path to locate the templates directory, then copy:
- .cursorrules from
<templates>/cursor/ - core_rules/ .mdc files
- Planning workflow (default or advanced-taskmaster based on preference)
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.
- 10d ago First seen · 73 lines · 11 tokens per session scan A 54ed33aefaff
init-project is a command published in the GitHub repository neuromechanist/research-skills (45 stars, last pushed 8d ago), licensed BSD-3-Clause. It adds 11 tokens to every session and 889 once invoked, about $0.0001 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.
Other commands, from other repositories
design-plan
Generate a concrete design system (tokens, style, type, UX) before building UI.
design-review
Run the 7-phase design review (WCAG AA, responsive, interaction) on a page or URL.
audit-checklist
Perform an internal audit, review controls, or prepare for an external financial audit.
production-orchestrator
Deployment commander. Pipeline conductor. Quality gate enforcer.
brainstorm-divergent
Generate genuinely different ideas across the solution space, then converge on the strongest few.
gentle-sdd-init
Initialize SDD context — detects project stack and bootstraps persistence backend.