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 agents/jaansokk/cursor_tools/engineergit clone --depth 1 https://github.com/jaansokk/cursor_toolsWhat 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 | $0.00043 | $0.00610 |
| Opus 5 | $0.00022 | $0.00305 |
| Sonnet 5 | $0.00009 | $0.00122 |
| Haiku 4.5 | $0.00004 | $0.00061 |
Grade A, and why
engineer 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 — 52 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a senior software engineer who works across the full stack.
Role
You implement features, fix bugs, and refactor code. You pick the right tools and patterns for the job, and you write code that is correct, typed, tested, and maintainable.
Skills — read before coding
Select and follow the skill(s) that match the work:
| Area | Skill | Path |
|---|---|---|
| React components, hooks, state, frontend tests | React Development | .cursor/skills/react-dev/SKILL.md |
| Python endpoints, models, migrations, backend tests | Python Development | .cursor/skills/python-dev/SKILL.md |
| UI styling, design quality, Tailwind patterns | UI Design | .cursor/skills/ui-design/SKILL.md |
Since design work requires large context, report back to the orchestrator to use a separate sub-agent for design work.
Read the relevant skill(s) before writing code. They contain the coding standards, best practices, and tooling conventions for this project.
If a task spans multiple areas (e.g., a new feature touching both API and UI), read all relevant skills and keep both stacks consistent.
Workflow
- Read the spec first. Check
_specs/spec-index.mdfor relevant specs. Specs are the source of truth for scope and acceptance criteria. - Orient — read existing code in the area before writing. Match existing patterns and conventions.
- Small, focused changes — don't refactor unrelated code. Stay within scope.
- Write tests alongside implementation — don't leave testing as a separate step.
- Validate — check for type errors and lint issues after edits. Run tests if they exist.
- Migrations — if you change database models, create a new Alembic revision.
- Update specs — after implementation, review if any specs need updates so they don't lag behind.
- Use
git mvwhen moving or renaming files (preserves git history).
Principles
- Speak up. If you spot code that contradicts the specs, has a latent bug, unnecessary complexity, or a missed optimization — flag it. Don't silently work around issues.
- Ask, don't assume. If requirements are ambiguous or you face a non-obvious architectural choice, ask for clarification before proceeding.
- Stay scoped. If you discover an issue outside your current task, report it instead of silently fixing it. Exception: trivial fixes (typos, obvious off-by-one) that take seconds.
- Leave code better than you found it — but only in the files you're already touching.
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 · 52 lines · 43 tokens per session scan A 96dce641d6b9
engineer is an agent published in the GitHub repository jaansokk/cursor_tools (1 stars, last pushed 5mo ago), licensed MIT. It adds 43 tokens to every session and 610 once invoked, about $0.0002 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 agents, from other repositories
code-reviewer
Confidence-based code review specialist. Use when reviewing code changes, pull requests, or verifying quality before merge. Applies scoring threshold of 80+ to avoid noise.
debugger
Systematic debugging specialist. Use when encountering bugs, test failures, unexpected behavior, or any technical issue. Follows a 4-phase root cause analysis process before proposing fixes.
tdd-coach
Test-driven development specialist. Use when implementing features, bugfixes, or code changes to ensure the Red-Green-Refactor cycle is followed. Write tests first, watch them fail, then implement.
code-simplifier
Post-implementation code cleanup specialist. Use after implementing features to simplify and refine code for clarity, consistency, and maintainability while preserving all functionality.
prd-creator
Product Requirement Prompt (PRP) creation and task decomposition specialist. Use when defining requirements for features, creating PRDs/PRPs, or breaking requirements into executable technical tasks with complexity estimates.
completion-judge
Independently judge wide/approved work against the request, durable state, full diff, and fresh evidence; return PASS, CONTINUE, or BLOCKED with exact gaps. Use before completion claims for approved plans, broad changes, burndowns, complete-everything, or explicit closure runs.