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 skills/dirac-run/dirac/new-toolnpx skills add dirac-run/dirac --skill new-toolgit clone --depth 1 https://github.com/dirac-run/diracWrote 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/skills/dirac-run/dirac/new-tool)<a href="https://agentmods.dev/skills/dirac-run/dirac/new-tool"><img src="https://agentmods.dev/badge/skills/dirac-run/dirac/new-tool.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 | $0.00017 | $0.00473 |
| Opus 5 | $0.00009 | $0.00236 |
| Sonnet 5 | $0.00003 | $0.00095 |
| Haiku 4.5 | $0.00002 | $0.00047 |
Grade A, and why
new-tool 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
Creating a New Custom Tool
You are creating a new custom tool for Dirac. The request may come directly from the user, or you may identify that a reusable tool would help accomplish the task.
Step 1: Gather Requirements
Use requirements already established by the task and conversation. Ask the user only for details that are genuinely missing or ambiguous. If the requirements are clear, proceed without an interview.
- Tool name — a
snake_caseidentifier (e.g.run_tests,format_code,analyze_deps). - Description — what the tool does, shown to the LLM.
- Parameters — for each input the tool needs:
- Name (
snake_case) - Type (
string|boolean|integer|array|object) - Required or optional
- Instruction text for the LLM
- Name (
- Scope — where should the tool live?
- Global (
~/.dirac/tools/): available in every workspace - Workspace (
<workspace>/.dirac/tools/): available only in this project - Task (
<task storage>/tools/): available only for this task, survives task resume
- Global (
- Requirements — any specific behavior, logic, edge cases, or env traits the tool should use.
Step 2: Create the Tool with upsert_tool
Call the upsert_tool tool with the gathered information. It handles code generation, compilation, validation, and smoke testing internally.
Step 3: Handle Results
- Success (
✓): proceed to Step 4. - Failure (
❌): read the error, adjust the requirements, and callupsert_toolagain.
Step 4: Inform the User
Tell the user:
- Global and workspace tools appear in the Tools tab and default to disabled until enabled.
- Task-scoped tools are automatically available for this task and persist across task resume.
- Enabled tools are available to the main agent and to subagents whose allowlist includes the tool id/name.
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 · 42 lines · 17 tokens per session scan A 27633fc0696d
new-tool is a skill published in the GitHub repository dirac-run/dirac (1,473 stars, last pushed yesterday), licensed Apache-2.0. It adds 17 tokens to every session and 473 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 skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
brainstorming
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
auto-perf-optimize
Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.
chat-perf
Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…