Dirac is an open-source coding agent for carrying out complex software-engineering tasks in editors, terminals, and Agent Client Protocol clients. It is used by developers who want autonomous task execution, precise codebase editing, parallel work, and control over model providers.
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 skills add dirac-run/dirac --skill delete-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/delete-tool)<a href="https://agentmods.dev/skills/dirac-run/dirac/delete-tool"><img src="https://agentmods.dev/badge/skills/dirac-run/dirac/delete-tool/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/skills/dirac-run/dirac/delete-tool"><img src="https://agentmods.dev/badge/skills/dirac-run/dirac/delete-tool.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Tool Misuse · line 70 Tool parameters are crafted to achieve unintended or unsafe behavior. Parameter abuse can bypass intended safety checks (e.g. shell=True, --force, dangerous glob patterns).Fix: Validate all tool parameters against an allowlist. Reject dangerous parameter values (shell=True, --force, -rf /) and use safe defaults.
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 | $0.00015 | $0.00722 |
| Opus 5.5 | $0.00006 | $0.00289 |
| Sonnet 5.5 | $0.00003 | $0.00144 |
| Haiku 4.5 | $0.00002 | $0.00072 |
Grade C, and why
delete-tool scanned grade C with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 1mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Recursive force deletehighDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
rm -rf <tool-directory-path> How it starts
The opening of the file, as written. The whole thing — 83 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Deleting a User-Defined Custom Tool
You are helping the user delete a custom tool that was previously created with the /new-tool command. Only user-defined tools (global or workspace scope) can be deleted — built-in tools are protected and cannot be removed.
Step 1: Discover User Tools
Scan both tool directories for user-created tools:
- Global tools —
~/.dirac/tools/(or$DIRAC_DIR/tools/ifDIRAC_DIRis set) - Workspace tools —
<workspace>/.dirac/tools/
Use list_files to enumerate subdirectories, then read_file each dirac-tool.json manifest to collect tool metadata (id, name, scope, entry).
Also read the spec from tool.ts to get the tool's description.
If no user tools are found in either location, inform the user that there are no user-defined tools to delete and stop.
Step 2: Present the Tool List
Present the discovered tools to the user grouped by scope. For each tool show:
- id (from manifest)
- name (from manifest)
- description (from tool.ts spec)
- scope (global or workspace)
- path (filesystem location of the tool directory)
Format the list clearly, for example:
**Global tools** (~/.dirac/tools/):
1. analyze_deps — Analyze project dependencies
2. format_code — Auto-format source files
**Workspace tools** (<workspace>/.dirac/tools/):
3. run_tests — Run the project test command
Use respond with operation question to let the user select which tool(s) to delete. Include a "Cancel — don't delete anything" option.
Step 3: Confirm Deletion
After the user selects one or more tools, confirm the deletion explicitly:
You are about to permanently delete the following tool(s):
run_testsfrom<workspace>/.dirac/tools/run_tests/This will remove the tool directory and all its files. This action cannot be undone. The tool will no longer load in new sessions.
Proceed?
Use respond with operation question and "Yes, delete" and "No, cancel" options.
Step 4: Delete the Tool
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.
- 1mo ago First seen · 83 lines · 15 tokens per session scan C 63e16b37c778
delete-tool is a skill published in the GitHub repository dirac-run/dirac (1,542 stars, last pushed yesterday), licensed Apache-2.0. It adds 15 tokens to every session and 722 once invoked, about $0.0001 per session on Opus 5.5. A static security scan graded it C with 1 finding (recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
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…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…