Debug
asgeirtj/system_prompts_leaks
Enable debug logging for this session and help diagnose issues
Debug and validate runnable TIRx kernels by selecting and executing the applicable correctness tools.
No licenceAuto-check passed
Install Tirx Debug Kernel
$ npx skills add mlc-ai/TIRx-harness --skill tirx-debug-kernel -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install mlc-ai/TIRx-harness tirx-debug-kernel --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/mlc-ai/TIRx-harness.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/tirx-debug-kernel .claude/skills/tirx-debug-kernel && rm -rf skills-srcUse ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.
Claude Code skills documentation · loads skills from .claude/skills/
Install the "tirx-debug-kernel" agent skill from https://github.com/mlc-ai/TIRx-harness/tree/main/skills/tirx-debug-kernel into .claude/skills/tirx-debug-kernel/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "tirx-debug-kernel", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/mlc-ai/TIRx-harness/tree/main/skills/tirx-debug-kernelType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add mlc-ai/TIRx-harness --skill tirx-debug-kernel -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install mlc-ai/TIRx-harness tirx-debug-kernel --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/mlc-ai/TIRx-harness.git skills-src && mkdir -p .agents/skills && cp -r skills-src/skills/tirx-debug-kernel .agents/skills/tirx-debug-kernel && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "tirx-debug-kernel" agent skill from https://github.com/mlc-ai/TIRx-harness/tree/main/skills/tirx-debug-kernel into .agents/skills/tirx-debug-kernel/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "tirx-debug-kernel", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add mlc-ai/TIRx-harness --skill tirx-debug-kernel -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install mlc-ai/TIRx-harness tirx-debug-kernel --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/mlc-ai/TIRx-harness.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/skills/tirx-debug-kernel .cursor/skills/tirx-debug-kernel && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "tirx-debug-kernel" agent skill from https://github.com/mlc-ai/TIRx-harness/tree/main/skills/tirx-debug-kernel into .cursor/skills/tirx-debug-kernel/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "tirx-debug-kernel", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/mlc-ai/TIRx-harness.git --path skills/tirx-debug-kernel--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add mlc-ai/TIRx-harness --skill tirx-debug-kernel -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install mlc-ai/TIRx-harness tirx-debug-kernel --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/mlc-ai/TIRx-harness.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/skills/tirx-debug-kernel .gemini/skills/tirx-debug-kernel && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "tirx-debug-kernel" agent skill from https://github.com/mlc-ai/TIRx-harness/tree/main/skills/tirx-debug-kernel into .gemini/skills/tirx-debug-kernel/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "tirx-debug-kernel", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install mlc-ai/TIRx-harness tirx-debug-kernelInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add mlc-ai/TIRx-harness --skill tirx-debug-kernel -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/mlc-ai/TIRx-harness.git skills-src && mkdir -p .github/skills && cp -r skills-src/skills/tirx-debug-kernel .github/skills/tirx-debug-kernel && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "tirx-debug-kernel" agent skill from https://github.com/mlc-ai/TIRx-harness/tree/main/skills/tirx-debug-kernel into .github/skills/tirx-debug-kernel/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "tirx-debug-kernel", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add mlc-ai/TIRx-harness --skill tirx-debug-kernel -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install mlc-ai/TIRx-harness tirx-debug-kernel --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/mlc-ai/TIRx-harness.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/skills/tirx-debug-kernel .opencode/skills/tirx-debug-kernel && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "tirx-debug-kernel" agent skill from https://github.com/mlc-ai/TIRx-harness/tree/main/skills/tirx-debug-kernel into .opencode/skills/tirx-debug-kernel/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "tirx-debug-kernel", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
Facts
- Skill name
tirx-debug-kernel- GitHub stars
- 119
- Token cost
- ~1k tokens
- SKILL.md length
- 512 words
- Files
- 6 (incl. references)
- Skills in repo
- 3
- Repo updated
- First seen
- Licence
- None found
At a glance
Debug and validate runnable TIRx kernels by selecting and executing the applicable correctness tools.
- Works in 3 steps: Run every applicable checker first.… → If a numerical mismatch remains, run… → Escalate to the workload's normal GPU…
- Produces suspect results
- SKILL.md covers Default order, Tool routing, Workflow and Report tool defects, plus 1 more section
- Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md
What it does
Tirx Debug Kernel is an agent skill from mlc-ai/TIRx-harness. Debug and validate runnable TIRx kernels by selecting and executing the applicable correctness tools. Use whenever a kernel fails, produces suspect results, or a code change needs evidence about synchronization, memory safety, or numerical behavior.
Its SKILL.md is about 1k tokens, which your agent loads only when the skill is triggered. The skill folder holds 7 other files, including reference files (for example `agents/openai.yaml`, `references/compute-sanitizer.md` and `references/numsim.md`).
The repository describes itself as: An Open Compiler Harness for Agentic GPU Programming.
When your agent uses it
- Produces suspect results
- A code change needs evidence about synchronization
- Numerical behavior
Example prompts
- “/tirx-debug-kernel”
Requirements
- Python 3
Workflow steps
3 steps, taken from the first numbered list in SKILL.md.
- Run every applicable checker first. Synccheck and Racecheck do not reserve a
- If a numerical mismatch remains, run NumSim on the smallest representative
- Escalate to the workload's normal GPU correctness check. If Synccheck or
What it can do on your machine
Read from SKILL.md and the folder at commit 6449c3d. It shows what the files ask for, not the result of running them.
Tool permissions
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Runs code
No scripts in the folder and no shell commands in SKILL.md.
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md.
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Context cost
Tirx Debug Kernel loads about 1k tokens when it runs, and up to ~3.8k if it reads all its reference files. Until then it costs about 67 tokens; SKILL.md has 512 words of instructions outside code blocks.
Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.
Safety
Auto-check passed
The automated check found no risky patterns in SKILL.md.
Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.
SKILL.md
Without a licence we can't republish the file, so here is its outline and opening line. It has 512 words (~1,003 tokens).
“Use correctness tools to investigate the kernel. Reading a tool guide or suggesting a command is not a substitute for running the tool when a runnable case is available.”
- name
- tirx-debug-kernel
Files
SKILL.md and 5 other files (references) in skills/tirx-debug-kernel of mlc-ai/TIRx-harness.
- SKILL.md
- agents/openai.yaml
- references/compute-sanitizer.md
- references/numsim.md
- references/racecheck.md
- references/synccheck.md
Open the folder on GitHubat commit 6449c3d
Compare with similar skills
Tirx Debug Kernel next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Tirx Debug Kernel this skillmlc-ai/TIRx-harness | 119 | — | ~1k | Automated safety check: Pass | None | |
| Debugasgeirtj/system_prompts_leaks | 69k | — | ~439 | Automated safety check: Pass | CC0-1.0 | |
| Debug Sandbox ExecutionHKUDS/OpenSpace | 7.7k | — | ~843 | Automated safety check: Pass | MIT | |
| Python Debug Execution 911f17HKUDS/OpenSpace | 7.7k | — | ~892 | Automated safety check: Pass | MIT | |
| Python Debug ExecutionHKUDS/OpenSpace | 7.7k | — | ~662 | Automated safety check: Pass | MIT | |
| Debugging Toolkitsickn33/agentic-awesome-skills | 47k | 1 repos | ~344 | Automated safety check: Pass | MIT |
Similar skills
Debug Sandbox Execution
HKUDS/OpenSpace
Debug Python code execution failures by capturing partial traces, isolating failing functions, and incrementally verifying outputs
Python Debug Execution 911f17
HKUDS/OpenSpace
Debug Python script execution failures by capturing full tracebacks and verifying working directory
Python Debug Execution
HKUDS/OpenSpace
Debug Python scripts with proper error surfacing and working directory verification
Debugging Toolkit
sickn33/agentic-awesome-skills
A skill your agent uses when working with debugging toolkit smart debug (Alias for debugging-toolkit-smart-debug)
Debugging Code
sickn33/agentic-awesome-skills
Interactively debug source code — set breakpoints, step through execution line by line, inspect live variable state, evaluate expressions against the running program, and navigate the call stack to…
More from mlc-ai/TIRx-harness
Tirx Wiki
mlc-ai/TIRx-harness
Authoritative reference for TIRx-lite authoring on TIRx: TIRx-lite APIs, canonical kernels, optimization guidance, PTX ISA, and GPU references.
Tirx Profile Kernel
mlc-ai/TIRx-harness
Profile and optimize runnable TIRx kernels by selecting and executing the applicable measurement and analysis tools.
Questions about Tirx Debug Kernel
What does Tirx Debug Kernel do?
Debug and validate runnable TIRx kernels by selecting and executing the applicable correctness tools. Tirx Debug Kernel is an agent skill from mlc-ai/TIRx-harness. Debug and validate runnable TIRx kernels by selecting and executing the applicable correctness tools.
When should I use Tirx Debug Kernel?
Tirx Debug Kernel fits situations like: produces suspect results; A code change needs evidence about synchronization; numerical behavior.
How do I install Tirx Debug Kernel in Claude Code?
Run `npx skills add mlc-ai/TIRx-harness --skill tirx-debug-kernel -a claude-code`. Or copy the skill folder (skills/tirx-debug-kernel in mlc-ai/TIRx-harness) into .claude/skills/tirx-debug-kernel in your project. Claude Code loads it when a task matches its description.
How do I install Tirx Debug Kernel in Codex?
Run `npx skills add mlc-ai/TIRx-harness --skill tirx-debug-kernel -a codex`. Or copy the skill folder (skills/tirx-debug-kernel in mlc-ai/TIRx-harness) into .agents/skills/tirx-debug-kernel in your project. Codex loads it when a task matches its description.
Can I use Tirx Debug Kernel in Cursor, Gemini CLI or GitHub Copilot?
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add mlc-ai/TIRx-harness --skill tirx-debug-kernel -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/tirx-debug-kernel, .gemini/skills/tirx-debug-kernel, .github/skills/tirx-debug-kernel and .opencode/skills/tirx-debug-kernel in your project.
What does Tirx Debug Kernel need to run?
SKILL.md names no scripts, command-line tools or credentials: Tirx Debug Kernel is instructions for the agent only. Our summary lists: Python 3.
Does Tirx Debug Kernel access the network?
SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.
Is Tirx Debug Kernel safe to install?
Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.
What licence does Tirx Debug Kernel use?
No licence was found for Tirx Debug Kernel or its repository. Without one, default copyright applies: ask the author before reusing or redistributing it.
How many tokens does Tirx Debug Kernel use?
About 1k tokens (SKILL.md is roughly 4k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 2.8k tokens, read only when the agent opens those files.
What are the alternatives to Tirx Debug Kernel?
Skills that share tags, products or a category with Tirx Debug Kernel: Debug (asgeirtj/system_prompts_leaks, 69k stars), Debug Sandbox Execution (HKUDS/OpenSpace, 7.7k stars), Python Debug Execution 911f17 (HKUDS/OpenSpace, 7.7k stars) and Python Debug Execution (HKUDS/OpenSpace, 7.7k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Tirx Debug Kernel?
mlc-ai (a GitHub organization) maintains it in mlc-ai/TIRx-harness, which has 119 GitHub stars. The repository holds 3 skills in this directory. The repository was last updated on October 6, 2026.
Source: mlc-ai/TIRx-harness on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.