Borrowing it
Nothing to install: this file belongs to ric03uec/clawrium. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/ric03uec/clawrium/main/.claude/skills/itx-execute/SKILL.mdgit clone --depth 1 https://github.com/ric03uec/clawriumWrote 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/ric03uec/clawrium/itx-execute)<a href="https://agentmods.dev/skills/ric03uec/clawrium/itx-execute"><img src="https://agentmods.dev/badge/skills/ric03uec/clawrium/itx-execute/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/ric03uec/clawrium/itx-execute"><img src="https://agentmods.dev/badge/skills/ric03uec/clawrium/itx-execute.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
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 →
- medium Excessive Agency · line 248 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
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 | $0.00017 | $0.07421 |
| Opus 5.5 | $0.00007 | $0.02968 |
| Sonnet 5.5 | $0.00003 | $0.01484 |
| Haiku 4.5 | $0.00002 | $0.00742 |
Grade A, and why
itx-execute scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 1mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 805 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Issue Execution
Execute the implementation plan for a GitHub issue.
Orchestrate Mode
Triggered by orchestrate as the first token in arguments
(e.g. /itx-execute orchestrate 112). Use when the issue is a parent
with linked subtasks and you want a hands-off, stacked-PR pipeline
across all subtasks.
Preconditions
- Parent issue exists and has sub-issues linked (via GitHub
addSubIssue). Detect via:gh issue view <parent> --json title,body,labels && \ gh api graphql -f query='query($owner: String!, $repo: String!, $num: Int!) { repository(owner: $owner, name: $repo) { issue(number: $num) { subIssues(first: 50) { nodes { number title state } } } } }' -f owner="$OWNER" -f repo="$REPO" -F num=<parent> tmuxavailable on the host. If not, fail with a clear message — orchestrate mode requires tmux.- The
claudeCLI is available (command -v claude). Check this before creating a tmux session, branch, or worktree; fail clearly if it is missing. - A plan file exists at
.itx/<parent>/00_PLAN.md(created by/itx-plan-create). Refuse to start otherwise.
ATX availability is not a precondition. Children use the
fallback chain in ATX Review below. Handoff is still keyed on
PR-open — without ATX, that just means the child opens the PR after
local make test + make lint pass instead of after an ATX rating
clears.
Orchestration contract
Orchestrate mode and the tmux-backed standalone worktree path are currently
Claude Code-specific even when this skill is invoked from another harness.
They launch child sessions through the claude CLI; selecting the active
harness for child execution is outside this workflow's current contract.
The orchestrator does only these things:
- Creates worktrees + branches + tmux windows for each subtask.
- Spawns a child claude session per subtask via
claude --dangerously-skip-permissions '/itx-execute <N>'in the subtask's worktree. - Polls subtask PR state every ~5 minutes.
- When a subtask's PR appears (the child's handoff signal), spawns the next subtask with the correct stacked base.
- Surfaces stuck children (PRs carrying
[ITX-STUCK]) in the end-of-run summary table, but does not halt the pipeline waiting for user input — see "Stuck child" below.
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 Changed · -13 lines 5b3ca51a9b71
- 1mo ago Changed · +51 lines 41b402a8a420
- 1mo ago Changed · -1 lines 1f5aae314a72
- 2mo ago First seen · 768 lines · 17 tokens per session scan A c7d82a14a866
itx-execute is a skill published in the GitHub repository ric03uec/clawrium (67 stars, last pushed 13d ago), licensed Apache-2.0. It adds 17 tokens to every session and 7,421 once invoked, about $0.0001 per session on Opus 5.5. 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
python
Use when the task is Python itself, in any framework or none: PEP 695 generics, mypy --strict typing, dataclass/Protocol/TypedDict/Enum choices, asyncio.TaskGroup, stdlib idioms, src/ layout + pyproject.toml with uv, ruff+mypy+pytest gate. NOT a FastAPI/ASGI service (that is fastapi), NOT a deep pytest suite (that is…
dd-code-generation
Use pup CLI for immediate Datadog operations or generate code for integration into applications.
telegram
Telegram Bot skill for sending and editing Telegram messages via Bot API. Use when Bub needs to: (1) Send a message to a Telegram user/group/channel, (2) Reply to a specific Telegram message with replytomessageid, (3) Edit an existing Telegram message, or (4) Push proactive Telegram notifications. Prefer rich…
gh
GitHub CLI skill for interacting with GitHub via the gh command line tool. Use when Bub needs to (1) Create, view, or manage GitHub repositories, (2) Work with issues and pull requests, (3) Create and manage releases, (4) Run and monitor GitHub Actions workflows, (5) Create and manage gists, (6) Install and manage…
modern-python-toolchain
Modern Python project setup with uv, ruff, and pyright. Use when initializing a new Python project, configuring the Python environment, setting up linting/formatting, or when a project needs uv (the fast Python package manager). Trigger on: 'set up Python', 'new Python project', 'configure uv', 'install uv', 'ruff'…
sync-check
Walks the documentation dependency web after a CLI code change and reports which downstream files (skills, SOPs, READMEs, plugin references) are out of sync. Use after fixing a bug, adding a command, changing auth behavior, refactoring, or before committing — and when the user says "sync check", "update docs"…