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/ric03uec/clawrium/itx-executenpx skills add ric03uec/clawrium --skill itx-executegit 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.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 | $0.06792 |
| Opus 5 | $0.00009 | $0.03396 |
| Sonnet 5 | $0.00003 | $0.01358 |
| Haiku 4.5 | $0.00002 | $0.00679 |
Grade A, and why
itx-execute scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured today.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 767 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Issue Execution
Execute the implementation plan for a GitHub issue.
Orchestrate Mode
Triggered by orchestrate as the first token in arguments
(e.g. /itx-execute orchestrate 112). Use when the issue is a parent
with linked subtasks and you want a hands-off, stacked-PR pipeline
across all subtasks.
Preconditions
- Parent issue exists and has sub-issues linked (via GitHub
addSubIssue). Detect via:gh issue view <parent> --json title,body,labels && \ gh api graphql -f query='query($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.- 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
The orchestrator (the claude session that runs orchestrate mode) 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.
The orchestrator does NOT:
- Touch source code.
- Run tests / lint directly.
- Merge PRs. Merging is the user's decision.
- Block on user input. If something requires a decision, the child records it as a Callout on its PR and proceeds.
- Bypass ATX when ATX is available; bypass
--no-verify. - Spawn all subtask windows up front. Windows are created on demand when the predecessor's PR is open.
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.
- today Changed · -1 lines 1f5aae314a72
- 5d ago First seen · 768 lines · 17 tokens per session scan A c7d82a14a866
itx-execute is a skill published in the GitHub repository ric03uec/clawrium (51 stars, last pushed yesterday), licensed Apache-2.0. It adds 17 tokens to every session and 6,792 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
load-github-action-thread
Download retained Codex GitHub Action thread artifacts and load their rollout history into the local Codex app. Use when asked to open, load, import, resume, or inspect a Codex automation thread from a GitHub Actions run or a related GitHub issue or pull request.
uv-mapping
Inspect, generate, transform, and visualize UV channels on StaticMesh assets (UVMappingService). Use when the user asks to check/add/remove UV channels, auto-unwrap UVs, transform (tile/offset/rotate) UVs, check UV health/islands, or export a UV layout image.
depsguard
Install and run DepsGuard, a zero-dependency CLI that scans and fixes package manager configs (npm, pnpm, yarn, bun, uv) for supply chain security best practices.
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…
deploying-osquery-for-endpoint-monitoring
Deploys and configures osquery for real-time endpoint monitoring using SQL-based queries to inspect running processes, open ports, installed software, and system configuration. Use when building visibility into endpoint state, threat hunting across fleet, or implementing compliance monitoring. Activates for requests…
aget-propose-actions
Propose ranked next-best actions with evidence grounding, time budgets, and execute-all default. Formalizes the fleet's highest-frequency interaction pattern.