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 ric03uec/clawrium --skill issue-triagegit 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/issue-triage)<a href="https://agentmods.dev/skills/ric03uec/clawrium/issue-triage"><img src="https://agentmods.dev/badge/skills/ric03uec/clawrium/issue-triage.svg" alt="Measured on agentmods" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00036 | $0.00680 |
| Opus 5 | $0.00018 | $0.00340 |
| Sonnet 5 | $0.00007 | $0.00136 |
| Haiku 4.5 | $0.00004 | $0.00068 |
Grade A, and why
issue-triage scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 4d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 67 lines — stays where its author put it; the contents beside it link to each section on GitHub.
issue-triage
Triage incoming work on ric03uec/clawrium. Run on a 10-minute poll cycle.
The loop is: find issues that need triage → read them carefully → apply
labels → draft a planning file as a PR.
Inputs
For each candidate issue:
- Title and body.
- Current labels (skip if
needs-triageis absent or the issue already has atype:*label). - The repo's
LABELS.mdfor the allowed taxonomy. Do not invent labels.
Candidates are issues opened or updated in the last 15 minutes (giving the poll a 5-minute overlap so nothing is missed during a slow run). Use:
gh issue list --repo ric03uec/clawrium \
--search "sort:updated-desc updated:>$(date -u -d '15 minutes ago' +%Y-%m-%dT%H:%M:%SZ)" \
--json number,title,body,labels,updatedAt
Output
- Apply labels from the taxonomy in
LABELS.md. At minimum: onetype:*, onecomplexity:*, onearea:*. Addneeds-reviewwhen the issue lacks a clear Definition of Done. - Open a PR adding
.itx/active/<issue-number>/plan.mdwith a one-page scaffold (Outcome / Approach / Files / Risk). Title:chore(triage): draft plan for #<n>. Body links to the issue.
Hard constraints
- Never apply the
agent-readylabel. The PAT denies it; even if it did not, this label is a human decision. - Never push directly to
mainor merge a PR. PRs targetmainwith a feature branch namedtriage/<issue-number>-<slug>. - If the issue body is empty or one sentence, label
needs-reviewand leave a single short comment asking for Outcome + Definition of Done. Do not invent requirements. - If
LABELS.mdis missing or unreadable, stop and post a[ITX-STUCK]comment on the issue rather than guessing label names.
Anti-patterns
- Re-labeling issues that already have a
type:*label — assume a human or earlier triage decided. Touch only the missing dimensions. - Drafting an
.itx/active/<n>/plan.mdthat exceeds one page. The plan is a starting point for/itx-plan-create, not a substitute for it. - Commenting on the issue with summaries of the body. The body is the source of truth; do not paraphrase it back.
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 Changed 5d7457b22683
- 8d ago First seen · 67 lines · 36 tokens per session scan A 79565fce95ae
issue-triage is a skill published in the GitHub repository ric03uec/clawrium (51 stars, last pushed 4d ago), licensed Apache-2.0. It adds 36 tokens to every session and 680 once invoked, about $0.0002 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
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…
using-labby
Use when operating Labby through its CLI, MCP, HTTP API, or web UI; installing or updating Labby; configuring LABBYHOME; bootstrapping, repairing, or rolling back an Incus gateway or host service; exporting, verifying, or restoring durable state; checking health or logs; managing gateway upstreams, OAuth, or protected…
opencli-sitemap-author
Use when creating or maintaining OpenCLI site sitemaps: agent-facing navigation, page-state, action, workflow, API-reference, pitfall, and fallback knowledge for a website. Use after browser exploration discovers durable site context, when a sitemap is stale, or when promoting local site knowledge into the repo.
feishu
Work with Feishu or Lark bots, docs, sheets, bitables, approval flows, and OpenAPI/MCP setup without hardcoding credentials.
interview
Ask one useful structured question at a time only when material product/implementation choices are genuinely missing; remember answers and produce a brief/spec. Discoverable facts should be investigated instead of asked.