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 shikanime-labs/skills --skill sks-triagegit clone --depth 1 https://github.com/shikanime-labs/skillsWrote 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/shikanime-labs/skills/sks-triage)<a href="https://agentmods.dev/skills/shikanime-labs/skills/sks-triage"><img src="https://agentmods.dev/badge/skills/shikanime-labs/skills/sks-triage/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/shikanime-labs/skills/sks-triage"><img src="https://agentmods.dev/badge/skills/shikanime-labs/skills/sks-triage.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00054 | $0.02431 |
| Opus 5.5 | $0.00022 | $0.00972 |
| Sonnet 5.5 | $0.00011 | $0.00486 |
| Haiku 4.5 | $0.00005 | $0.00243 |
Grade A, and why
sks-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 3d 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 — 226 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Triage
Scope-level entry point for triage: given an org, repo, issue, or
PR, find what lacks metadata and assign every empty, context-derivable
field — never inventing a value the repo does not offer. Per-kind deep flows
live in sks-issue-triage / sks-pr-triage; this skill owns the scopes they
cannot reach — repo and org — and the org issue fields and project card
fields they predate.
Org specifics — target orgs, default assignee, default reviewer — live in
references/shikanime.md; the issue-field mechanics in
references/issue-fields.md. Load references/cloud-pi-native.md when
triaging a cloud-pi-native repo.
Available scripts
Run them as <skill-dir>/scripts/... — paths resolve against the skill
directory, not the target repo.
scripts/discover-metadata.sh REPO— every triage-relevant value the repo or its org offers: labels, open milestones, projects, assignees, enabled issue types, org issue fields. The source of truth for step 3; never set a value it does not list.scripts/scan-untriaged.sh REPO— open issues and PRs whose metadata is incomplete, computed against what the repo actually supports. Columns: number, kind, missing classes.
When to Use
- "Triage this repo" / "triage the org backlog" — sweep every open item missing metadata, then assign what each one is missing.
- "Triage issue #N / PR #N" — assign all empty, derivable fields on one item.
- "Assign metadata (type, labels, assignee, fields, card fields) to #N."
- Zero untriaged items found → report that and change nothing.
Not for: discussions (sks-discussion-triage), closing unworkable issues
(sks-issue-triage), rewording a PR body (sks-pr-triage), diagnosing a
defect (sks-investigate).
Prerequisites
ghauthenticated against the target repo; target it directly.- Outside the org's own repos, confirm the target with the user first
(
references/shikanime.mdnames them).
Inputs
- Target:
ORG,OWNER/REPO, orN(withinR;Rdefaults to the cwdorigin, else ask). CAP— max items to touch in one sweep (default 10); the remainder is reported, not processed.
What ships with it
7 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 3d ago Changed · +8 lines · +4 tokens per session f1b4354b1121
- 7d ago Changed f99888cffecf
- 10d ago Changed 51e44dc368e9
- 14d ago Changed · +4 lines 3387fa43b521
- 19d ago First seen · 214 lines · 50 tokens per session scan A 20e19e25167c
sks-triage is a skill published in the GitHub repository shikanime-labs/skills (2 stars, last pushed today), licensed Apache-2.0. It adds 54 tokens to every session and 2,431 once invoked, about $0.0002 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 2026-09-30.
Other skills, from other repositories
github-issue-pr-attribs
Standardize GitHub ISSUE and PR metadata (Assignee, Reviewer, Labels, Project, Milestone, Development, Relationship) and ship a strong, well-structured code-review template. Includes ready-to-use issue forms, PR template, and a severity/rubric review model.
sdlc-review
Review Kanban handoffs and route verified outcomes.
tech-debt
Track, categorize and prioritize technical debt across the codebase — scans for debt indicators, maintains a register.
pr-review-triage
Watch open PRs, check CI status, review staleness, merge conflicts, and unanswered review comments. Produces a prioritized watchlist.
issue-creation
Trigger: issue creation, bug reports, feature requests, or issue approval. Create and triage GitHub issues from repository evidence.
systemic-issue-triage
Trigger: new issue, bug report, triage, backlog, issue flood, community report, root cause, dead-end, blocked user. Attack issues by root class, never one-by-one; fixes must shrink the system, not grow it.