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 Unique-Divine/jiyuu --skill gh-labelsgit clone --depth 1 https://github.com/Unique-Divine/jiyuuWrote 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/unique-divine/jiyuu/gh-labels)<a href="https://agentmods.dev/skills/unique-divine/jiyuu/gh-labels"><img src="https://agentmods.dev/badge/skills/unique-divine/jiyuu/gh-labels/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/unique-divine/jiyuu/gh-labels"><img src="https://agentmods.dev/badge/skills/unique-divine/jiyuu/gh-labels.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 | $0.00098 | $0.01895 |
| Opus 5.5 | $0.00039 | $0.00758 |
| Sonnet 5.5 | $0.00020 | $0.00379 |
| Haiku 4.5 | $0.00010 | $0.00189 |
Grade A, and why
gh-labels 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 — 187 lines — stays where its author put it; the contents beside it link to each section on GitHub.
GitHub labels
Reference for what labels mean, then how to add them to a repo that does not have them yet.
My labels
Prefix convention:
S-*labels describe issue status.prio-p*labels describe issue priority.A-*labels describe product or engineering areas.
Status labels
S-triage: (#F9D0C4) | Status: This issue is waiting on initial triage. More Info: https://tinyurl.com/25uty9w5S-needs-scope: (#f08583) | Needs someone to work further on the design for the feature or fix. NOT YET accepted.S-impl: (#04d0e4) | Status: Implementation-ready. Clear and fully specificedS-blocked: (#f08583) | Status: 🧱 Blocked by an external dependency or unresolved decision.S-someday-maybe: (#f08583) | Status: 🤔 Intentionally paused. Currently on hold or out of scope.
Priority labels
prio-p0-critical: (#aaeaec) | Priority: Critical or super urgentprio-p1-high: (#aaeaec) | Priority: Highprio-p2-normal: (#aaeaec) | Priority: Normalprio-p3-low: (#aaeaec) | Priority: Low. Please focus on p2 or higher for now.
Area labels
A-ext-dev-tools: (#eab6cb) | Area: Tools built for developers outside the organization- Use for external SDKs, libraries, codegen, examples, and developer docs,
such as the Nibiru TypeScript package
nibijs. - A CLI or API does not qualify just because developers can use it. Check whether the work primarily serves external developers rather than internal operations or end-user flows.
- Use for external SDKs, libraries, codegen, examples, and developer docs,
such as the Nibiru TypeScript package
A-perf: (#eab6cb) | Area: End-user speed, throughput, latency, and work that measures or improves them- Includes block time, transaction throughput, caching, benchmarks, and observability tied to a performance goal.
A-tech-investment: (#eab6cb) | Area: Internal work that helps the team ship faster- Includes CI, E2E tests, automation, AI workflows, team communication, and
internal tools. Use label
A-perfwhen the goal is end-user speed.
- Includes CI, E2E tests, automation, AI workflows, team communication, and
internal tools. Use label
A-ops: (#eab6cb) | Area: Operational work such as deployments, governance proposals, and bookkeeping- Use for carrying out on-chain deployments and governance actions. Work on
deployment tooling belongs under label
A-tech-investment.
- Use for carrying out on-chain deployments and governance actions. Work on
deployment tooling belongs under label
A-ux: (#eab6cb) | Area: Solve friction in apps and wallets; improve acquisition, activation, referrals, and retention- Use for solutions to friction users encounter in apps, wallets, or other flows, and for work geared toward user acquisition or activation, referrals, and retention.
A-security: (#eab6cb) | Area: Security hardening, advisories, and upstream-sourced fixes- Use for advisories, vulnerability fixes, hardening, and tickets sourced
from upstream repos by agent skill
upstream-watch. Track mainnet-risk findings in private NibiruChain/sai-perps issues.
- Use for advisories, vulnerability fixes, hardening, and tickets sourced
from upstream repos by agent skill
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 · +9 lines aa6c6bd84039
- 21d ago Changed · +48 lines · +2 tokens per session 37887d19e380
- 1mo ago First seen · 130 lines · 96 tokens per session scan A 39350722d18c
gh-labels is a skill published in the GitHub repository Unique-Divine/jiyuu (6 stars, last pushed 5d ago), licensed MIT. It adds 98 tokens to every session and 1,895 once invoked, about $0.0004 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 2026-08-31.
Other skills, from other repositories
vhs-e2e-gif
Record a test run, a TUI session, or any terminal command as a GIF with VHS and attach it to a GitHub PR as a release-hosted asset, never a repo commit. Use when asked to record an e2e run, demo a fix on a PR, attach a GIF or screen recording to a pull request, show a test passing visually, or produce a terminal…
check-linters-before-commit
Before any commit, run linters, vet, tests, and build verification; do not commit until checks pass.
merge-conflict-resolution
Use when an in-progress merge, rebase, cherry-pick, or revert has conflicted hunks that require intent reconstruction, resolution, proof, and continuation.
session-repo
Restart this Claude session inside the git repository it is working on, keeping the conversation. Use when a remote (crctl / screen) session was started outside its repo - e.g. in the home directory - so the Claude apps show no branch, diff or pull request for it; or when the user asks to restart this session, move…
bmad-loop
Iterate over a list of story keys, executing dev → review → PR → CI → merge for each. Use when the user says "loop these stories [list]" or "run the loop on [story keys]".
gh-skill
Manage agent skills with gh skill. Use this skill to discover, preview, install, update, and publish Agent Skills so an agent can self-manage the skills available in its environment.