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-landgit 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-land)<a href="https://agentmods.dev/skills/shikanime-labs/skills/sks-land"><img src="https://agentmods.dev/badge/skills/shikanime-labs/skills/sks-land/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-land"><img src="https://agentmods.dev/badge/skills/shikanime-labs/skills/sks-land.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 | $0.00034 | $0.02805 |
| Opus 5 | $0.00017 | $0.01403 |
| Sonnet 5 | $0.00007 | $0.00561 |
| Haiku 4.5 | $0.00003 | $0.00281 |
Grade C, and why
sks-land scanned grade C with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured yesterday.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Recursive force deletehighDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
rm -rf <path> How it starts
The opening of the file, as written. The whole thing — 253 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Shikanime Org PR Landing
Land a shikanime-labs/* / shikanime-studio/* PR only after sks-pr-resolve
reconciled it and a human approving review is in place — protect main. Not
for opening (sks-pr), review (sks-pr-review), reconciling
(sks-pr-resolve), or direct "push to main". This skill only lands.
When to Use
- "Land a shikanime PR after DoD gates pass."
- "Close an issue deliberately after merge (verify N-of-N)."
- "Run post-merge sync (docs, downstream rebases)."
Pre-landing gates (must already hold)
Gate 1 — DoD discharged. Issue criteria (- [ ], sks-issue) all checked;
re-read the ledger (unchecked box blocks merge):
gh issue view <N> --repo <org>/<repo> --json body --jq .body
Gate 2 — yorha-operator approval (mandatory, non-bypassable). Before
any other review consideration, the merge is blocked until yorha-operator
has an APPROVED review on the current head commit — a stale approval after a
new push does not count, and --admin may bypass branch protection but never
this gate. CI green: gh pr checks <M> --repo <org>/<repo>. Verify the
operator approval against the head SHA (REST reviews carry commit_id):
R=<org>/<repo>; M=<PR>
HEAD=$(gh pr view "$M" -R "$R" --json headRefOid -q .headRefOid)
gh api "repos/$R/pulls/$M/reviews" --paginate \
--jq 'map(select(.user.login == "yorha-operator" and .state == "APPROVED"
and .commit_id == "'"$HEAD"'")) | length > 0'
False → BLOCKED: yorha-operator approval required — request it
(gh pr edit <M> -R "$R" --add-reviewer yorha-operator) or obtain it
verbally, then re-verify on the new head. In addition, sks-pr-review
approval applies as before: approved on current head; re-review if new
commits landed.
gh pr view <M> --repo <org>/<repo> --json reviews,headRefOid \
--jq '.reviews | map(select(.state == "APPROVED")) | length > 0'
Agent review is pre-flight; a human approving review is the gate. Where
branch protection blocks self-approval (e.g. shikanime-labs/skills,
nix-containers), a verbal lgtm from the operator (the user operating
yorha-operator) satisfies Gate 2 — land via
gh pr merge --squash --admin (see Merge procedure). --admin is what bypasses
the protection; no separate human review is then required.
What ships with it
3 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.
- yesterday Changed · +45 lines a44b8406c882
- 12d ago First seen · 208 lines · 34 tokens per session scan C e0ea519d1705
sks-land is a skill published in the GitHub repository shikanime-labs/skills (2 stars, last pushed today), licensed Apache-2.0. It adds 34 tokens to every session and 2,805 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it C with 1 finding (recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
github-repo-management
Clone/create/fork repos; manage remotes, releases.
github-pr-workflow
GitHub PR lifecycle: branch, commit, open, CI, merge.
bridge
Use when the user wants hyperflow's behavioral rules to apply outside the terminal CLI — in Claude Code Desktop, claude.ai web, or IDE extensions that don't load CLI plugins. Writes a managed doctrine block into the project's CLAUDE.md so autonomy + intent-routing + commit cadence + role separation + file-first rules…
atmos-hooks
Atmos hooks: lifecycle events, hook kinds, command/store/git/security hooks, step/steps hooks, when: conditions, scoping and overrides, toolchain integration, --skip-hooks, and Atmos Pro/local output.
taiyi-integration
A project workflow skill for closing a TaiyiForge change and recording it in a CHANGELOG.md file. It checks review results, tests, and the state of the working tree before archiving the change.
qa
QA test your code changes by reading your git diff, choosing the right validation path for frontend/browser and backend changes, and reporting pass/fail with evidence.