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 ArcBlock/agent-skills --skill landgit clone --depth 1 https://github.com/ArcBlock/agent-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/arcblock/agent-skills/land)<a href="https://agentmods.dev/skills/arcblock/agent-skills/land"><img src="https://agentmods.dev/badge/skills/arcblock/agent-skills/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/arcblock/agent-skills/land"><img src="https://agentmods.dev/badge/skills/arcblock/agent-skills/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 | $0.00062 | $0.02021 |
| Opus 5.5 | $0.00025 | $0.00808 |
| Sonnet 5.5 | $0.00012 | $0.00404 |
| Haiku 4.5 | $0.00006 | $0.00202 |
Grade A, and why
land 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 9d 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 — 142 lines — stays where its author put it; the contents beside it link to each section on GitHub.
land — take one thing to merged
/agentloop:land <work DID | w_<32hex> | 40-char sha | issue# | PR# | url>
/agentloop:land <n1> <n2> … # batch: one isolated subagent per target
/agentloop:land [one-line topic] # no reference: coherence check first
| Flag | Default | Effect |
|---|---|---|
--merge=auto |
single target | tests green + review clean → merge |
--merge=confirm |
batch | stop at ready to merge, ask |
--merge=never |
— | stop at ready to merge |
Read .claude/repo-profile.md first (repo_slug, default_branch, plugin_root,
package_manager, test_runner, agent_identity_script, comment_language,
change_set_record_entry). No profile → /agentloop:repo-setup. Never hardcode repo literals.
land is a router plus a single-item driver. An epic goes to /agentloop:epic-conductor; a backlog
to /agentloop:issue-sweep / /agentloop:pr-sweep; a multi-phase plan to /agentloop:build-phases.
Factory run (ARC_CODE_AGENT_RUN_ID set)
One turn only: run tests in the foreground and never end the turn waiting on a background shell or
child run. Merge authority is human: whatever --merge says, stop at ready to merge, post the
checklist comment + needs-human-confirm, report "ready to merge, human decision", end the run.
merge-verified-pr.sh exits 3 inside a run. Detail: headless-factory-run.md.
Step 0 — Resolve the target
Look up /work first; GitHub is a projection, not identity:
arc --json afs exec /.actions/query --args '{"path":"/work","where":{"field":"meta.objectId","eq":"<DID>"},"limit":8}'
# Change Set @ sha:
arc --json afs exec /.actions/query --args '{"path":"/work","where":{"all":[{"field":"meta.workType","eq":"change-set"},{"field":"meta.head","eq":"<sha>"}]},"limit":8}'
A /work hit wins. A miss falls back to gh issue view / gh pr view (say it is an alias). An
issue and a PR both match → name both and ask. Argument shapes: reference/resolve-target.md.
What ships with it
5 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.
- 9d ago Changed · -64 lines · -2 tokens per session e30b88a810c9
- 13d ago Changed · -2 lines 9560336bb362
- 20d ago Changed · -421 lines · -103 tokens per session 5cfba704b021
- 26d ago Changed · +4 lines 66a52d0f4797
- 1mo ago Changed · +40 lines d4ef049c2fc1
- 1mo ago Changed · +24 lines · +18 tokens per session 532ed6f99aad
- 1mo ago First seen · 561 lines · 149 tokens per session scan A cd2c0a68a20b
land is a skill published in the GitHub repository ArcBlock/agent-skills (5 stars, last pushed 9d ago), licensed MIT. It adds 62 tokens to every session and 2,021 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 2026-09-04.
Other skills, from other repositories
batch
Research and plan a large-scale change, then execute it in parallel across 5–30 isolated worktree agents that each open a PR.
team-release
Orchestrate the release team — release-manager, qa-lead, devops-engineer, producer — to execute a release from candidate to deployment.
operating-github-cli
Default GitHub skill for the action agent. Use githubcli for any GitHub request — create/list/view/close issues and PRs, assign, labels, repos, releases, checks, github.com/owner/repo URLs, or gh api. Prefer over shellrun/!gh. Run these with githubcli in the current agent turn.
github
Drive GitHub via the official gh CLI — repos, issues, pull requests, releases, gists, Actions runs, and raw REST through gh api. Use when the user asks to inspect or manage GitHub.
testdino-releases
Use when the user wants to browse, inspect, create, or update releases/milestones in a TestDino project. Covers listreleases, getrelease, createrelease, and updaterelease. Accepts counter-style IDs like MS-12.
create-milestone
Create a GitHub milestone for an upcoming release. Suggests the next version based on the latest release, gathers all merged PRs and closed issues since that release, presents a draft with two tables (Issues and PRs) for user approval, then creates the milestone and assigns all approved items.