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 tokyubevoxelverse/fence --skill fencegit clone --depth 1 https://github.com/tokyubevoxelverse/fenceWrote 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/tokyubevoxelverse/fence/fence)<a href="https://agentmods.dev/skills/tokyubevoxelverse/fence/fence"><img src="https://agentmods.dev/badge/skills/tokyubevoxelverse/fence/fence/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/tokyubevoxelverse/fence/fence"><img src="https://agentmods.dev/badge/skills/tokyubevoxelverse/fence/fence.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 | $0.00057 | $0.00733 |
| Opus 5 | $0.00028 | $0.00367 |
| Sonnet 5 | $0.00011 | $0.00147 |
| Haiku 4.5 | $0.00006 | $0.00073 |
Grade A, and why
fence 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 10d 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 — 44 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Fence
"If you don't see the use of it, I certainly won't let you clear it away. Go away and think. Then, when you can come back and tell me that you do see the use of it, I may allow you to destroy it."
The user has pointed at a fence: a weird conditional, a magic sleep, a suspicious constant, a workaround nobody remembers. Your job is to find out why it was built, whether that reason still exists, and only then rule on removal.
Phase 1 — Excavate
Find the true origin, not just the latest touch:
git log -L/git blameon the exact lines; follow the code through file moves and renames (--follow,blame -C -C -C), and re-blame past refactoring commits — the commit that last formatted the line is rarely the commit that created it.- Extract from the introducing commit: full message, what else changed alongside (tests added in the same commit are gold — they encode the reason), linked issue/PR numbers.
- If a hosted forge is reachable, pull the PR description and review discussion for the introducing commit; that's where "why" actually gets written down.
- Search the codebase for siblings: the same constant, same pattern, or comments referencing the same issue elsewhere.
Phase 2 — Test whether the reason still stands
The fence was built against something. Check if that something still exists:
- Bug workaround → is the buggy dependency version still in range? Read the upstream issue: was it fixed, and in what version?
- Platform/browser/OS quirk → does the project still support that target? Check documented support matrix and build configs.
- Performance fix → does the hot path still exist? Is there a benchmark or test guarding it?
- Compatibility shim → does anything still call the old path? Trace the callers.
- Where feasible, test empirically: remove the fence in a scratch worktree, run the tests, and if the original commit came with a repro or test, run that.
Phase 3 — The ruling
Deliver a short dossier — origin story (commit, date, author, the why), current status of the original reason, evidence — ending in exactly one ruling:
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.
- 10d ago First seen · 44 lines · 57 tokens per session scan A e359b9829e77
fence is a skill published in the GitHub repository tokyubevoxelverse/fence (1 stars, last pushed 1mo ago), licensed MIT. It adds 57 tokens to every session and 733 once invoked, about $0.0003 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 2026-08-31.
Other skills, from other repositories
gh-pr-merge-worktree-checkout-trap
Diagnose and bypass gh pr merge --squash --delete-branch failing with "failed to run git: fatal: 'main' is already used by worktree at ..." when another git worktree has main checked out. Use when: (1) you run gh pr merge and see this exact error, (2) you have multiple worktrees in the repo (e.g. .claude/worktrees/)…
pr-conflict-from-mid-flight-merges
A pull request that was clean when you opened it now says on GitHub "This branch has conflicts that must be resolved", because others landed on main over the days it sat open. Use when gh pr view N --json mergeable,mergeStateStatus returns CONFLICTING and DIRTY, when your branch carries commits you do not recognise…
parallel-pr-template-fork-duplicates-moved-section
Diagnose silent semantic duplication after two parallel PRs ship. Use when: (1) one PR (the mover) relocates a section/component/block from template X to template Y (X loses it, Y gains it), (2) a sibling PR (the forker), authored against pre-mover main, creates / promotes / copies template Z from the OLD version of X…
pr-hijack-via-stale-worktree-branch-ref
Diagnose and recover from accidentally overwriting another session's open PR when git push -u origin in a long-lived worktree silently replaces the remote branch ref. Use when ANY of the following appears: (1) you ran git checkout -b origin/main and git push -u and git reported [new branch] even though the branch…
wip-branch-linter-revert-system-reminder-trap
Avoid silently accepting linter / automation reverts of deliberate wip-branch framings. Use when: (1) working on a wip / preview branch with intentional non-default constants, SQL framings, copy strings, or feature toggles; (2) a system-reminder mid-session says "[file] was modified, either by the user or by a linter.…
worktree-stale-local-main-ref-inflates-pr-diff
Stop a false "my PR is reverting/touching dozens of upstream files" alarm when git diff main... reports far more files than your commit changed, in a multi-worktree repo. Use when: (1) you're in a worktree at /.claude/worktrees/ / (or any git worktree), (2) git diff main...HEAD (3-dot) or --stat shows tens/hundreds of…