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 bendrucker/claude --skill flockgit clone --depth 1 https://github.com/bendrucker/claudeWrote 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/bendrucker/claude/flock)<a href="https://agentmods.dev/skills/bendrucker/claude/flock"><img src="https://agentmods.dev/badge/skills/bendrucker/claude/flock/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/bendrucker/claude/flock"><img src="https://agentmods.dev/badge/skills/bendrucker/claude/flock.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00050 | $0.02415 |
| Opus 5.5 | $0.00020 | $0.00966 |
| Sonnet 5.5 | $0.00010 | $0.00483 |
| Haiku 4.5 | $0.00005 | $0.00242 |
Grade A, and why
flock 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 18d 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 — 115 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Flock
State
!bun ${CLAUDE_SKILL_DIR}/scripts/claim.ts
NO HERDR means there is no server to coordinate. Say so and stop.
One flock runs per machine, and the FLOCK line settles which:
OK: this pane is it. Sweep.ELSEWHERE:herdr workspace focusthat ID, say where it went, stop.UNCLAIMED: rename this workspace toflockif it holds nothing else, then sweep. Otherwise create one, tell the user to run/flockthere, and stop. A pane keeps the workspace it launched in, so moving this one readsELSEWHEREon the next load.
The board classifies every row and prints only the ones you can act on. needs you, merge, and clean up get a row each. waiting, working, parked, and panes collapse to one line apiece, and a disposition with nothing in it is omitted. The count line at the top is the whole board.
Take the classification as given. It already read the checks, the review decision, and the merge state, so re-fetching them to second-guess a parked or waiting row spends tokens on rows with no action attached.
The PR column reads #N, draft#N, merged#N, -, or ?. The REPO column reads a bare name for a repository you own, and owner/repo for anything else, a fork's upstream target included. An owner there means the row is not yours to merge, though a conflict or a red check on it is still yours to fix.
FLAGS reads clean or a comma-joined list, forge state first. failing:lint,build names the jobs that went red, capped at three plus a count. running means CI has not finished, conflicting and behind come from the merge state, blocked marks a green pull request some other gate holds, approved and changes-requested come from the review, checks:none means the pull request runs no checks at all, and checks:? means the forge would not say.
The checkout flags follow. merged, occupied, and carries:N leave a row clear for cleanup, and every other flag holds it. Not self-evident: carries:N counts gitignored files a removal would delete, regenerable caches like node_modules/ and .terraform/ excluded, occupied means an agent is sitting in the pane, reused means the merged#N beside it belongs to different work under a recycled branch name, and unreadable or unpushed:? mean git would not report the state at all, which raises the row rather than parking it.
What ships with it
13 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.
- scripts/board.test.ts 6.1 KB runs code
- scripts/board.ts 5.7 KB runs code
- scripts/claim.ts 23 KB runs code
- scripts/defer.ts 1.2 KB runs code
- scripts/deferred.test.ts 4.4 KB runs code
- scripts/deferred.ts 3.9 KB runs code
- scripts/disposition.test.ts 19 KB runs code
- scripts/disposition.ts 10 KB runs code
- scripts/exec.ts 2.2 KB runs code
- scripts/forge.test.ts 16 KB runs code
- scripts/forge.ts 18 KB runs code
- scripts/worktree.test.ts 9.3 KB runs code
- scripts/worktree.ts 8.5 KB runs code
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.
- 18d ago Changed · +5 lines d772140ab2b4
- 21d ago Changed · +2 lines 0153704e65bc
- 1mo ago Changed · +1 lines 8af570e0277f
- 1mo ago Changed 85b1338e800c
- 1mo ago First seen · 107 lines · 50 tokens per session scan A cadbec91e8dd
flock is a skill published in the GitHub repository bendrucker/claude (18 stars, last pushed today), licensed MIT. It adds 50 tokens to every session and 2,415 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 2026-09-06.
Other skills, from other repositories
phx-pr-review
Address feedback left on a GitHub pull request: fetch unresolved review threads, make agreed Elixir/Phoenix code fixes, reply, and resolve. Use for a PR URL/number or reviewer comments. NOT for pre-PR review, findings triage, or CI monitoring.
branch-and-worktree-workflow
Isolates feature work in its own branch or worktree and integrates it cleanly when done. Use this when starting work that should not disturb the current workspace, when several efforts must proceed in parallel on one repository, or when implementation is finished and the change needs merging, rebasing, or splitting…
precommit
Pre-commit checks — lint:fix -> build -> test.
next-step
Change-aware next step advisor. Use when: user asks what to do next, workflow progression is unclear, session just started with dirty worktree. Not for: executing the suggested command (user decides), auto-loop decisions (hooks handle that). Output: findings-based suggestions or session summary with commit seed.
precommit-fast
Quick pre-commit checks — lint:fix -> test.
signing-preflight
Before the first commit of a session, check that commit signing will work — the key is loaded and unlocked — and ask the operator to unlock it once, up front, instead of discovering it after a hundred unsigned commits. Never disables signing silently, never re-signs history without asking. Use at the start of…