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 ychampion/cskill-agents --skill empty-repo-bundle-preflightgit clone --depth 1 https://github.com/ychampion/cskill-agentsWrote 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/ychampion/cskill-agents/empty-repo-bundle-preflight)<a href="https://agentmods.dev/skills/ychampion/cskill-agents/empty-repo-bundle-preflight"><img src="https://agentmods.dev/badge/skills/ychampion/cskill-agents/empty-repo-bundle-preflight/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/ychampion/cskill-agents/empty-repo-bundle-preflight"><img src="https://agentmods.dev/badge/skills/ychampion/cskill-agents/empty-repo-bundle-preflight.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 | $0.00026 | $0.00462 |
| Opus 5 | $0.00013 | $0.00231 |
| Sonnet 5 | $0.00005 | $0.00092 |
| Haiku 4.5 | $0.00003 | $0.00046 |
Grade A, and why
empty-repo-bundle-preflight 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.
What it actually says
SKILL: Empty Repo Bundle Preflight
Domain: safety-worktrees
Trigger: Apply before running git bundle create to ensure the repository actually has refs, avoiding the 128 exit code and providing a clearer error path.
Source Pattern: Distilled from reviewed repo-safety, packaging, and worktree-management patterns.
Core Method
Run git for-each-ref --count=1 refs/ from the repository root; if the output is empty, report that the repo has no commits, record an analytics metric with the empty_repo outcome, and abort with a helpful message instead of invoking git bundle create, which would exit 128 on an empty repo. Sweep stale temporary refs first so the check reflects the true repo state, and treat the empty case as a known failure reason with a dedicated fail reason identifier that consumers can react to.
Key Rules
- Always clean up
refs/seed/stashandrefs/seed/rootbefore testing for refs so old placeholders cannot make an empty repo appear populated. - Capture the
empty_repooutcome via analytics or logs so you can audit why bundling never ran. - Return a structured error with a fail reason (
empty_repo) so callers can distinguish it from git failures or oversized bundles. - When the repo has refs, proceed to bundle creation without repeating the check unnecessarily.
Example Application
When building a git bundle upload helper, call this skill before _bundleWithFallback; if it signals an empty repo, stop and surface “Repository has no commits yet” to the UI and telemetry instead of letting git bundle create crash.
Anti-Patterns (What NOT to do)
- Do not rely on the git bundle exit code alone to detect emptiness; it produces a cryptic message and leaves temporary files behind.
- Do not skip the cleanup step—stale refs from prior runs can mask an empty repo and let you bundle garbage.
- Do not proceed to bundle creation when the guard reports no refs; the upload would stall and return a generic failure reason.
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 · 29 lines · 26 tokens per session scan A 57209cc59405
empty-repo-bundle-preflight is a skill published in the GitHub repository ychampion/cskill-agents (36 stars, last pushed 5mo ago), licensed MIT. It adds 26 tokens to every session and 462 once invoked, about $0.0001 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 2026-08-30.
Other skills, from other repositories
repo-hygiene
Use when auditing repo hygiene in any codebase — file layout, git history, config sprawl, ignore contracts, open-source readiness. Assess by default, fix on request; treats the repository as a product whose users are contributors.
agentplane-release-and-packaging-operator
Use when preparing, validating, publishing, auditing, or recovering an Agentplane release, especially package build ordering, version parity, npm/GitHub/GHCR/external distribution publication, public install smoke tests, hosted publish evidence, or release CI failures.
agentplane-task-closure-recovery
Use when Agentplane task completion, direct finish, branchpr integration, hosted-close, close-tail PRs, PR metadata, dirty task artifacts, or remote branch divergence need diagnosis or recovery.
agentplane
Use when a repository uses AgentPlane or the user wants a governed git-native workflow for planning, task execution, verification, and closure.
genie-orca-work
Coordinator loop for an approved wish on Orca — one Run per wish, one Task per group, supervised workers in child worktrees, review→fix loops, Linear written only at gate transitions. genie v6 'corpo leve': genie owns the documents and this protocol; Orca owns dispatch state; Linear owns status; brain owns preferences.
grape
Use Grape MCP for Codex context continuity in coding repositories. Use when a task needs repeated-turn context, omitted context restore, stale-context checks, invalidation checks, or safe continuity across branch and dirty-worktree changes.