Borrowing it
Nothing to install: this file belongs to kyleve/Stuff. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/kyleve/Stuff/main/.agents/skills/rebalance-snapshot-shards/SKILL.mdgit clone --depth 1 https://github.com/kyleve/StuffWrote 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/kyleve/stuff/rebalance-snapshot-shards)<a href="https://agentmods.dev/skills/kyleve/stuff/rebalance-snapshot-shards"><img src="https://agentmods.dev/badge/skills/kyleve/stuff/rebalance-snapshot-shards/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/kyleve/stuff/rebalance-snapshot-shards"><img src="https://agentmods.dev/badge/skills/kyleve/stuff/rebalance-snapshot-shards.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 | $0.00031 | $0.01325 |
| Opus 5.5 | $0.00012 | $0.00530 |
| Sonnet 5.5 | $0.00006 | $0.00265 |
| Haiku 4.5 | $0.00003 | $0.00133 |
Grade A, and why
rebalance-snapshot-shards 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 — 99 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Use the repository's ./snapshot-shards command to maintain
the shard plan.
Read the root AGENTS.md and
github-workflow before changes.
The README describes the commands and intake worker.
Select timing samples
- Fetch
origin/main. Inspect the working tree. Start from currentmainin an isolated branch or a suitable clean worktree. Search open PRs for an existing rebalance before creating another PR. If a matching PR exists, update that branch through the GitHub workflow. - Run
./snapshot-shards checkto identify the current suite inventory and intake count. Read.circleci/config.ymlfor the current snapshot job and worker count. - Select the latest three successful snapshot jobs from distinct commits on
main. Usegh apito read commit statuses and obtain the CircleCI job UUIDs. Retain each source commit, job URL, and completion date for the PR. Exclude runs with incompatible toolchains, runner classes, or snapshot selections. Prefer samples after changes to snapshot infrastructure or suite contents. If fewer comparable jobs exist, use the available complete jobs and report the sample count. - Download each job with
./circleci-artifacts JOB_UUID. Select onlysnapshot-timings/results-*.xmlbeneath each job directory. Downloads can contain separateexec-NNNNdirectories for workers. Exclude unrelated XML, duplicate downloads, failed jobs, and partial results. - Verify that every selected job covers the current suite inventory exactly once across its workers. Reject JUnit documents with failures, errors, skipped tests, or invalid durations. An empty intake worker has no timing document. If coverage is incomplete, select another comparable successful job. If no complete sample exists, report the missing evidence and leave the plan unchanged.
Use the installed CLI help for exact flags. These read-only commands locate the samples:
gh api 'repos/{owner}/{repo}/commits?sha=main&per_page=30'
gh api 'repos/{owner}/{repo}/commits/{sha}/status'
circleci job get JOB_UUID --json
circleci artifact JOB_UUID --json
./circleci-artifacts JOB_UUID
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 · +14 lines 39dd6bd0cec7
- 22d ago First seen · 85 lines · 31 tokens per session scan A ef4fc059fb1f
rebalance-snapshot-shards is a skill published in the GitHub repository kyleve/Stuff (4 stars, last pushed today), licensed Apache-2.0. It adds 31 tokens to every session and 1,325 once invoked, about $0.0001 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 2026-10-08.
Other skills, from other repositories
Verification & Quality Assurance
Comprehensive truth scoring, code quality verification, and automatic rollback system with 0.95 accuracy threshold for ensuring high-quality agent outputs and codebase reliability.
quality-scan
Run a scoped, read-only quality scan and report exact-candidate evidence, failures and frozen debt. Use for an ad-hoc gate sweep or release preparation; a static scan is not full release acceptance.
e2e-testing
Use when reviewing CI coverage, automated checks, or test strategy related to Implement end-to-end testing. Focus on whether the rule is continuously verified, not just documented.
mirrord-prev-env
Help users create and manage mirrord preview environments — running a modified service as an isolated pod in a shared Kubernetes cluster, scoped by an environment key and HTTP/queue traffic filtering, so teams can validate and review changes against real traffic without affecting live services. Use when a developer…
test-setup
Scaffold the test framework and CI — tests/ directory, engine test runner, GitHub Actions workflow. Once, before the first sprint.
ci
Configure Ginkgo for continuous integration — the recommended CLI flag set and the rationale for each flag (-r -p --randomize-all --randomize-suites --fail-on-pending --fail-on-empty --keep-going --cover --race --trace --json-report --timeout --poll-progress-after/-interval), invoking via go run to pin the CLI to…