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 agentmods add skills/yujiachen-y/agent-bundle/format-codenpx skills add yujiachen-y/agent-bundle --skill format-codegit clone --depth 1 https://github.com/yujiachen-y/agent-bundleWhat 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 | $0.00011 | $0.00153 |
| Opus 5 | $0.00005 | $0.00077 |
| Sonnet 5 | $0.00002 | $0.00031 |
| Haiku 4.5 | $0.00001 | $0.00015 |
Grade A, and why
format-code 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 2d 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
Format Code
You are given raw Python code by the user. Follow these steps exactly:
- Write the user's code to
/workspace/input.pyusing the Write tool. - Run the formatter in the sandbox using Bash:
autopep8 --in-place /workspace/input.py - Read
/workspace/input.pyusing the Read tool. - Return the Read result as the final answer.
Rules:
- Always use the path
/workspace/input.py. - Do not invent formatted output from memory.
- Do not skip the Read step.
- If the Bash command fails, return the command error output directly.
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.
- 2d ago First seen · 24 lines · 11 tokens per session scan A e71f97f112e7
format-code is a skill published in the GitHub repository yujiachen-y/agent-bundle (10 stars, last pushed 2mo ago), licensed MIT. It adds 11 tokens to every session and 153 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 2026-08-31.
Other skills, from other repositories
troubleshoot-sandbox
Troubleshoot OpenSandbox issues by running diagnostics (logs, inspect, events, summary) via CLI or HTTP API to diagnose sandbox failures like OOM, crash, image pull errors, network problems, etc.
bump-go-version
Bumps the Go version to the latest release across go.mod, tools.mod, and Dockerfiles.
k8s-api-conventions
Guides the agent to follow Kubernetes API conventions for OSS standards.
test-pyramid
Analyze the repo's unit and E2E tests and propose rebalancing toward a test pyramid — which E2E tests (or assertions inside them) can be covered by unit tests, which unit-level gaps genuinely need E2E coverage, and where coverage is duplicated. Use when the user asks about test pyramid, test rebalancing, "should this…
triage-issues
Triage open GitHub issues for kubernetes-sigs/agent-sandbox by mapping them to roadmap.md and assigning k8s priority labels + Kanban Priority (P0–P4) on Project.
fix-flakes
Diagnose and fix flaky tests tracked as open kind/flake issues in kubernetes-sigs/agent-sandbox — reproduce the flake, apply a minimal fix, and open a PR linking the issue. Use when asked to fix a flake, work through kind/flake issues, or when run on a schedule after dev/tools/flake-report has filed flake issues.