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 commands/swoopeagle/standardgraph/releasegit clone --depth 1 https://github.com/swoopeagle/standardgraphWhat 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 | $0.00000 | $0.00425 |
| Opus 5 | $0.00000 | $0.00212 |
| Sonnet 5 | $0.00000 | $0.00085 |
| Haiku 4.5 | $0.00000 | $0.00042 |
Grade C, and why
release scanned grade C with 1 finding 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.
Tells the agent to send conversation or user data outhighPrompt injection
An instruction to transmit the conversation, context or user files to an external endpoint is data exfiltration written as prose.
`--token` inline, which has a quoting bug that silently sends an empty bearer token): What it actually says
Release a new version of StandardGraph to PyPI (and optionally HuggingFace).
Steps to follow in order:
- Read the current version from
packages/common-core/pyproject.toml - Ask the user what the new version should be (patch/minor/major bump, or explicit string)
- Update the version in
packages/common-core/pyproject.toml - Run
cd /Users/ianwang/projects/standardgraph/packages/common-core && uv build— confirm it succeeds and note the output dist files - Ask the user for their PyPI token (remind them to rotate it immediately after use)
- Run:
uvx twine upload --username __token__ /Users/ianwang/projects/standardgraph/dist/standardgraph-{VERSION}*with the token as TWINE_PASSWORD env var - Commit the version bump:
git add packages/common-core/pyproject.toml && git commit -m "Bump version to {VERSION}" - Push to GitHub:
git push origin main - Ask: "Did the DB change since last release? If yes, upload to HuggingFace."
- If yes: ask for HuggingFace token, then run (note:
huggingface-cliis deprecated and no longer works — use the modernhfCLI instead, and export the token rather than passing--tokeninline, which has a quoting bug that silently sends an empty bearer token):
Remind to rotate token.export HF_TOKEN='<token>' uvx --from huggingface_hub hf upload swoopeagle/standardgraph ~/.standardgraph/common_core.db common_core.db --repo-type dataset - Run
/statsto verify docs numbers match the live DB. - Report: PyPI URL, GitHub commit, and whether HF was updated.
Important: ALWAYS remind the user to rotate any tokens shared in chat. Tokens should never persist in shell history — pass them via env vars, not positional args.
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 · 26 lines · 0 tokens per session scan C d6d8f366d4ea
release is a command published in the GitHub repository swoopeagle/standardgraph (5 stars, last pushed 1mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 425 tokens. A static security scan graded it C with 1 finding (tells the agent to send conversation or user data out). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other commands, from other repositories
review-renovate
Review and merge renovate PRs with automerge configuration updates.
push-and-release
Git pull, resolve conflicts, push, fix hook errors, then release.
release
Perform a full release: generate release notes, bump version, commit, tag, and push.
release
Create a full stable release for the project. Optionally pass a title suffix (e.g., "Template Presets Fix") or extra notes.
SHIP_RELEASE
Ship the active release/X.Y.Z — build the installer, merge to main, tag, push, and publish the GitHub release. Run after /prerelease passes.
release
This compatibility command keeps /oh-my-claudecode:release available without loading the full release skill description in every Claude Code session.