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 agents/xiaolai/vmark/release-stewardgit clone --depth 1 https://github.com/xiaolai/vmarkWhat 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 | $0.00019 | $0.00106 |
| Opus 5 | $0.00010 | $0.00053 |
| Sonnet 5 | $0.00004 | $0.00021 |
| Haiku 4.5 | $0.00002 | $0.00011 |
Grade A, and why
release-steward 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 3d 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
You propose commit(s) that match Work Items:
- One commit per Work Item (no mixed-scope commits).
type(scope): summary(e.g.fix(file-ops): open recent uses active tab)- Bullet body with behavior + tests.
Commit policy:
- Never commit unless the user explicitly says “commit”.
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.
- 3d ago First seen · 15 lines · 19 tokens per session scan A d15db138abf3
release-steward is an agent published in the GitHub repository xiaolai/vmark (544 stars, last pushed 3d ago), licensed ISC. It adds 19 tokens to every session and 106 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 agents, from other repositories
git-workflow
Agent "git-workflow" from callstack/react-native-testing-library, covering git, releases, and pr workflow, agent git restrictions, commits and releases and pr draft workflow.
git-workflow-master
Git工作流专家，负责分支策略设计、合并冲突解决、代码历史维护、CI集成和团队Git规范制定.
shipper
Git and GitHub Operations — commits, pushes, PRs, issue comments.
git-agent
Background git operations agent - commits, PRs, branch management, release workflows. Runs on Sonnet to free main session.
git
Specialized git operations — semantic commits, PR descriptions, branch naming, changelog generation, release tagging. Convention-aware utility replacing ad-hoc git commands.
commit
Use when: the owner wants to commit, save work, or release — the lead delegates ALL commits here, never runs git commit itself. Do NOT use for: read-only git ops (status/log/diff — run directly), non-commit code changes (domain expert + sniper own those).