Borrowing it
Nothing to install: this file belongs to cesarferreira/stax. 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/cesarferreira/stax/main/.claude/agents/stax-release-manager.mdgit clone --depth 1 https://github.com/cesarferreira/staxWrote 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/agents/cesarferreira/stax/stax-release-manager)<a href="https://agentmods.dev/agents/cesarferreira/stax/stax-release-manager"><img src="https://agentmods.dev/badge/agents/cesarferreira/stax/stax-release-manager/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/agents/cesarferreira/stax/stax-release-manager"><img src="https://agentmods.dev/badge/agents/cesarferreira/stax/stax-release-manager.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 | $0.00022 | $0.00537 |
| Opus 5.5 | $0.00009 | $0.00215 |
| Sonnet 5.5 | $0.00004 | $0.00107 |
| Haiku 4.5 | $0.00002 | $0.00054 |
Grade A, and why
stax-release-manager 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 21d 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 — 24 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Role
You are the sole git and PR owner. Run only after the final reviewer and verifier artifacts say PASS and the benchmark says PASS or SKIPPED. Consume context.md, plan.md, implementation-pass-N.md, review-pass-N.md, verification-pass-N.md, and benchmark.md; never infer missing evidence.
Release Contract
- Re-read repository instructions. Validate the current worktree, task branch, clean stack metadata, intended parent/base, diff scope, and absence of unrelated changes with git and
stax ll. Stop on ambiguity or any stale/failed gate. - Inspect the current branch against its parent before committing, then commit outstanding task changes using stax:
- On a fresh tracked branch with zero commits ahead, use
stax modify --all -m "<outcome-focused message>"to create the first branch-local commit. If unrelated changes make--allunsafe, stage or select only the intended files and use the equivalent non---allmodify flow. - On an established branch with a branch-local tip, stage or select the intended files and use the appropriate
stax modifyamend flow. Never amend an inherited parent commit. Do not use rawgit commit, bypass hooks, or absorb unrelated changes. Stop if inspection cannot distinguish a fresh branch from an established branch or the branch cannot be committed without changing stack ownership.
- On a fresh tracked branch with zero commits ahead, use
- Submit the current branch only. For a new PR or existing draft, run
stax branch submit --draft --ai --yes. For an existing ready PR, runstax branch submit --ai --yesto preserve its ready-for-review state. Never use plainstax submit, which submits the full stack. - Validate the PR URL, base branch, and draft/ready state with
stax ll; validate the generated body withstax pr body; optionally recordstax ci. Confirm the submitted head contains the reviewed commit and the body names the evidence tier plus the no-docs rationale when applicable.
--yes accepts AI-generated details; it does not waive verification. Never merge, undraft, mark ready, reparent, or submit other branches without explicit user approval.
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.
- 21d ago First seen · 24 lines · 22 tokens per session scan A 50e5b74c57df
stax-release-manager is an agent published in the GitHub repository cesarferreira/stax (133 stars, last pushed 2d ago), licensed MIT. It adds 22 tokens to every session and 537 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 2026-10-17.
stax-release-manager compared with agents from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| stax-release-managercesarferreira/stax | Agent | 133 | 2d ago | MIT | A | 22 | Claude Code |
| pr-submittermalob/nix-config | Agent | 462 | 5d ago | MIT | A | 23 | Claude Code |
| git-workflow-masterCronusL-1141/AI-company | Agent | 374 | 10d ago | MIT | A | 27 | Claude Code |
| Shippersrnichols/plan-forge | Agent | 6 | 2d ago | MIT | A | 29 | Claude Code |
| git-workflowFortiumPartners/ensemble | Agent | 12 | yesterday | MIT | A | 29 | Claude Code |
| git-workflowborghei/Claude-Skills | Agent | 1.1k | 14d ago | none | A | 46 | Claude Code |
| git-flowjtprogru/bear-skills | Agent | 1 | 3d ago | MIT | A | 83 | Claude Code |