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 skills add XRenSiu/claude-code-forge --skill releasegit clone --depth 1 https://github.com/XRenSiu/claude-code-forgeWrote 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/xrensiu/claude-code-forge/release)<a href="https://agentmods.dev/skills/xrensiu/claude-code-forge/release"><img src="https://agentmods.dev/badge/skills/xrensiu/claude-code-forge/release.svg" alt="Measured on agentmods" 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 | $0.00200 | $0.01624 |
| Opus 5 | $0.00100 | $0.00812 |
| Sonnet 5 | $0.00040 | $0.00325 |
| Haiku 4.5 | $0.00020 | $0.00162 |
Grade A, and why
release 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 yesterday.
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 — 81 lines — stays where its author put it; the contents beside it link to each section on GitHub.
release — 合入不是终点,交付才是
产物:CHANGELOG.md 新条目、git tag vX.Y.Z、releases/vX.Y.Z.md(发布说明:变更 / 验证 / 回滚 / 逃逸缺陷入口)、
部署后验证记录。本文件写:发布在流水线里是什么、什么算交付完成、原语与出口、不可逆动作前的门。
用什么部署系统是你的份额(或仓库的事)。
缺口(Judgment + Control + Capability)
deletion 测试:撤掉本 skill,引擎在合入后说"完成"就停;没有版本、没有 changelog、部署了没验、出问题不知道 怎么回滚、线上反馈无处登记——世界层只在 G1 一处校准。缺的是产物序判据、不可逆动作(tag / push tag / deploy)前的确认门、和把机械半边编译掉的验证器。
世界(Σ)
- 版本从提交推导(Conventional Commits):范围内有
feat!/BREAKING CHANGE→ major;有feat→ minor; 只有fix/perf/其他 → patch。--bump auto就是这个规则;人可覆盖但要在发布说明写为什么。 - tag 与 changelog 是同一事实的两个投影:
CHANGELOG.md的## [X.Y.Z] - YYYY-MM-DD与 tagvX.Y.Z必须一致。 - 不可逆序(Σ 第 2 格):push tag、deploy 到生产、删旧版本——这些之前必须有回滚方案与确认。
- 部署后验证先于宣布完成:
--verify-cmd(健康检查 / 冒烟)绿了才是release.done=true;红了 → 回滚方案生效。 - 逃逸缺陷登记入口:发布说明末尾固定一段"发现问题?
/issue --escape并引用本版本"——线上反馈是世界层唯一的 外部校准源(参考文档 L8)。 - 关于用户的 Σ:"发一下"= 全套(tag + changelog + notes + verify);"只打 tag"= 仍要 changelog 条目一致;
"先不部署"=
release.skipped_reason留痕,不算交付完成。
判据(φ)
verify_release.py --version X.Y.Z:CHANGELOG 含该版本条目且日期合法;tag 存在(或--pre-tag模式下待打)且指向 merge sha;releases/vX.Y.Z.md含 Changes / Verification / Rollback / Escape 四段且 Rollback 非空;版本 ≥ 上一 tag; bump 与提交类型一致(--bump auto时)。- 部署验证:
--verify-cmdexit 0(或注明unverified: <原因>,此时release.done不能为 true)。 - 残差:回滚方案是否真的可执行(人判)。
原语(Π)
scripts/verify_release.py --version X.Y.Z [--changelog CHANGELOG.md] [--notes releases/vX.Y.Z.md] [--base <prev tag>] [--bump auto] [--pre-tag]—— exit 0 / 1 / 2。打 tag 前必须跑(--pre-tag),宣布完成前再跑一次(不带--pre-tag)。assets/release_notes_template.md·assets/changelog_entry_template.md。references/semver-and-rollback.md—— bump 规则、回滚方案的最小要素、部署验证清单。git tag -a vX.Y.Z -m …、git push origin vX.Y.Z、gh release create(存在性声明)。
门(γ)
- 打 tag / push tag / deploy 前给人看:展示版本、changelog 条目、发布说明、将执行的命令;确认再做。
--dry-run只产文件不打 tag 不部署。 - done_when:
verify_release.pyexit 0 ∧ verify-cmd 绿 ∧sdlc_state.py set release.version=… release.tag=… release.done=true。 - 在
/sdlc里:advance archive要求release.done=true或release.skipped_reason。
What ships with it
6 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- yesterday First seen · 81 lines · 200 tokens per session scan A 3c9aa8f7717b
release is a skill published in the GitHub repository XRenSiu/claude-code-forge (2 stars, last pushed today), licensed MIT. It adds 200 tokens to every session and 1,624 once invoked, about $0.0010 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 2026-09-05.
Other skills, from other repositories
release-announcement
Write a release announcement — changelog, blog post, in-app note, or social post — that leads with user impact, names the audience, and includes upgrade/migration steps without filler.
agent-release-swarm
Agent skill for release-swarm - invoke with $agent-release-swarm.
multi-agent-release-manager
Cleans up the workspace, formats code, runs presubmit checks, and uploads CLs to Gerrit.
release-notes
Generate user-facing release notes from tickets, PRDs, or changelogs. Creates clear, engaging summaries organized by category (new features, improvements, fixes). Use when writing release notes, creating changelogs, announcing product updates, or summarizing what shipped.
pack-submit
Package one of this agent's own skills as a standalone community pack and submit it to the aeon registry as a PR.
updater_guide
Guidance for checking for and installing Row-Bot updates.