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/modelstudioai/cli/changelog-writegit clone --depth 1 https://github.com/modelstudioai/cliWhat 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 | $0.02056 |
| Opus 5 | $0.00000 | $0.01028 |
| Sonnet 5 | $0.00000 | $0.00411 |
| Haiku 4.5 | $0.00000 | $0.00206 |
Grade A, and why
changelog-write 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 — 188 lines — stays where its author put it; the contents beside it link to each section on GitHub.
撰写 Change Log
触发条件
- 发布新版本(beta / rc / stable)后,需要为这个版本写一份 release notes
- 补写历史版本遗漏的 changelog
发布位置
更新仓库内的两份文件,英文优先,中文同步:
新版本条目插在文件顶部"## [X.Y.Z] - YYYY-MM-DD"位置,旧版本依次向下保留。两份文件保持一一对应——任何条目只在一份里出现,另一份漏写,视为错误。
输出格式:Keep a Changelog
本项目采用 Keep a Changelog 规范,标准 6 段(按出现顺序):
| 段名 | 含义 | 示例 |
|---|---|---|
Added |
新增功能 / 命令 / 参数 | 新增 bl app list |
Changed |
已有功能行为/形式变化(非破坏) | --page-num 改名 --page |
Deprecated |
即将移除但当前仍可用 | --legacy-flag 弃用,下个版本移除 |
Removed |
本版本删除的能力 | 移除 --instructions |
Fixed |
Bug 修复 | 修复视频生成模型错误 |
Security |
安全相关修复 | 修复凭据明文落盘 |
项目扩展段:Internal(放研发体系 / 工具链 / 测试基建,与用户无关但值得记录的工程改动)。
某段没内容就直接省略,不要写"无"。
撰写步骤
1. 确定版本边界
通过 package.json 的版本号变更找出两个版本的 commit 边界:
# 找出 packages/cli/package.json 历次版本变更
git log --all --oneline --pretty=format:'%h %ad %s' --date=short \
-G '"version"' -- packages/cli/package.json | head
记下:
prevBumpCommit— 上一个版本号 bump commit(如1.0.0的 commit)currBumpCommit— 当前版本号 bump commit(如1.0.1的 commit)
本版本内容 = git log prevBumpCommit..currBumpCommit。
2. 列出本版本所有 commit
git log <prevBumpCommit>..<currBumpCommit> --no-merges \
--pretty=format:'%h %ad %s' --date=short
注意:用
--no-merges过滤 merge commit,避免重复条目。
3. 逐条核对 commit 是否真的进了本版本
merge 顺序复杂时,commit 标题在但内容未必合入。用 git merge-base --is-ancestor 严格验证:
git merge-base --is-ancestor <featureCommit> <releaseCommit> \
&& echo "IN" || echo "NOT IN"
例:验证 agent chat(commit 12f2b1b)是否在 1.0.0(commit 3fc54ae)里:
git merge-base --is-ancestor 12f2b1b 3fc54ae && echo "IN" || echo "NOT IN"
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 · 188 lines · 0 tokens per session scan A b1828e19a214
changelog-write is an agent published in the GitHub repository modelstudioai/cli (320 stars, last pushed 4d ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 2,056 tokens. 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
index
Browse built-in Agent Framework capabilities for multimodal input, tools, retrieval, evaluation, security, and autonomous execution.
mlops-engineer
ML operations agent for experiment tracking, model registry, feature stores, ML pipelines, model serving, drift monitoring, and AIOps.
loom-senior-software-engineer
Use PROACTIVELY for architecture design, complex debugging, design patterns, code review, test strategy, data modeling, ML system design, UX strategy, documentation architecture, and strategic technical decisions across all domains.
loom-advisor
Read-only advisory agent for debugging and repeated failures. Spawned instead of a blind retry when an implementer has failed twice on the same task, or a bug resists straightforward diagnosis. Returns a root-cause diagnosis plus one concrete next step.
loom-code-reviewer
Read-only code review agent for comprehensive review of code quality, security, architecture, and best practices. Cannot modify files.
integrity-check
Detect adversarial content in .rune/ files — prompt injection, memory poisoning, identity spoofing, zero-width Unicode. Verdict: CLEAN/SUSPICIOUS/TAINTED.