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 skills/zelixag/ai-memex-cli/releasenpx skills add zelixag/ai-memex-cli --skill releasegit clone --depth 1 https://github.com/zelixag/ai-memex-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 | $0.00068 | $0.01787 |
| Opus 5 | $0.00034 | $0.00894 |
| Sonnet 5 | $0.00014 | $0.00357 |
| Haiku 4.5 | $0.00007 | $0.00179 |
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 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.
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 — 127 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Release ai-memex-cli
This skill drives the full publish pipeline for ai-memex-cli. It is invoked by the user (never proactively): npm publish is irreversible after 72h, GitHub Releases are public, and git tags propagate fast.
When to use
- User explicitly asks to release / publish / cut a new version
- Triggers (zh): "发版"、"发个新版本"、"上传新包"、"发布到 npm"、"打 tag"
- Triggers (en): "release", "publish", "ship a new version", "cut v0.3.0"
Do NOT trigger for: "ready to release?", "what's left before release?" — those are status questions, not commands.
Architecture
11 independent phase scripts under scripts/, each a Node .mjs runnable on its own. An orchestrator (scripts/orchestrator.mjs) chains them with confirmation prompts. pnpm release invokes the orchestrator.
Each phase prints a trailing line ::summary:: <json> on stdout — both the orchestrator and a driving agent can parse it to make decisions.
scripts/
├── orchestrator.mjs # pnpm release entry
├── 01-preflight.mjs # read-only checks
├── 02-sync-docs.mjs # invokes `claude -p` to update CHANGELOG/README/website
├── 03-bump-version.mjs # writes package.json
├── 04-build-all.mjs # pnpm build + (conditional) website → docs/
├── 05-test.mjs # pnpm test:run
├── 06-pack-preview.mjs # pnpm pack --dry-run + content audit
├── 07-git-finalize.mjs # commit + tag, local only
├── 08-publish.mjs # pnpm publish [--tag beta]
├── 09-git-push.mjs # push HEAD + tag
├── 10-github-release.mjs # gh release create (skipped for beta)
├── 11-verify.mjs # npm view + gh release view
└── _shared/ # log / shell / pkg / changelog helpers
Quick reference
| Goal | Command |
|---|---|
| patch stable | pnpm release |
| minor stable | pnpm release --bump minor |
| major stable | pnpm release --bump major |
| start a beta cycle | pnpm release --bump prepatch --beta |
| beta continuation | pnpm release --beta |
| graduate beta → stable | pnpm release --bump release |
| dry-run preview | pnpm release --dry-run |
| docs already match | pnpm release --manual-docs |
| CI / unattended | pnpm release --yes --push |
What ships with it
22 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.
- reference/beta-flow.md 3.2 KB
- reference/changelog-slicing.md 2.8 KB
- reference/github-release.md 2.6 KB
- reference/rollback.md 8.8 KB
- reference/windows-notes.md 3.3 KB
- reference/workflow.md 12 KB
- scripts/_shared/changelog.mjs 1.1 KB runs code
- scripts/_shared/log.mjs 1.2 KB runs code
- scripts/_shared/pkg.mjs 3.0 KB runs code
- scripts/_shared/shell.mjs 5.1 KB runs code
- scripts/01-preflight.mjs 4.5 KB runs code
- scripts/02-sync-docs.mjs 8.6 KB runs code
- scripts/03-bump-version.mjs 2.4 KB runs code
- scripts/04-build-all.mjs 4.5 KB runs code
- scripts/05-test.mjs 2.3 KB runs code
- scripts/06-pack-preview.mjs 3.8 KB runs code
- scripts/07-git-finalize.mjs 2.3 KB runs code
- scripts/08-publish.mjs 1.6 KB runs code
- scripts/09-git-push.mjs 1.6 KB runs code
- scripts/10-github-release.mjs 3.4 KB runs code
- scripts/11-verify.mjs 2.9 KB runs code
- scripts/orchestrator.mjs 14 KB runs code
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 · 127 lines · 68 tokens per session scan A e19ff8967880
release is a skill published in the GitHub repository zelixag/ai-memex-cli (9 stars, last pushed 3mo ago), licensed MIT. It adds 68 tokens to every session and 1,787 once invoked, about $0.0003 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 2026-08-31.
Other skills, from other repositories
wiki
LLM 维护的持久化 Markdown 知识库 —— 既可用作个人知识库（/wiki/）， 也可用于给开源项目做架构 wiki（ -wiki/）。 触发场景：用户说 "wiki"、"/wiki"、"添加到wiki"、"ingest"、"wiki lint"、 "wiki add"、"wiki query"、"wiki status"、"添加到知识库"、"导入这篇文章"、 "收藏这个"、"记到wiki里"、"建一个 wiki"、"给 X 做架构 wiki"。.
zenwiki-ask
Search this local ZenWiki and answer questions about its content with citations. Use this whenever the user asks anything about wiki topics — what / how / why / compare / list / which — that might be answered by pages under wiki/. Always run zenwiki search first; never answer from memory.
release
Prepare and publish stable Agent Lightning releases through the repository's version bump, pull-request checks, merge, tag, PyPI trusted-publishing, and versioned-documentation workflows. Use when asked to plan, cut, verify, or explain a release; treat nightly TestPyPI builds as a separate path.
release-notes
Generate user-facing release notes for Intelligent Terminal. Use when asked to write release notes, changelog, what-is-new summary, or prepare a release. Compares git commits between releases, looks up PR-linked issues and community contributors, then outputs formatted notes with "Verbed + Impact + Scenario" style…
release
Cut an AgentOS release via the scripts/publish flow. Use when the user asks to release, publish, cut a release, or bump the AgentOS version.
release-preview
Cut an AgentOS release-preview. Use when the user asks for a preview, release-preview, or a branch dist-tag build.