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/elastic/elastic-docs-skills/docs-stack-releasenpx skills add elastic/elastic-docs-skills --skill docs-stack-releasegit clone --depth 1 https://github.com/elastic/elastic-docs-skillsWhat 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 | $0.00110 | $0.06896 |
| Opus 5 | $0.00055 | $0.03448 |
| Sonnet 5 | $0.00022 | $0.01379 |
| Haiku 4.5 | $0.00011 | $0.00690 |
Grade A, and why
docs-stack-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 — 386 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Docs release issue ([Docs release] X.Y.Z in elastic/dev) is the source of truth -- not the eng [Release] issue. Create missing docs issues (§1.1) or collect dates from the user. Missing issue URLs: (issue TBD).
Playbooks: v9 -- v8. Templates: minor -- 9.x patch -- 8.x patch.
| Line | Repo | Config files | Deploy watch |
|---|---|---|---|
| 9.x+ | elastic/docs-builder |
config/assembler.yml, config/versions.yml |
docs-internal-workflows bump PRs + prod version-bump (§0.3) |
| 8.x / 7.x | elastic/docs |
shared/versions/stack/*.asciidoc, conf.yaml |
None -- do not use docs-internal-workflows |
Invariants
- IDs, dates, PR URLs, @mentions: from
gh, the docs issue, Slack, or the user. Never invent. Missing →(issue TBD)or[@handle]and ask. - Never mix 8.x and 9.x in one PR. 8.x/7.x:
elastic/docsonly; nodocs-internal-workflows. - Checklist is the step index. Live-fetch only open work. RN merge is not a checkbox -- always
gh pr viewblocking RN URLs. - A PR URL in the RN table is blocking until merged. Skip only
No changes/N/A. Do not exempt Fleet, Agent, or any product by name. - Check boxes this skill just completed. Do not check anyone else's work (including docs-eng). Do not wait to be asked.
- Slack:
<@USER_ID>only; show a preview and confirm before send; thread follow-ups on the FF announcement. Read slack-templates.md before drafting or sending. - Live/released Slack only after the gate (§0.3) and a user eyeball of the site. Do not draft before the gate.
- Empty args / "how's my release": session state → active docs issue. Do not ask which version if one is in flight. After closed-issue cleanup leaves none, stop -- do not rediscover.
- Cleanup = docs issue
CLOSEDonly. 404 = drop that ID and rediscover. No TTL. - RC varies each release -- read from the
#mission-controlcoordination thread or eng issue. Never hardcode a name. - Do not offer a Slack ping or PR whose issue box is already checked, or that the user already said they sent.
What ships with it
1 file 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.
- 2d ago First seen · 386 lines · 110 tokens per session scan A c428b242d725
docs-stack-release is a skill published in the GitHub repository elastic/elastic-docs-skills (71 stars, last pushed 4d ago), licensed Apache-2.0. It adds 110 tokens to every session and 6,896 once invoked, about $0.0006 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 skills, from other repositories
codex-docs-drift-scout
Install the AutoHub docs-drift Codex automation from signed AutoVault skill resources and audit its render fidelity with autovault doctor.
writing-docs
Skill "writing-docs" from Wade-DevCode/awesome-coding-skills-cn, covering 写文档, 何时用, 核心规则, 1. 开头讲"这是什么、解决什么问题、给谁用",30 秒能判断要不要继续读 and 2. 快速开始可复制即用:安装命令、最小示例,真实可跑.
pr-description
写 Pull Request 描述时使用。让 reviewer 快速理解与审查。.
writing-skills
How to write, split, and review docs/skills/ files in testsuite. Load when creating, editing, or deleting a skill.
bun-test
Complete guide to Bun's native test runner: writing tests, expect matchers, mocks, spies, lifecycle hooks, snapshots, code coverage, reporters, DOM testing, and test configuration.
bun-runtime-http
Covers Bun.serve, HTTP server configuration, routing, streaming responses, WebSockets, TLS/SSL, and middleware with Bun's native APIs.