obot: Skill for Claude Code

.claude/skills/draft-release-blog/SKILL.md

draft-release-blog is a skill for Claude Code from obot-platform/obot. It costs 101 tokens per session (4,421 once invoked), scanned A, original, MIT.

A writing procedure for preparing a release announcement for an obot software version, using existing obot blog posts as a style reference. It normally creates a Markdown draft for review.

In plain words
What is it for?
Use it to gather features from a draft GitHub release, research supporting details, and prepare a blog draft or, when explicitly requested, a WordPress draft.
Why use it?
It adds the context and explanation that short release notes often leave out.

Skill for Claude Code

Written for Claude Code: $CLAUDE_PROJECT_DIR variable. Also seen: names the AskUserQuestion tool; mentions Claude Code; mentions Codex.

This is obot-platform/obot's own configuration. It tells Claude Code how to work on obot itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything obot configures →

About the project

Obot is an open-source platform that helps organizations manage, secure, and govern AI clients, models, tools, MCP servers, skills, credentials, and hosted workloads. It is for teams that need controlled access, identity and permissions, sandboxed execution, registries, and audit records across agents such as Claude Code, Codex, Cursor, and IDE tools. The catalogue entries supply skills and instructions that can be managed or used within the Obot platform.

obot-platform/obot · 1,167 stars · on GitHub · obot.ai

Reuse

Borrowing it

Nothing to install: this file belongs to obot-platform/obot. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/obot-platform/obot/main/.claude/skills/draft-release-blog/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/obot-platform/obot

Made for: Claude Code.

Wrote 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.

agentmods badge for draft-release-blog

README.md
[![agentmods](https://agentmods.dev/badge/skills/obot-platform/obot/draft-release-blog/github.svg)](https://agentmods.dev/skills/obot-platform/obot/draft-release-blog)
Your own site
<a href="https://agentmods.dev/skills/obot-platform/obot/draft-release-blog"><img src="https://agentmods.dev/badge/skills/obot-platform/obot/draft-release-blog/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.

agentmods 80×15 button for draft-release-blog

Your own site · 80×15
<a href="https://agentmods.dev/skills/obot-platform/obot/draft-release-blog"><img src="https://agentmods.dev/badge/skills/obot-platform/obot/draft-release-blog.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 101 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 4,421 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00101 $0.04421
Opus 5.5 $0.00040 $0.01768
Sonnet 5.5 $0.00020 $0.00884
Haiku 4.5 $0.00010 $0.00442

Measured 17d ago against content hash 4881e52da445, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

draft-release-blog scanned grade A with 1 finding 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 17d ago.

The scan reads SKILL.md. This mod also ships 1 executable file (md_to_html.py), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

cat_id=$(curl -s "https://obot.ai/wp-json/wp/v2/categories?slug=product-updates&_fields=id" | jq '.[0].id')
.claude/skills/draft-release-blog/SKILL.md · 236 lines

How it starts

The opening of the file, as written. The whole thing — 236 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Draft Release Blog Post

Drafts a blog post announcing an obot release. Sources the feature spine from the draft GitHub release (the output of the draft-release skill or an existing draft on GitHub), then does additional research to add the kind of detail, context, and rationale that release notes deliberately omit but a blog post needs.

The blog is for obot.ai's hosted Wordpress CMS. The default output is a markdown file at <repo root>/release-blog-<VERSION>.md (i.e. the current project directory) that the user can paste into the CMS themselves. Writing it into the repo makes it easy to review in the IDE; it is an intentionally untracked file — do not commit it and do not add it to .gitignore. If the user explicitly asks to post it (e.g. "post it up there", "create the draft in Wordpress"), the skill can also create the post as a Wordpress draft via the obot-wordpress MCP server (see step 8). The skill never publishes a live post without explicit user confirmation of the publish status.

Voice reference

Before drafting, every time, read the two most recent release announcement posts on obot.ai. They are the reference for voice, structure, and the "Get started" links. Find them through the public Wordpress REST API: release posts are in the Product Updates category and their slugs start with announcing-obot and contain the version (v0-25-0, v-0-26-0). Titles are not reliable, since some release posts do not put the version in the title.

cat_id=$(curl -s "https://obot.ai/wp-json/wp/v2/categories?slug=product-updates&_fields=id" | jq '.[0].id')
curl -s "https://obot.ai/wp-json/wp/v2/posts?categories=${cat_id}&per_page=20&orderby=date&order=desc&_fields=date,slug,link,title" \
  | jq -r '[.[] | select(.slug | test("^announcing-obot.*v-?[0-9]+-[0-9]+-[0-9]+"))][:2][] | "\(.date) \(.link) \(.title.rendered)"'

Then fetch each post's body from the same API (/wp-json/wp/v2/posts?slug=<slug>&_fields=content) and strip the HTML tags. This returns the full text, while WebFetch only returns a summary. Note each post's word count, section headings, opener, and the exact link targets in its closing section.

Read the full file on GitHub · 236 lines

Files

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.

Changes

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.

  1. 17d ago Changed · +7 lines 4881e52da445
  2. 2mo ago First seen · 229 lines · 101 tokens per session scan A 68de8729a9a7

Subscribe to this mod's changes

draft-release-blog is a skill published in the GitHub repository obot-platform/obot (1,167 stars, last pushed yesterday), licensed MIT. It adds 101 tokens to every session and 4,421 once invoked, about $0.0004 per session on Opus 5.5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

draft-release-blog compared with skills from other repositories

draft-release-blog next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
draft-release-blogobot-platform/obotSkill1.2kyesterdayMITA101Claude Code
prompt-designbasementstudio/xmcpSkill1.3k9d agoMITA22Claude Code, Codex
claude-code-dmworkMininglamp-OSS/octo-serverSkill1.1k2d agoApache-2.0A0Claude Code, Codex
octocode-subagentbgauryy/octocodeSkill9572d agoMITA80Claude Code, Codex
octocode-roastbgauryy/octocodeSkill9572d agoMITA71Claude Code, Codex
dataforseo-mcp-serverdataforseo/mcp-server-typescriptSkill2604d agoApache-2.0A46Claude Code, Codex
cometchat-android-v6-compose-placementcometchat/cometchat-skillsSkill16222d agoMITA127Claude Code