AgentConnect is an open-source platform that lets teams and multiple AI agents collaborate in shared conversations and work processes across services such as Slack, Telegram, Discord, GitHub, GitLab, and Linear. Teams use it to assign agents roles, have agents call one another, and start work from messages, issues, pull requests, webhooks, or schedules.
Borrowing it
Nothing to install: this file belongs to agentconnect-md/agentconnect. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/agentconnect-md/agentconnect/main/.claude/skills/agentconnect-release/SKILL.mdgit clone --depth 1 https://github.com/agentconnect-md/agentconnectWrote 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/agentconnect-md/agentconnect/agentconnect-release)<a href="https://agentmods.dev/skills/agentconnect-md/agentconnect/agentconnect-release"><img src="https://agentmods.dev/badge/skills/agentconnect-md/agentconnect/agentconnect-release/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.
<a href="https://agentmods.dev/skills/agentconnect-md/agentconnect/agentconnect-release"><img src="https://agentmods.dev/badge/skills/agentconnect-md/agentconnect/agentconnect-release.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00048 | $0.01847 |
| Opus 5.5 | $0.00019 | $0.00739 |
| Sonnet 5.5 | $0.00010 | $0.00369 |
| Haiku 4.5 | $0.00005 | $0.00185 |
Grade A, and why
agentconnect-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 1mo 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 — 152 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AgentConnect Release
Handle follow-up for published releases: verify publication, write a short English
## Summary above the existing notes, and close issues whose complete fixes shipped.
Default to agentconnect-md/agentconnect; respect an explicitly requested repository.
Scope
- Requests for examples, drafts, or "write the latest N" produce drafts in chat.
- An explicit request to update releases, including an existing authorized watcher, permits writing the summaries for that scope without asking again.
- Authorized release watches for
agentconnect-md/agentconnectinclude commenting on and closing verified fixes after stable publication succeeds. For other repositories, issue follow-up must be explicitly within scope. One-off summary requests do not change issues. - Creating or invoking this skill does not create a watcher, publish a new release, change versions, update docs and blogs, or start a historical issue sweep.
Establish the release scope
- Fetch current release records through authenticated GitHub tools or
gh. For "latest N," exclude drafts and prereleases unless requested, order bypublished_at, and paginate until the requested stable releases are covered. - Resolve each release tag and its preceding stable tag in the same release line. For a new major version, use the preceding major's last stable release. Use that release range, not current main or the immediately preceding RC.
- Read the existing notes and relevant merged PR descriptions; inspect the tagged diff when a title is ambiguous or a migration, removal, or security claim needs confirmation. Roadmap checkboxes and newer documentation do not prove a feature shipped in this release.
- Keep claims within the evidence. Distinguish newly introduced capabilities from later improvements. Link relevant docs or blogs only after checking the page and its applicability to the release.
Summary writing rules
- Always use exactly
## Summary. Do not alternate with Highlights, What's New, or Overview, or add a second Features/Fixes hierarchy inside the summary. - Write in English. For several meaningful changes, use
- **Feature Name** — One or two short sentences about what users can do.For a small release, one short paragraph or two is enough. Do not fill a quota. - Consolidate related PRs into a capability, such as Gitea Support, Agent Setup in Webchat, or Centralized Memory Management. Explain outcomes, not module names, protocol fields, storage tables, or a list of commit titles.
- Keep small interaction tweaks within a broader capability or omit them from the summary. Mention important fixes briefly. Dependency bumps, CI changes, tests, and refactors stay in the technical notes unless users need to act.
- Select by user impact, not the generated changelog category: an Internal entry can contain a removal users need to know, while a feat entry may be too small for a headline.
- Include concrete removals, changed defaults, migrations, or required upgrade actions as a short paragraph starting Behavior change:, Subscription change:, or Upgrade note: within the Summary. Do not invent instructions or claim that an upgrade requires no action without evidence.
- Omit the generated version/date heading; GitHub already displays both. Remove only that redundant heading when editing existing notes.
- Keep the original detailed notes below the summary. GitHub Releases are the canonical version record; a docs Updates page can reuse it. Blogs cover major releases or worthwhile product stories and are not required for every version.
What ships with it
2 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.
- 1mo ago First seen · 152 lines · 48 tokens per session scan A 7da108da6798
agentconnect-release is a skill published in the GitHub repository agentconnect-md/agentconnect (1,520 stars, last pushed today), licensed Apache-2.0. It adds 48 tokens to every session and 1,847 once invoked, about $0.0002 per session on Opus 5.5. 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 2026-09-29.
agentconnect-release compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| agentconnect-releaseagentconnect-md/agentconnect | Skill | 1.5k | today | Apache-2.0 | A | 48 | Claude Code, Codex |
| agent-framework-py-releasemicrosoft/agent-framework | Skill | 15k | yesterday | MIT | A | 102 | Claude Code, Codex |
| oma-dev-workflowfirst-fluke/oh-my-agent | Skill | 1.4k | yesterday | MIT | A | 29 | Claude Code |
| aiwg-prjmagly/aiwg | Skill | 229 | yesterday | MIT | A | 25 | Claude Code, Codex |
| artifact-metadatajmagly/aiwg | Skill | 229 | yesterday | MIT | A | 21 | Claude Code, Codex |
| git-mirror-auditjmagly/aiwg | Skill | 229 | yesterday | MIT | A | 22 | Claude Code, Codex |
| launchsimota/agent-skills | Skill | 98 | 11d ago | MIT | A | 40 | Claude Code, Codex |