claude-teammate 0.1.26 → 0.1.28

package/README.md

@@ -17,12 +17,16 @@
   <a href="https://github.com/ignify-rd/claude-teammate/blob/main/LICENSE"><img src="https://img.shields.io/badge/license-MIT-blue" alt="MIT License" /></a>
 </p>
 
-# An autonomous software engineer that lives in your Jira and GitHub
+<h1 align="center">An autonomous software engineer<br />that lives in your Jira and GitHub</h1>
 
 Claude Teammate is an AI bot that works around the clock - picking up tickets, writing plans, opening PRs, acting on feedback, and reviewing code. No stand-ups. No Slack pings. No passive-aggressive "per my last email." Just like your best teammate, minus the coffee breath.
 
 Assign it tickets. It ships.
 
+<p align="center">
+  <img src="assets/demo.gif" alt="Demo" width="640" style="border: 1px solid #d1d5db;" />
+</p>
+
 |        | Step               | What happens                                                                                          |
 | ------ | ------------------ | ----------------------------------------------------------------------------------------------------- |
 | **01** | Assign the ticket  | Assign the Jira ticket to the bot.                                                                    |
@@ -30,8 +34,6 @@ Assign it tickets. It ships.
 | **03** | It ships           | Opens a PR. Responds to feedback. Keeps going until it's merged.                                      |
 | **04** | It remembers       | Retains build commands, known pitfalls, and lessons from every task it has shipped - so the next ticket in the same epic starts smarter. |
 
-![Demo](assets/demo.gif)
-
 <br/>
 
 ## Claude Teammate is right for you if
@@ -104,7 +106,15 @@ tm8 start
 
 `start` creates `~/.tm8/.env` on the first run. If that config already exists with the required values, setup is skipped and your credentials are not prompted for again.
 
-To run multiple agents on the same machine, use `--local` to store agent status and memory in the current working folder.
+```env
+# .env file generated by `tm8 start`
+JIRA_BASE_URL=https://yourorg.atlassian.net
+JIRA_BOT_EMAIL=bot@yourorg.com
+JIRA_BOT_API_TOKEN=...
+GITHUB_PAT=ghp_...
+```
+
+To run multiple agents on the same machine, use `--local` to store agent status and memory in the current working directory.
 
 To upgrade to latest version
 
@@ -119,7 +129,7 @@ tm8 status
 tm8 stop
 ```
 
-Global runtime files and memory are stored in:
+Runtime files and memory are stored in:
 
 ```text
 ~/.tm8/
@@ -136,20 +146,6 @@ Global runtime files and memory are stored in:
             └── issue-{jira-key}.md
 ```
 
-With `--local`, the same `.claude-teammate/` and `memory/` folders are created in the current working directory instead.
-
-`epic-{jira-key}.md` stores shared epic facts such as canonical epic identity, related repositories, reusable summaries, and guardrails. `issue-{jira-key}.md` stores issue-specific workflow state, clarification history, and GitHub issue tracking.
-
-The worker polls Jira once per minute. It transitions `To Do` issues to `In Progress`, asks for repo URLs when epic memory lacks them, clones all referenced repos into `.claude-teammate/repos/`, uses Claude CLI to clarify requirements from Jira comments across those repos, and creates GitHub issues once the requirements are clear enough.
-
-```env
-# .env file generated by `tm8 start` or `tm8 start --local`
-JIRA_BASE_URL=https://yourorg.atlassian.net
-JIRA_BOT_EMAIL=bot@yourorg.com
-JIRA_BOT_API_TOKEN=...
-GITHUB_PAT=ghp_...
-```
-
 <br/>
 
 ## FAQ
@@ -166,18 +162,17 @@ Yes. Each epic is scoped to its own Jira domain and workspace, and can map to on
 **Does it understand the codebase or just generate generic code?**
 It reads the actual repository before writing anything - structure, conventions, existing patterns. The plan it proposes is specific to your code, not a template.
 
+**Can I use Claude skills or MCP, and does it respect `CLAUDE.md`?**
+Yes. Claude skills, configured MCP servers, and repo instructions in `CLAUDE.md` are available and respected just like they are in a normal Claude-driven workflow. Playwright MCP is built in and enabled by default so challenging frontend tasks can be verified in-browser.
+
 <br/>
 
 ## Roadmap
 
+- Ensure no conflicts for multiple concurrent claude-teammate agents
 - GitLab support
 - Bitbucket support
-- Ensure no conflicts for multiple concurrent claude-teammate agents
-- Slack and Teams notifications when PRs are opened or merged
-- Automatic PR description generation from commit history and issue context
-- Branch-naming convention enforcement per epic or project config
-- Stale-issue nudges when tickets sit unactioned past a configurable threshold
-- Test-coverage gating before issue closure
+- Slack and Teams integration
 
 <br/>
 

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "claude-teammate",
-  "version": "0.1.26",
+  "version": "0.1.28",
   "description": "CLI bootstrapper for Claude Teammate.",
   "license": "MIT",
   "type": "module",

package/src/claude.js

@@ -1074,7 +1074,7 @@ Instructions:
 - Implement the plan described in the pull request body.
 - Smart quotes and em/en dashes are not allowed. Use: smart quotes -> ", em/en dashes -> -.
 - If the latest human PR comment requests a change or reports a problem, address that feedback as part of this implementation run.
-- If this involves frontend behavior, infer how to start the app from the repository code, launch it locally, and verify the implementation with Playwright MCP.
+- If this involves challenging frontend fixes/implementations, infer how to start the app from the repository code, launch it locally, and verify the implementation with Playwright MCP.
 - Do not commit or push; leave modified files in the working tree.
 - Return summary as 1-2 sentences suitable to post directly as a PR comment.
 - Return epic_facts and epic_guardrails only for reusable non-obvious repo or epic knowledge. Use epic_facts for durable factual notes such as build commands or stable repo behavior. Leave them empty when there is nothing worth remembering.