agent-afk 3.80.7 → 3.81.1

package/README.md

@@ -1,8 +1,8 @@
 # Agent AFK
 
-> Past the happy path of AI coding.
+> Works while you're away.
 >
-> One prompt, one agent, one clean diff is the easy case. **Agent AFK** is the runtime for everything after — multi-session work, nested subagents, verification loops, and traces you can actually read. Local-first. Bring your own model.
+> Start a coding run before dinner. Agent AFK works locally, texts you when it's done or stuck, and leaves behind a PR, trace, and Telegram thread showing exactly what happened.
 
 [![npm version](https://img.shields.io/npm/v/agent-afk.svg)](https://www.npmjs.com/package/agent-afk)
 [![Node](https://img.shields.io/node/v/agent-afk.svg)](https://nodejs.org/)
@@ -13,13 +13,7 @@
 npm install -g agent-afk
 ```
 
-Requires Node ≥ 20. Then point it at an API key:
-
-```bash
-export ANTHROPIC_API_KEY=sk-ant-...
-# or, for Anthropic OAuth:
-afk login
-```
+Requires Node ≥ 20.
 
 Smoke test:
 
@@ -33,7 +27,9 @@ afk doctor       # environment self-check
 - **Chat from your terminal** — `afk chat "..."` for one-shot, `afk i` for a REPL with full tool access (Bash, file ops, web fetch, grep/glob, subagents).
 - **Hand long work off to a daemon** — `afk daemon` runs headless. Pair it with `send_telegram` and you get pings on your phone when work lands in a terminal state.
 - **Message Claude from Telegram** — `afk telegram setup` walks you through bot token + allowlist. After that you have a private chat surface backed by the same session manager as the REPL.
-- **Built-in orchestrators** — `/mint`, `/diagnose`, `/spec`, `/research`, `/ship`, `/review` dispatch subagent waves. `/mint` takes a feature idea and runs spec → research → plan → parallelize → build → verify → ship. `/diagnose` forks parallel root-cause hypotheses for failing tests and bugs. (Maintainer-loop skills like `/forge` and `/audit-fit` are hidden by default; set `AFK_INTERNAL=1` to surface them.)
+- **Built-in orchestrators** — `/mint`, `/diagnose`, `/spec`, `/research`, `/ship`, `/review` dispatch subagent waves. `/mint` takes a feature idea and runs spec → research → plan → parallelize → build → verify → ship. `/diagnose` forks parallel root-cause hypotheses for failing tests and bugs.
+
+> **Agent AFK Pro:** Autonomous skill-generation (`/forge`) and the calibrated skill-qualification rubric (`/qualify`) are reserved for Agent AFK Pro and are not part of the open-source build.
 - **Cross-session memory** — Claude remembers preferences, decisions, and procedures across runs. Backed by SQLite at `~/.afk/agent-framework/memory/` plus a `HOT.md` that injects into every future session's system prompt.
 - **Background tasks** — Ctrl+B in the REPL detaches the current turn into a tracked task; `/tasks` lists them, `/attach <id>` re-attaches.
 

package/dist/bundled-plugins/awa-bundled/skills/contract/SKILL.md

@@ -1,6 +1,6 @@
 ---
 name: contract
-description: "Reference convention for sub-agent I/O schemas. Loaded by orchestrator skills via /contract and into agents (e.g., qualify) via the `skills:` field."
+description: "Reference convention for sub-agent I/O schemas. Loaded by orchestrator skills via /contract and into agents via the `skills:` field."
 ---
 
 # Contract

package/dist/bundled-plugins/awa-bundled/skills/ground-claim/SKILL.md

@@ -10,7 +10,7 @@ Self-referential meta-capability questions about the current repository, framewo
 
 - "What does this repo enable?"
 - "What are the orchestration patterns available?"
-- "List the skills in private-framework."
+- "List the available skills."
 - "What capabilities does the plugin provide?"
 - "Show me what the framework can do."
 
@@ -25,11 +25,11 @@ Skip: usage questions ("how do I use X?"), bug reports, feature requests, techni
    - Read at least one concrete source file per capability. Record the file path and specific line numbers.
    - Do not rely on training data, model recall, or session-listing attachments. Evidence must come from Read tool output.
 
-3. **Build the answer inline.** As you write the response, embed citations **within claims**, not in a separate appendix. Format: `path/to/file.md:line—<claim context>`. Example: `agents/qualify.md:5—the qualify agent enforces a force-multiplier rubric`.
+3. **Build the answer inline.** As you write the response, embed citations **within claims**, not in a separate appendix. Format: `path/to/file.md:line—<claim context>`. Example: `skills/mint/SKILL.md:5—the mint skill orchestrates end-to-end feature delivery`.
 
 4. **Tag ungrounded claims.** If a capability claim cannot be traced to a file read, prefix it with `[UNVERIFIED: what would be needed to verify this]`. Never present an unverified claim without the tag.
 
-5. **Declare sources read.** Explicitly name which files you read in the response (e.g., "Read: `skills/mint/SKILL.md`, `agents/qualify.md`, `hooks/hooks.json`").
+5. **Declare sources read.** Explicitly name which files you read in the response (e.g., "Read: `skills/mint/SKILL.md`, `hooks/hooks.json`").
 
 ## Hard rules