agent-notes 2.29.0__tar.gz → 2.32.0__tar.gz

{agent_notes-2.29.0 → agent_notes-2.32.0}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: agent-notes
-Version: 2.29.0
+Version: 2.32.0
 Summary: AI agent configuration manager for Claude Code, OpenCode, and Copilot
 Author-email: Eugene Naumov <min.verkligheten@gmail.com>
 License-Expression: MIT
@@ -44,8 +44,8 @@ agent-notes doctor
 
 **What's Included**
 - 19 specialized AI subagents (Opus reasons, Sonnet executes, Haiku explores)
-- 47+ on-demand skills (Rails, Docker, Git, Kamal, Process)
-- Global rules and guardrails
+- 50+ on-demand skills (Rails, Docker, Git, Kamal, Process)
+- Global rules and guardrails (including a ban on AI self-attribution in commits/PRs)
 - Agent memory with 3 storage options (Local, Obsidian, Wiki)
 - Configuration for Claude Code, OpenCode, and GitHub Copilot
 
@@ -63,12 +63,6 @@ pipx install agent-notes
 agent-notes install
 ```
 
-Update anytime:
-
-```bash
-pipx upgrade agent-notes && agent-notes install
-```
-
 **venv + pip (if you prefer to manage your own environment):**
 
 ```bash
@@ -77,12 +71,34 @@ pip install agent-notes
 agent-notes install
 ```
 
-Update anytime:
+### Upgrade from a previous version
+
+**Update in place (normal upgrade):**
+
+With pipx:
+```bash
+pipx upgrade agent-notes && agent-notes install
+```
 
+With venv:
 ```bash
 pip install --upgrade agent-notes && agent-notes install
 ```
 
+**Clean reinstall (from an older version, fresh slate):**
+
+If you are on a significantly older version or want a fresh configuration, uninstall completely and reinstall:
+
+With pipx:
+```bash
+agent-notes uninstall && pipx uninstall agent-notes && pipx install agent-notes && agent-notes install
+```
+
+With venv:
+```bash
+agent-notes uninstall && pip uninstall agent-notes && pip install agent-notes && agent-notes install
+```
+
 ### Local build (developers)
 
 ```bash
@@ -119,6 +135,36 @@ agent-notes config provider openrouter   # prints "configured" or "no key"
 
 </details>
 
+<details>
+<summary>Uninstall</summary>
+
+To fully remove agent-notes:
+
+**pipx:**
+
+```bash
+agent-notes uninstall
+pipx uninstall agent-notes
+```
+
+Run `agent-notes uninstall` first — it removes agent files, hooks, settings.json entries, context file, and state that agent-notes installed. Then `pipx uninstall` removes the package itself. The `agent-notes uninstall` command must run while the CLI is still installed.
+
+**venv:**
+
+```bash
+agent-notes uninstall
+deactivate
+rm -rf .venv
+```
+
+Run `agent-notes uninstall` first to clean up installed components, then deactivate the environment and delete the `.venv` directory.
+
+**Note on memory and vault permissions:**
+
+If you configured agent-notes to access your memory vault (Obsidian or local), those read/write permissions are intentionally left in place after uninstalling so Claude Code and other tools can still access your notes. To remove them, edit `~/.claude/settings.json` and delete the entries under `permissions.allow` that reference your vault path (e.g. `Read(/path/to/your/vault/**)`, `Write(/path/to/your/vault/**)`, `Edit(/path/to/your/vault/**)`).
+
+</details>
+
 ---
 
 <details>
@@ -236,7 +282,7 @@ agent-notes memory lint               # health-check
 <details>
 <summary>Skills</summary>
 
-47+ on-demand knowledge modules across Rails, Docker, Kamal, Git, and Process. Run `agent-notes list skills` for the current list, or browse `agent_notes/data/skills/`.
+50+ on-demand knowledge modules across Rails, Docker, Kamal, Git, and Process. Run `agent-notes list skills` for the current list, or browse `agent_notes/data/skills/`.
 
 The session context hook auto-generates a skill index from SKILL.md frontmatter at install time, so agents always know what skills are available without loading full skill content. This keeps context overhead low while maintaining skill discoverability.
 
@@ -251,26 +297,29 @@ Load the docker-compose skill for multi-service setup
 
 | Failure mode | What goes wrong | Skills that help |
 |---|---|---|
-| Misalignment | Claude starts building before the problem is resolved | `/grill-me`, `/grill-with-docs` |
-| Verbosity | Responses are bloated; context window fills with noise | `/caveman`, `/setup-project-context` |
-| Broken code | Claude codes without a feedback loop or evidence trail | `/tdd` (improved), `/debugging-protocol` (improved) |
-| Ball of mud | Architecture drifts; modules grow shallow and tangled | `/improve-codebase-architecture`, `/zoom-out` |
+| Misalignment | Claude starts building before the problem is resolved | `/grill-me`, `/grilling`, `/grill-with-docs` |
+| Vague scope | Work starts without a spec or ticketed breakdown | `/to-spec`, `/to-tickets`, `/wayfinder`, `/triage` |
+| Broken code | Claude codes without a feedback loop or evidence trail | `/tdd`, `/diagnosing-bugs` |
+| Ball of mud | Architecture drifts; modules grow shallow and tangled | `/improve-codebase-architecture`, `/codebase-design`, `/domain-modeling` |
 
 **Skill descriptions:**
 
-- `/grill-me` — Interview the user until the problem is fully resolved before touching code
+- `/grill-me`, `/grilling` — Interview the user relentlessly until the plan is fully resolved before touching code
 - `/grill-with-docs` — Same, but cross-references CONTEXT.md and ADRs and updates them inline
-- `/caveman` — Ultra-compressed reply mode (~75% token savings) for rapid iteration
-- `/setup-project-context` — Bootstraps a CONTEXT.md domain glossary (ubiquitous language)
-- `/tdd` — RED-GREEN-REFACTOR with tracer-bullet vertical slices; horizontal-slicing anti-pattern added
-- `/debugging-protocol` — Phase 1 rewritten as "build a feedback loop first" with 9 strategies
-- `/improve-codebase-architecture` — Deletion test to find shallow modules; surfaces deepening opportunities
-- `/zoom-out` — Quick orientation map of an unfamiliar code area
+- `/tdd` — RED-GREEN-REFACTOR with tracer-bullet vertical slices; integration-first testing
+- `/diagnosing-bugs` — Diagnosis loop for hard bugs and performance regressions (build a feedback loop first)
+- `/improve-codebase-architecture` — Scan for deepening opportunities, present a visual HTML report, then grill the chosen one
+- `/codebase-design` — Shared vocabulary for designing deep modules and choosing where seams go
+- `/domain-modeling` — Pin down ubiquitous language, maintain a CONTEXT.md glossary and ADRs
 - `/handoff` — Compact conversation into a handoff document for a fresh agent session
-- `/to-prd` — Synthesize conversation into a Product Requirements Document
-- `/to-issues` — Break a plan/PRD into vertical-slice issues (HITL/AFK classification)
+- `/to-spec` — Synthesize the current conversation into a spec and publish it to the issue tracker
+- `/to-tickets` — Break a plan/spec into tracer-bullet tickets with declared blocking edges
+- `/wayfinder` — Plan work larger than one agent session as a map of investigation tickets
+- `/triage` — Move issues and external PRs through a triage state machine into agent-ready briefs
+- `/research` — Investigate a question against primary sources and capture findings as Markdown
 - `/prototype` — Throwaway prototypes: terminal app for logic or UI variations for visual
-- `/write-a-skill` — Meta-skill for creating new skills with proper structure
+- `/setup-agent-tracker` — One-time per-repo setup of the issue tracker, triage labels, and domain doc layout
+- `/writing-great-skills` — Reference for writing and editing skills well
 
 </details>
 
@@ -409,6 +458,8 @@ By default, `agent-notes install` re-runs the interactive wizard and prompts for
 
 The plugin build scripts (`scripts/build-claude-plugin.sh`, `scripts/build-opencode-plugin.sh`) automatically use `.venv/bin/python` when present, fall back to system `python3`, and honor a `PYTHON=` override.
 
+**Note:** `uv` is used only in the local development and release workflow (see `scripts/release`). It is not required to install or use agent-notes — end users should use `pipx` or `pip` / `venv`.
+
 ### Test structure
 
 - `tests/functional/` — Unit tests
@@ -461,7 +512,7 @@ See [docs/ARCHITECTURE.md](docs/ARCHITECTURE.md), [docs/ADD_CLI.md](docs/ADD_CLI
 ## Inspired by
 
 - [Andrej Karpathy's LLM Wiki](https://gist.github.com/karpathy/442a6bf555914893e9891c11519de94f) — The wiki memory backend implements his compile-once, query-forever knowledge pattern with structured page types and three core operations (ingest, query, lint)
-- [Matt Pocock's skills repo](https://github.com/mattpocock/skills) — Skill format (SKILL.md per directory), failure-mode table (misalignment, verbosity, broken code, architectural degradation), and several core skills (tdd, grill-me, grill-with-docs, improve-codebase-architecture, zoom-out, caveman)
+- [Matt Pocock's skills repo](https://github.com/mattpocock/skills) — Skill format (SKILL.md per directory), failure-mode table (misalignment, broken code, architectural degradation), and a set of engineering/productivity skills vendored from the upstream repo (tdd, grill-me, grilling, grill-with-docs, diagnosing-bugs, improve-codebase-architecture, codebase-design, domain-modeling, prototype, handoff, research, to-spec, to-tickets, triage, wayfinder, writing-great-skills). Last synced from upstream commit [`391a270`](https://github.com/mattpocock/skills/commit/391a2701dd948f94f56a39f7533f8eea9a859c87) (2026-07-10), reviewed for prompt-injection before import.
 
 ## License
 

{agent_notes-2.29.0 → agent_notes-2.32.0}/README.md

@@ -12,8 +12,8 @@ agent-notes doctor
 
 **What's Included**
 - 19 specialized AI subagents (Opus reasons, Sonnet executes, Haiku explores)
-- 47+ on-demand skills (Rails, Docker, Git, Kamal, Process)
-- Global rules and guardrails
+- 50+ on-demand skills (Rails, Docker, Git, Kamal, Process)
+- Global rules and guardrails (including a ban on AI self-attribution in commits/PRs)
 - Agent memory with 3 storage options (Local, Obsidian, Wiki)
 - Configuration for Claude Code, OpenCode, and GitHub Copilot
 
@@ -31,12 +31,6 @@ pipx install agent-notes
 agent-notes install
 ```
 
-Update anytime:
-
-```bash
-pipx upgrade agent-notes && agent-notes install
-```
-
 **venv + pip (if you prefer to manage your own environment):**
 
 ```bash
@@ -45,12 +39,34 @@ pip install agent-notes
 agent-notes install
 ```
 
-Update anytime:
+### Upgrade from a previous version
+
+**Update in place (normal upgrade):**
+
+With pipx:
+```bash
+pipx upgrade agent-notes && agent-notes install
+```
 
+With venv:
 ```bash
 pip install --upgrade agent-notes && agent-notes install
 ```
 
+**Clean reinstall (from an older version, fresh slate):**
+
+If you are on a significantly older version or want a fresh configuration, uninstall completely and reinstall:
+
+With pipx:
+```bash
+agent-notes uninstall && pipx uninstall agent-notes && pipx install agent-notes && agent-notes install
+```
+
+With venv:
+```bash
+agent-notes uninstall && pip uninstall agent-notes && pip install agent-notes && agent-notes install
+```
+
 ### Local build (developers)
 
 ```bash
@@ -87,6 +103,36 @@ agent-notes config provider openrouter   # prints "configured" or "no key"
 
 </details>
 
+<details>
+<summary>Uninstall</summary>
+
+To fully remove agent-notes:
+
+**pipx:**
+
+```bash
+agent-notes uninstall
+pipx uninstall agent-notes
+```
+
+Run `agent-notes uninstall` first — it removes agent files, hooks, settings.json entries, context file, and state that agent-notes installed. Then `pipx uninstall` removes the package itself. The `agent-notes uninstall` command must run while the CLI is still installed.
+
+**venv:**
+
+```bash
+agent-notes uninstall
+deactivate
+rm -rf .venv
+```
+
+Run `agent-notes uninstall` first to clean up installed components, then deactivate the environment and delete the `.venv` directory.
+
+**Note on memory and vault permissions:**
+
+If you configured agent-notes to access your memory vault (Obsidian or local), those read/write permissions are intentionally left in place after uninstalling so Claude Code and other tools can still access your notes. To remove them, edit `~/.claude/settings.json` and delete the entries under `permissions.allow` that reference your vault path (e.g. `Read(/path/to/your/vault/**)`, `Write(/path/to/your/vault/**)`, `Edit(/path/to/your/vault/**)`).
+
+</details>
+
 ---
 
 <details>
@@ -204,7 +250,7 @@ agent-notes memory lint               # health-check
 <details>
 <summary>Skills</summary>
 
-47+ on-demand knowledge modules across Rails, Docker, Kamal, Git, and Process. Run `agent-notes list skills` for the current list, or browse `agent_notes/data/skills/`.
+50+ on-demand knowledge modules across Rails, Docker, Kamal, Git, and Process. Run `agent-notes list skills` for the current list, or browse `agent_notes/data/skills/`.
 
 The session context hook auto-generates a skill index from SKILL.md frontmatter at install time, so agents always know what skills are available without loading full skill content. This keeps context overhead low while maintaining skill discoverability.
 
@@ -219,26 +265,29 @@ Load the docker-compose skill for multi-service setup
 
 | Failure mode | What goes wrong | Skills that help |
 |---|---|---|
-| Misalignment | Claude starts building before the problem is resolved | `/grill-me`, `/grill-with-docs` |
-| Verbosity | Responses are bloated; context window fills with noise | `/caveman`, `/setup-project-context` |
-| Broken code | Claude codes without a feedback loop or evidence trail | `/tdd` (improved), `/debugging-protocol` (improved) |
-| Ball of mud | Architecture drifts; modules grow shallow and tangled | `/improve-codebase-architecture`, `/zoom-out` |
+| Misalignment | Claude starts building before the problem is resolved | `/grill-me`, `/grilling`, `/grill-with-docs` |
+| Vague scope | Work starts without a spec or ticketed breakdown | `/to-spec`, `/to-tickets`, `/wayfinder`, `/triage` |
+| Broken code | Claude codes without a feedback loop or evidence trail | `/tdd`, `/diagnosing-bugs` |
+| Ball of mud | Architecture drifts; modules grow shallow and tangled | `/improve-codebase-architecture`, `/codebase-design`, `/domain-modeling` |
 
 **Skill descriptions:**
 
-- `/grill-me` — Interview the user until the problem is fully resolved before touching code
+- `/grill-me`, `/grilling` — Interview the user relentlessly until the plan is fully resolved before touching code
 - `/grill-with-docs` — Same, but cross-references CONTEXT.md and ADRs and updates them inline
-- `/caveman` — Ultra-compressed reply mode (~75% token savings) for rapid iteration
-- `/setup-project-context` — Bootstraps a CONTEXT.md domain glossary (ubiquitous language)
-- `/tdd` — RED-GREEN-REFACTOR with tracer-bullet vertical slices; horizontal-slicing anti-pattern added
-- `/debugging-protocol` — Phase 1 rewritten as "build a feedback loop first" with 9 strategies
-- `/improve-codebase-architecture` — Deletion test to find shallow modules; surfaces deepening opportunities
-- `/zoom-out` — Quick orientation map of an unfamiliar code area
+- `/tdd` — RED-GREEN-REFACTOR with tracer-bullet vertical slices; integration-first testing
+- `/diagnosing-bugs` — Diagnosis loop for hard bugs and performance regressions (build a feedback loop first)
+- `/improve-codebase-architecture` — Scan for deepening opportunities, present a visual HTML report, then grill the chosen one
+- `/codebase-design` — Shared vocabulary for designing deep modules and choosing where seams go
+- `/domain-modeling` — Pin down ubiquitous language, maintain a CONTEXT.md glossary and ADRs
 - `/handoff` — Compact conversation into a handoff document for a fresh agent session
-- `/to-prd` — Synthesize conversation into a Product Requirements Document
-- `/to-issues` — Break a plan/PRD into vertical-slice issues (HITL/AFK classification)
+- `/to-spec` — Synthesize the current conversation into a spec and publish it to the issue tracker
+- `/to-tickets` — Break a plan/spec into tracer-bullet tickets with declared blocking edges
+- `/wayfinder` — Plan work larger than one agent session as a map of investigation tickets
+- `/triage` — Move issues and external PRs through a triage state machine into agent-ready briefs
+- `/research` — Investigate a question against primary sources and capture findings as Markdown
 - `/prototype` — Throwaway prototypes: terminal app for logic or UI variations for visual
-- `/write-a-skill` — Meta-skill for creating new skills with proper structure
+- `/setup-agent-tracker` — One-time per-repo setup of the issue tracker, triage labels, and domain doc layout
+- `/writing-great-skills` — Reference for writing and editing skills well
 
 </details>
 
@@ -377,6 +426,8 @@ By default, `agent-notes install` re-runs the interactive wizard and prompts for
 
 The plugin build scripts (`scripts/build-claude-plugin.sh`, `scripts/build-opencode-plugin.sh`) automatically use `.venv/bin/python` when present, fall back to system `python3`, and honor a `PYTHON=` override.
 
+**Note:** `uv` is used only in the local development and release workflow (see `scripts/release`). It is not required to install or use agent-notes — end users should use `pipx` or `pip` / `venv`.
+
 ### Test structure
 
 - `tests/functional/` — Unit tests
@@ -429,7 +480,7 @@ See [docs/ARCHITECTURE.md](docs/ARCHITECTURE.md), [docs/ADD_CLI.md](docs/ADD_CLI
 ## Inspired by
 
 - [Andrej Karpathy's LLM Wiki](https://gist.github.com/karpathy/442a6bf555914893e9891c11519de94f) — The wiki memory backend implements his compile-once, query-forever knowledge pattern with structured page types and three core operations (ingest, query, lint)
-- [Matt Pocock's skills repo](https://github.com/mattpocock/skills) — Skill format (SKILL.md per directory), failure-mode table (misalignment, verbosity, broken code, architectural degradation), and several core skills (tdd, grill-me, grill-with-docs, improve-codebase-architecture, zoom-out, caveman)
+- [Matt Pocock's skills repo](https://github.com/mattpocock/skills) — Skill format (SKILL.md per directory), failure-mode table (misalignment, broken code, architectural degradation), and a set of engineering/productivity skills vendored from the upstream repo (tdd, grill-me, grilling, grill-with-docs, diagnosing-bugs, improve-codebase-architecture, codebase-design, domain-modeling, prototype, handoff, research, to-spec, to-tickets, triage, wayfinder, writing-great-skills). Last synced from upstream commit [`391a270`](https://github.com/mattpocock/skills/commit/391a2701dd948f94f56a39f7533f8eea9a859c87) (2026-07-10), reviewed for prompt-injection before import.
 
 ## License
 

agent_notes-2.32.0/agent_notes/VERSION

@@ -0,0 +1 @@
+2.32.0

{agent_notes-2.29.0 → agent_notes-2.32.0}/agent_notes/cli.py

@@ -291,7 +291,7 @@ def main():
 
     # hook
     p_hook = subparsers.add_parser("hook", help="Claude Code hook integrations")
-    p_hook.add_argument("subaction", choices=["memory-bridge", "session-discover"],
+    p_hook.add_argument("subaction", choices=["memory-bridge", "precompact-memory-bridge", "session-discover", "guard-credentials"],
         help="Hook to run")
 
     # cost-report