@mthanh/vespercli 1.8.0 → 2.0.0

package/assets/skills/vesper-catalog-editing-safety/SKILL.md

@@ -1,142 +0,0 @@
----
-name: vesper-catalog-editing-safety
-description: Pre-edit safety checklist for touching Vesper's own asset catalog and provisioning code — assets/, scripts/generate-claude-assets.js, src/cli/utils/settings.js, src/cli/utils/claude-target.js. Use before editing any catalog asset (agent, skill, prompt, instruction), the Claude-asset generator, or the Copilot/Claude settings-injection code in this repo. Prevents re-deriving the dual-target distribution model from scratch and catches the generator-boundary and git-hygiene-dual-list traps that have already caused a blocking architecture-review finding and a shipped bug.
----
-
-# Vesper Catalog Editing Safety
-
-## Overview
-
-This repo (`@mthanh/vespercli`) is self-hosting: it produces the very agent/skill/prompt catalog it installs into itself and every other project. That self-hosting creates footguns that are easy to rediscover the hard way — one already caused a blocking architecture-review finding, another shipped as a real bug. This skill is a **pre-flight checklist**, not the narrative — walk it before touching provisioning code or catalog assets, and follow the links when you need the full story.
-
-Full narrative + citations: [`docs/architecture.md`](../../../docs/architecture.md). Terse always-loaded version: `.claude/vesper/context.md`'s Conventions section. Read this skill first — it tells you *which* parts of those two documents matter for the edit in front of you.
-
-## When to Use This Skill
-
-Load this skill before:
-
-- Editing anything under `assets/` — core, extended, or the generated `assets/claude/` tree
-- Editing `scripts/generate-claude-assets.js`
-- Editing `src/cli/utils/settings.js` or `src/cli/utils/claude-target.js`
-- Planning or reviewing a change that touches how Copilot or Claude Code *discovers* a Vesper asset (settings arrays, plugin install, guard blocks, reinject hooks)
-- Editing `.claude/rules/*.md`, `.vesper/instructions/`, or `.vesper/skills/` override paths
-- Editing `VESPER_GIT_PATHS` (`settings.js`) or `assets/hooks/pre-commit`
-- Reviewing a plan/PR that proposes any of the above — this is a research **and** review-time checklist, not just an implementation-time one
-
-## Instructions
-
-### Step 1 — Route the edit to the right trap
-
-| You're touching...                                                    | Go to        |
-| ----------------------------------------------------------------------- | ------------ |
-| A file under `assets/agents/`, `assets/skills/`, `assets/instructions/`, `assets/prompts/`, or `assets/claude/*` | Checklist A — Dual Asset Tree |
-| `scripts/generate-claude-assets.js` itself                              | Checklist A  |
-| `.vesper/instructions/`, `.vesper/skills/`, or a new `.claude/rules/*.md` | Checklist B — Discovery Wiring |
-| `getCoreAssetEntries()` or `VSCODE_SETTINGS_MAP` in `settings.js`        | Checklist B  |
-| `ensureClaudeMdGuardBlock()` or `VESPER_REINJECT_COMMAND` in `claude-target.js` | Checklist B |
-| `VESPER_GIT_PATHS` in `settings.js`, or `assets/hooks/pre-commit`        | Checklist C — Git-Hygiene Dual List |
-| Anything about which target (Copilot vs Claude) gets what               | Checklist D — Distribution Model (background only) |
-
-Most edits hit exactly one checklist. If unsure, read Checklist D first — it's the model everything else sits on.
-
-### Checklist A — Dual Asset Tree (the highest-value trap)
-
-`scripts/generate-claude-assets.js` has a narrow, explicit remit — verified against its own header comment (`scripts/generate-claude-assets.js:11-14`):
-
-| Copilot source                                        | Claude output                                           |
-| ------------------------------------------------------- | ----------------------------------------------------------- |
-| `assets/agents/<name>/<name>.agent.md`                 | `assets/claude/agents/<name>.md`                          |
-| `assets/prompts/<name>/<name>.prompt.md`               | `assets/claude/commands/<name>.md`                        |
-| `assets/skills/<name>/`                                | `assets/claude/skills/<name>/` (near-verbatim)             |
-| `assets/instructions/<name>/<name>.instructions.md`    | `assets/claude/skills/<name>/SKILL.md` (new skill)         |
-
-**That table is the entire remit.** `assets/core/` is never read by this script, at all — by design, not by omission (the script's own comment: *"the 12 core agents + the orchestrator playbook are hand-authored separately in assets/claude/ and are never touched by this script"*). Neither is `assets/vendor/` — reviewed, pinned third-party snapshots (e.g. `assets/vendor/i-have-adhd/`, `assets/vendor/ponytail/`) live outside the four scan roots and the three write targets on purpose. A vendored asset is edited only by re-vendoring (a reviewed PR bumping its pinned SHA), never through the generator; do not move it under `assets/skills/` or `assets/claude/` to "make the generator pick it up."
-
-- [ ] Is the file under `assets/core/`?
-  - **Yes** → There is no generator step for you. Hand-edit **both** the Copilot source (`assets/core/{agents,skills,instructions,prompts}/...`) **and** its `assets/claude/` twin. Before editing the twin, check it for **Claude-only content that doesn't exist in the Copilot source** and preserve it — e.g. `assets/claude/skills/agent-fundamentals/SKILL.md`'s `## Direct Collaboration (Nested Delegation)` section has no Copilot-side counterpart. Never diff the two sides expecting them to match; they're allowed to diverge by design.
-  - **No** (it's under `assets/agents/`, `assets/skills/`, `assets/instructions/`, or `assets/prompts/`) → Edit the Copilot source only, then run `node scripts/generate-claude-assets.js` to regenerate its Claude twin. **Never hand-edit anything under `assets/claude/`** for a file that came from this table — your edit will be silently clobbered (or drift undetected) the next time the generator runs.
-- [ ] If you're editing `assets/claude/` directly right now — stop and confirm which case above you're actually in. Hand-editing generated output is the single most common way this trap gets tripped.
-- [ ] If your task is planning/reviewing (not implementing) a catalog change: confirm the plan doesn't assume a core-skill/core-agent edit will "just flow through" the generator step. It won't — this exact wrong assumption produced a blocking architecture-review finding (BC-2) and a near-miss self-contradiction in an agent's own file-write rules in a prior session.
-
-### Checklist B — Local Overrides vs. Discovery Wiring (per target)
-
-"A file exists at the right path" and "the target actually discovers it" are two different guarantees — satisfied differently per target.
-
-**Copilot** — `.vesper/instructions/*.instructions.md` and `.vesper/skills/**/SKILL.md` are project-local override paths. They are **inert on their own**.
-
-- [ ] Does `getCoreAssetEntries()` (`src/cli/utils/settings.js:1321-1363`, appending entries around lines 1348-1360) explicitly include a `${workspaceFolder}/.vesper/instructions` and `${workspaceFolder}/.vesper/skills` entry in the arrays it writes into `.vscode/settings.json` (keyed by `VSCODE_SETTINGS_MAP`, `settings.js:70-75`)? If you're adding a *new* override path convention, it needs the equivalent wiring here — a path convention alone is invisible to Copilot without a matching settings-array entry. This exact gap was found and fixed once already.
-
-**Claude Code** — `.claude/skills/{domain}/SKILL.md` needs no wiring; it's natively auto-discovered. `.claude/rules/{name}.md` is different — it has two moving parts, neither of which is native Claude Code behavior:
-
-- [ ] Does `CLAUDE.md` carry an `@.claude/rules/{name}.md` import line **outside** the `<!-- vesper:start -->...<!-- vesper:end -->` guard block? (`ensureClaudeMdGuardBlock()`, `src/cli/utils/claude-target.js:257`.) Inside the guard block, it gets regenerated away on the next `update`/`/reinit`.
-- [ ] Does the rule still need to survive `/clear`? The `SessionStart(clear)` reinject hook (`VESPER_REINJECT_COMMAND`, `claude-target.js:723-753`) dynamically enumerates `.claude/rules/*.md` at hook-fire time — sorted, `.md`-filtered — alongside the three fixed `.claude/vesper/*.md` playbook files. You don't need to register a new rule file anywhere for this to work; a missing `.claude/rules/` directory is swallowed by an outer try/catch (no-op). But if you're changing the *enumeration logic itself*, verify it still globs correctly.
-
-### Checklist C — Git-Hygiene Dual List (no single source of truth)
-
-`VESPER_GIT_PATHS` (`src/cli/utils/settings.js:173-185`) and the `vesper_git_paths` shell string in `assets/hooks/pre-commit:16` describe the same set of "project knowledge that must ride along with any commit touching other work." They are **hand-mirrored**, not generated from one source.
-
-- [ ] Edited one list? Edit the other too, in the **same relative order**. There is no codegen link between them (open technical debt) — nothing will catch a divergence for you.
-- [ ] Every entry is **slash-less** (`.claude/skills`, never `.claude/skills/`). A trailing slash turns the pre-commit hook's match clause (`case "$candidate" in "$p"/*)`) into a pattern with a literal double slash that never matches a real staged path — silently defeating the guardrail for that one entry. This has already shipped as a real bug once.
-
-### Checklist D — Distribution Model (background, read when the trap isn't obvious)
-
-- **Copilot**: nothing is copied into the project. Vesper injects settings entries (`chat.agentFilesLocations` / `chat.instructionsFilesLocations` / `chat.promptFilesLocations` / `chat.agentSkillsLocations`, see `VSCODE_SETTINGS_MAP` at `settings.js:70-75`) into `.vscode/settings.json`, pointing at the installed npm package's `assets/` tree. `getCoreAssetEntries()` (`settings.js:1321-1363`) assembles the full entry list.
-- **Claude Code**: the catalog is a **user-level plugin**, installed once and shared across every project on the machine — `~/.claude/skills/vesper/{agents,commands,skills}/`. `getClaudePluginDir()` (`claude-target.js:36-38`) resolves the path; `installClaudePluginCatalog()` (`claude-target.js:157-171`) performs the install/refresh. Only a small per-project set of files lives in the repo itself: `.claude/vesper/{orchestrator,orchestration,context}.md`, `.mcp.json`, `.claude/settings.json`.
-- Both targets share one on-disk index at `.vesper/index.db`.
-
-If your edit changes *where* either target looks, or *what* gets written into the project vs. the shared install location, this is the model to reason from before touching Checklist A/B.
-
-## Examples
-
-### Example 1: Adding a brand-new skill to the extended catalog
-
-**Input**: "Add a new skill `assets/skills/foo-bar/SKILL.md`."
-
-**Process**:
-1. Checklist A applies (extended tree, not `assets/core/`).
-2. Write `assets/skills/foo-bar/SKILL.md` (+ any `references/`, `scripts/`, `assets/` subfolders) under the Copilot source tree only.
-3. Do **not** hand-write anything under `assets/claude/skills/foo-bar/` — that's the generator's job.
-4. Note in the handoff/PR that `node scripts/generate-claude-assets.js` must be run (by a maintainer or a later pipeline step with Bash access) before the skill exists on the Claude Code target.
-
-### Example 2: Editing a core skill (`assets/core/skills/agent-fundamentals/`)
-
-**Input**: "Add a new rule to `agent-fundamentals`'s Terminal Discipline table."
-
-**Process**:
-1. Checklist A applies, `assets/core/` branch — no generator step exists.
-2. Edit `assets/core/skills/agent-fundamentals/SKILL.md` (Copilot source).
-3. Before editing `assets/claude/skills/agent-fundamentals/SKILL.md`, re-read it fully — it already carries the Claude-only `## Direct Collaboration (Nested Delegation)` section that has no Copilot-side counterpart. Add the new rule to both files without disturbing that section.
-
-### Example 3: Adding a `${workspaceFolder}`-relative override path for a new asset type
-
-**Input**: "Support project-local overrides for prompts, the same way `.vesper/instructions` works today."
-
-**Process**:
-1. Checklist B applies (Copilot branch).
-2. Confirm `getCoreAssetEntries()` in `settings.js` needs a new `${workspaceFolder}/.vesper/prompts`-style entry appended into the `chat.promptFilesLocations` array — the path convention alone will not make Copilot discover it.
-3. Flag in the plan/review that this wiring step is required, not optional — it's the exact class of gap that was found and fixed once already in this repo.
-
-## Edge Cases
-
-**"I'm only touching `assets/claude/` to fix an obvious typo."** Still routes through Checklist A. If the source file is under the extended tree, fix the typo in the Copilot source and regenerate — don't patch the generated copy even for a one-character fix, or the next generator run silently reverts it.
-
-**"The instruction/prompt/agent I'm adding doesn't map cleanly to the generator's table."** `assets/core/instructions/*.instructions.md` files are hand-folded into the orchestrator/rules constructs (Checklist B), not mechanically converted — there is no automatic instructions → Claude-skill path for core instructions the way there is for the extended tree.
-
-**"I can't tell if a file is 'core' or 'extended.'"** Core = anything under `assets/core/`. Extended = `assets/agents/`, `assets/skills/`, `assets/instructions/`, `assets/prompts/` (no `core/` segment). If genuinely ambiguous, check whether an `assets/claude/` twin already exists and whether it looks hand-authored (has Claude-only sections) vs. mechanically generated (near-verbatim mirror) — that's a strong signal of which bucket it's in.
-
-**"I don't have Bash tool access to run the generator."** Note it explicitly in your output/handoff rather than silently skipping it — the change is incomplete on the Claude Code target until a maintainer or a later pipeline step runs `node scripts/generate-claude-assets.js`.
-
-## Related Files
-
-- `assets/` — the Copilot-format source catalog (`core/` hand-authored default install; `agents/`, `skills/`, `instructions/`, `prompts/` extended/opt-in)
-- `assets/claude/` — generated Claude-target twin of the extended tree, plus hand-maintained Claude-only twins of `assets/core/`
-- `assets/vendor/` — reviewed, pinned snapshots of third-party assets (e.g. `assets/vendor/i-have-adhd/`, `assets/vendor/ponytail/`); a generator-excluded category, installed project-level at init time, never scanned/written by the generator and never a scan root
-- `scripts/generate-claude-assets.js` — the extended-tree generator; never touches `assets/core/`
-- `src/cli/utils/settings.js` — `VSCODE_SETTINGS_MAP`, `getCoreAssetEntries()`, `VESPER_GIT_PATHS`
-- `src/cli/utils/claude-target.js` — `getClaudePluginDir()`, `installClaudePluginCatalog()`, `ensureClaudeMdGuardBlock()`, `VESPER_REINJECT_COMMAND`
-- `assets/hooks/pre-commit` — the hand-mirrored `vesper_git_paths` shell list
-
-## References
-
-- [`docs/architecture.md`](../../../docs/architecture.md) — full narrative, all four facts, with additional citations and the specific incidents (BC-2 architecture-review finding, the trailing-slash bug) that motivated this checklist.
-- `.claude/vesper/context.md` — terse, always-loaded version of the same conventions, auto-injected into every session in this repo.

package/assets/skills/vesper-catalog-editing-safety/manifest.json

@@ -1,8 +0,0 @@
-{
-  "name": "vesper-catalog-editing-safety",
-  "version": "1.0.0",
-  "generated": "2026-07-19T18:29:56.208Z",
-  "files": [
-    "SKILL.md"
-  ]
-}

package/assets/skills/vscode-agent-config/SKILL.md

@@ -1,90 +0,0 @@
-# Skill: VS Code Agent Configuration
-
-## When to Use
-
-Use this skill when:
-
-- Configuring VS Code for agentic workflows (Vesper, Copilot, Cline, etc.)
-- Setting up auto-approval for safe terminal commands or MCP tools
-- Migrating configuration from folder-based to workspace-based setups
-- Troubleshooting agent permission issues or MCP connection problems
-
-## Prerequisites
-
-- VS Code installed
-- Access to `.vscode/settings.json` or `*.code-workspace` file
-
-## Process
-
-### Step 1: Determine Configuration Target
-
-Check the workspace structure to decide where to apply settings.
-
-- **Single Folder**: Use `.vscode/settings.json`.
-- **Multi-Root Workspace**: Use the `*.code-workspace` file (settings are nested under `"settings": {}`).
-
-### Step 2: Configure Terminal Auto-Approval
-
-Add `chat.tools.terminal.autoApprove` to allow agents to run safe commands without interruption.
-
-**Rules:**
-
-1. **Never** auto-approve wildcards for potentially destructive commands (`rm *`, `curl *`).
-2. **Always** scope by tool name and specific flags.
-3. **Network Safety**: Only allow `curl` with `-I`/`--head` or localhost targets.
-
-**Example Configuration:**
-
-```json
-"chat.tools.terminal.autoApprove": {
-  // Read-only filesystem
-  "ls": true,
-  "cat": true,
-  "grep": true,
-  "find": true,
-  "git status": true,
-
-  // Safe Network (Head only or Localhost)
-  "curl -I *": true,
-  "curl -s http://localhost:*": true,
-
-  // Package scripts
-  "npm run *": true,
-  "npm test": true
-}
-```
-
-### Step 3: Configure MCP Tools
-
-Use `chat.tools.eligibleForAutoApproval` for MCP tools.
-
-**Note:** Tool names become valid once their MCP servers are discovered.
-
-```json
-"chat.tools.eligibleForAutoApproval": {
-  "vesper_search": true,
-  "vesper_symbols": true,
-  "resolve-library-id": true
-}
-```
-
-## Common Issues
-
-- **Settings not applying**: Check if you are in a Workspace file but editing `.vscode/settings.json` (Workspace file takes precedence).
-- **Curl command blocked**: Ensure your regex matches exactly (e.g., `curl -I` vs `curl --head`).
-- **MCP tool not auto-approved**: Use only the tool name (e.g., `vesper_search`), not `server_tool` format.
-- **"Value is not accepted" warning**: VS Code schema validates against discovered tools only. Unknown MCP tools show warnings until their servers are discovered — safe to ignore for known tools.
-
-## Agent-Specific MCP Tools
-
-Some agents require additional MCP tools to function. Vesper CLI handles this automatically:
-
-```bash
-vesper add agents clickup-agent  # Adds agent + 32 clickup_* tools
-```
-
-**Pattern for adding new agent tools:**
-
-1. Add tools array to `MCP_TOOLS_BY_AGENT` in `src/cli/utils/settings.js`
-2. CLI's `add` command automatically detects and adds tools when agent is added
-3. Tools are validated dynamically once MCP server is discovered

package/assets/skills/vscode-agent-config/manifest.json

@@ -1,8 +0,0 @@
-{
-  "name": "vscode-agent-config",
-  "version": "1.0.0",
-  "generated": "2026-07-19T18:29:56.209Z",
-  "files": [
-    "SKILL.md"
-  ]
-}

package/assets/skills/web-design-guidelines/manifest.json

@@ -1,8 +0,0 @@
-{
-  "name": "web-design-guidelines",
-  "version": "1.0.0",
-  "generated": "2026-07-19T18:29:56.209Z",
-  "files": [
-    "SKILL.md"
-  ]
-}

package/assets/skills/web-frameworks/manifest.json

@@ -1,24 +0,0 @@
-{
-  "name": "web-frameworks",
-  "version": "1.0.0",
-  "generated": "2026-07-19T18:29:56.210Z",
-  "files": [
-    "SKILL.md",
-    "references/nextjs-app-router.md",
-    "references/nextjs-data-fetching.md",
-    "references/nextjs-optimization.md",
-    "references/nextjs-server-components.md",
-    "references/remix-icon-integration.md",
-    "references/turborepo-caching.md",
-    "references/turborepo-pipelines.md",
-    "references/turborepo-setup.md",
-    "scripts/__init__.py",
-    "scripts/nextjs_init.py",
-    "scripts/requirements.txt",
-    "scripts/tests/coverage-web.json",
-    "scripts/tests/requirements.txt",
-    "scripts/tests/test_nextjs_init.py",
-    "scripts/tests/test_turborepo_migrate.py",
-    "scripts/turborepo_migrate.py"
-  ]
-}

package/assets/vendor/i-have-adhd/VENDOR.md

@@ -1,56 +0,0 @@
-<!-- markdownlint-disable-file -->
-
-# Vendored asset: i-have-adhd
-
-A **reviewed, pinned snapshot** of a third-party skill. This is a
-vendored (externally-sourced-**once**) asset — NOT an externally-synced one.
-Do **not** edit the snapshot locally. Re-vendor **only** by a deliberate,
-reviewed pull request; it is **never** fetched at runtime and **never**
-refreshed automatically.
-
-## Provenance
-
-- **Upstream**: <https://github.com/ayghri/i-have-adhd>
-- **Pinned commit SHA**: `07684c4ab625dd7d1ea6e99e065f60bc0ac6a1ba`
-- **Upstream path**: `skills/i-have-adhd/SKILL.md`
-- **Retrieved**: 2026-07-29
-- **License**: MIT — Copyright (c) 2026 Ayoub Ghriss (see [`LICENSE`](./LICENSE), retained verbatim)
-- **Reviewer**: principal-software-engineer (Vesper) — 2026-07-29
-
-## Content review (before commit)
-
-The snapshot was inspected specifically for the untrusted-content hazards, per
-the architecture review's content-review discipline:
-
-- **Prompt injection / host-prompt override** — NONE. The skill explicitly
-  defers to the harness: *"the system prompt outranks this skill."*
-- **Behavioral override beyond output styling** — NONE. It shapes response
-  *format* only, and explicitly preserves safety confirmations for destructive
-  actions (*"Safety wins over brevity"*).
-- **Tool-permission escalation** — NONE. No tool calls, no permission requests.
-- **Data exfiltration** — NONE. No network access, no reading of secrets, no
-  external sends.
-- **Destructive instructions** — NONE. `rm -rf` appears only as an *example* of
-  an action that MUST be confirmed first.
-
-**Verdict**: inert output-styling guidance; safe to vendor and redistribute as data.
-
-## What Vesper installs from this snapshot
-
-When the opt-in gate is enabled, `vespercli init`/reinit installs, at the
-**project** level (never the shared user-level plugin dir):
-
-- `.claude/skills/i-have-adhd/SKILL.md` — this snapshot, verbatim (on-demand reference)
-- `.claude/rules/i-have-adhd.md` — a minimal always-on activation rule derived
-  from this snapshot (derives from and does not exceed it)
-- a marker-scoped `@import` in `CLAUDE.md` (outside the vesper guard block)
-
-The upstream `INSTALL.md` instructions (Claude plugin marketplace add /
-`npx skills` / `curl … -o`) are **UNTRUSTED** and are **NEVER executed** by
-Vesper. Only this reviewed content is taken, as data.
-
-## Re-vendoring (reviewed PR only)
-
-To update this snapshot: fetch the new upstream content at a new pinned SHA,
-re-run the content review above, update the SHA + retrieval date + reviewer
-here, and land it as a reviewed pull request. There is no automated path.

package/assets/vendor/ponytail/VENDOR.md

@@ -1,115 +0,0 @@
-<!-- markdownlint-disable-file -->
-
-# Vendored asset: ponytail
-
-A **reviewed, pinned snapshot** of a third-party skill — the vendored
-(externally-sourced-**once**) category, NOT an externally-synced one. Do **not**
-edit the snapshot locally. Re-vendor **only** by a deliberate, reviewed pull
-request; it is **never** fetched at runtime and **never** refreshed automatically.
-
-**No executable code is vendored.** The vendored payload is a single markdown
-file (the decision-ladder rule/skill text). Every executable and non-Claude
-artifact from the upstream repo is deliberately excluded (see Exclusions).
-
-## Provenance
-
-- **Upstream**: <https://github.com/DietrichGebert/ponytail>
-- **Pinned commit SHA**: `16f29800fd2681bdf24f3eb4ccffe38be3baec6b`
-- **Upstream path vendored**: `skills/ponytail/SKILL.md` (the core decision-ladder skill body ONLY)
-- **Retrieved**: 2026-08-02 (via GitHub API at the pinned SHA, as inert data)
-- **License**: MIT — Copyright (c) 2026 DietrichGebert (see [`LICENSE`](./LICENSE), retained verbatim)
-- **Reviewer**: principal-software-engineer (Vesper) — 2026-08-02
-- **Architecture sign-off**: GRANTED-WITH-CONDITIONS (SHA `16f29800fd2681bdf24f3eb4ccffe38be3baec6b`,
-  `se-system-architecture-reviewer`). Scoped to THIS SHA only — any re-vendor at a
-  new SHA requires a fresh per-snapshot sign-off. Conditions folded into the
-  install: (1) the derived always-on `.claude/rules/ponytail.md` is a minimal
-  activation pointer that does NOT promote the testing opinion or the
-  "at most three short lines" output directive into always-injected context —
-  those stay on-demand in the installed SKILL.md body only.
-
-## Scope — markdown-only (what IS vendored)
-
-- `SKILL.md` — the upstream `skills/ponytail/SKILL.md` decision-ladder rule/skill
-  text, verbatim. Markdown only, no code.
-
-## Exclusions (deliberately NOT vendored)
-
-Vendoring executable code would break this category's "never executed"
-invariant, so the following upstream artifacts are **excluded**:
-
-- **`hooks/`** — auto-executing Node.js / shell / PowerShell (`ponytail-activate.js`,
-  `ponytail-config.js`, `ponytail-instructions.js`, `ponytail-mode-tracker.js`,
-  `ponytail-runtime.js`, `ponytail-subagent.js`, `ponytail-statusline.sh`,
-  `ponytail-statusline.ps1`, `claude-codex-hooks.json`). This is the standout
-  risk of this repo and the primary reason the subset is narrowed to rule text.
-- **`scripts/` / build tooling** — maintainer tooling, CI (`.github/workflows/`),
-  `benchmarks/` (Python + JS), `__init__.py`, `.env.example`.
-- **Other-editor rule variants** — `.cursor/rules/ponytail.mdc`,
-  `.windsurf/rules/ponytail.md`, `.clinerules/ponytail.md`,
-  `.github/copilot-instructions.md`, `.kiro/steering/ponytail.md`,
-  `.qoder/rules/ponytail.md`, `.agents/rules/ponytail.md`,
-  `.openclaw/skills/*`, `.opencode/*` (incl. executable `.cjs`/`.mjs` plugins).
-- **Auxiliary skills (five)** — `skills/ponytail-review`, `skills/ponytail-audit`,
-  `skills/ponytail-debt`, `skills/ponytail-gain`, `skills/ponytail-help`.
-- **Plugin manifests / marketing** — `.claude-plugin/`, `.codex-plugin/`,
-  `.devin-plugin/`, `.qoder-plugin/`, `marketplace.json`, `plugin.json`,
-  `assets/` (logos, banners, benchmark SVGs).
-
-Always-on UX is provided by Vesper's own minimal rule + `CLAUDE.md` import
-wiring (exactly like i-have-adhd), NOT by any upstream hook.
-
-## Trust note — star count disregarded
-
-The upstream repo shows an **anomalous ~93.5k-star count on a repository created
-2026-06-12 (under two months old)**. This was **disregarded as a trust signal** —
-popularity is not provenance, and an implausible star velocity on a very young
-repo is, if anything, a caution flag. Trust here rests solely on the per-snapshot
-content review below and the markdown-only, no-executable-code scoping.
-
-## Content review (before commit)
-
-Reviewed the vendored `SKILL.md` for the untrusted-content hazards. It is a prose
-review because the payload is markdown-only:
-
-- **Prompt injection / host-prompt override** — NONE. The persistence directive
-  ("ACTIVE EVERY RESPONSE") governs coding style only and explicitly yields to
-  the user ("User insists on the full version → build it, no re-arguing").
-- **Behavioral override beyond scope** — NONE. It shapes *what code you build*
-  (YAGNI / minimalism) and output brevity; it does not attempt to disable safety
-  or override the host system prompt.
-- **Tool-permission escalation** — NONE. No tool calls, no permission requests.
-- **Data exfiltration** — NONE. No network access, no reading of secrets, no
-  external sends.
-- **Destructive instructions** — NONE. "Deletion over addition" refers to writing
-  less code in the diff under construction, not to filesystem/command actions;
-  no `rm`/force-push/destructive commands appear. It explicitly preserves input
-  validation, error handling, security, and accessibility, and mandates leaving a
-  runnable check behind for non-trivial logic.
-
-**Verdict**: inert markdown coding-style guidance; safe to vendor and redistribute
-as data. **No executable code vendored** — the payload is a single markdown file.
-
-## Untrusted install instructions — never executed
-
-The upstream repo ships install instructions (Claude/Codex plugin marketplace
-`/plugin install`, git installs, `curl`-based extension installs, npm-style refs)
-and auto-executing hooks. These are **UNTRUSTED** and are **NEVER executed** by
-Vesper. Install/maintain read ONLY from this committed snapshot — there is no
-runtime fetch.
-
-## What Vesper installs from this snapshot (Phase 2, once signed off)
-
-When the opt-in gate is enabled, `vespercli init`/reinit will install, at the
-**project** level:
-
-- `.claude/skills/ponytail/SKILL.md` — this snapshot, verbatim (on-demand reference)
-- `.claude/rules/ponytail.md` — a minimal always-on activation rule derived from
-  it (derives from and does not exceed this snapshot)
-- a marker-scoped `@import` in `CLAUDE.md` (`<!-- vesper:ponytail:start/end -->`)
-
-## Re-vendoring (reviewed PR only)
-
-To update this snapshot: fetch new upstream content at a new pinned SHA, re-run
-the content review + exclusion confirmation above, update the SHA + retrieval
-date + reviewer + sign-off here, and land it as a reviewed pull request. There is
-no automated path.