Aligns claude-skills with secrets-out-of-common etap-1 migration: the canonical home for plain-text local-dev secrets is now ~/.config/projects-secrets/, outside any git tree. setup-interns [v0.3.0 → v0.4.0, MINOR — write target changed]: - Phase 1 drops gitignore-sanity check (no longer needed) - Phase 2 plan block drops Gitignore line - Phase 3 backs up ~/.config/projects-secrets/interns.env if present - Phase 5 writes ~/.config/projects-secrets/interns.env (mkdir -p ahead) - Phase 6 cwd documentation: secrets path no longer relative to cwd; uses INTERNS_SECRETS_PATH env var (or ~/.config default) — independent - Common-mistakes drops "missing gitignore rule" entry using-interns [v0.2.0 → v0.2.1, PATCH — wording]: - Always-ask paths section reflects new canonical secrets home - Prerequisites text updates setup-interns write target interns-design.md (wiki concept): path refs updated for ASCII layer diagram, Layer 1 example block, Phase 5 description, comparison table, and final cross-cutting note. **/projects-secrets/** added to always-ask documentation pattern. dist/: setup-interns.skill + using-interns.skill rebuilt. Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
250 lines
15 KiB
Markdown
250 lines
15 KiB
Markdown
---
|
||
name: setup-interns
|
||
version: 0.4.0
|
||
description: Installs and configures the local `interns` MCP server — clones the repo to `~/projects/.common/lib/interns-mcp/` (or uses an existing clone), `pip install -e` it, writes `~/.config/projects-secrets/interns.env` with endpoint API keys, and registers `mcpServers.interns` in `~/.claude.json`. Use this skill when the user says "install interns", "set up interns", "configure interns", "настрой интернов", "установи интернов", "interns не работает", "interns isn't working", or whenever the `mcp__interns__*` tools are missing in a session that needs delegation. Cross-platform — Windows / Linux / macOS. Mutates user-level config and writes secrets; pauses for confirmation before every write.
|
||
---
|
||
|
||
# setup-interns
|
||
|
||
> One-time skill that gets the local `interns` MCP server running with the user's endpoint API keys and a registered `mcpServers.interns` entry in `~/.claude.json`. Stops at confirmation gates because the procedure runs `pip install`, writes a secret-bearing `.env` file, and edits user-level config.
|
||
|
||
Reference: full design lives in this repo at `.wiki/concepts/interns-design.md` (Layer 1/2/3 architecture, MVP catalog, always-ask paths, routing hints).
|
||
|
||
## When to use
|
||
|
||
- User explicitly asks: install / set up / configure interns.
|
||
- A `using-interns`-driven task fails because `mcp__interns__*` tools aren't available in the session.
|
||
- New machine in the user's multi-machine fleet — install once per machine that wants delegation.
|
||
- Migrating a stale install (endpoint key rotated, server source moved, broken `dist/` artifact) — same procedure, Phase 1 detects what's already in place.
|
||
|
||
## Out of scope
|
||
|
||
- Issuing or rotating endpoint API keys (Ollama Cloud, OpenRouter, etc.). The skill *uses* keys the user already has; if there is none, it points at the provider's settings page and stops.
|
||
- Running `interns-mcp` itself — the Claude Code harness spawns it on session start.
|
||
- Authoring new interns or editing `~/projects/.common/config/interns/config.yaml` — that's a content task, not a setup task.
|
||
- Any other MCP server.
|
||
- Setting up the entire `common` monorepo beyond what `interns-mcp` needs. The clone step gets the full monorepo (it also contains `projects-meta-mcp` and other shared tools), but this skill only verifies the `lib/interns-mcp/` subdirectory.
|
||
|
||
## Hard rule: don't auto-mutate config
|
||
|
||
The procedure runs `pip install`, writes `~/.config/projects-secrets/interns.env` (carries endpoint API keys), and edits `~/.claude.json`. **Always pause for explicit confirmation between Phase 1 (discovery, read-only) and Phase 2 (plan), and again before Phase 3 (backup + writes).** A trigger phrase grants permission to inspect, not to install or write secrets.
|
||
|
||
## Procedure
|
||
|
||
### Phase 0 — Environment sanity
|
||
|
||
- Confirm Claude Code is the current harness (need `mcpServers` registration in `~/.claude.json`).
|
||
- Confirm `python` ≥ 3.11 and `pip` are on `PATH`. Report the resolved interpreter path (`python -c "import sys; print(sys.executable)"`); the skill will pin this exact path in the MCP registration so a later `python` shadowed by another env doesn't silently take over.
|
||
- Confirm `node` is on `PATH` (`node --version`). The `repo_read` intern runs `npx repomix@latest` as a subprocess. If `node` is absent, the user must install Node.js 20+ before proceeding — `repo_read` calls will fail at runtime with a clear "node not found" error.
|
||
- (Optional, recommended) Pre-warm the repomix binary: `npx --yes repomix@latest --version`. This caches the package so the first real `repo_read` call is instant (5–10s first-run penalty avoided). Skip silently on failure — the call will just be slower the first time.
|
||
- Confirm network reachability to the configured endpoints (default: `https://ollama.com/v1`). On HTTP 401 / 403 later, the API key is dead — stop and ask for a new one.
|
||
- Confirm `git` is on `PATH` (needed for clone-fallback in Phase 4 if the source isn't already present).
|
||
- Pick paths: `~/projects/.common/lib/interns-mcp/` (source), `~/projects/.common/config/interns/config.yaml` (catalog), `~/.config/projects-secrets/interns.env` (keys, outside any git tree), `~/.claude.json` (MCP registration). POSIX-style paths resolve correctly under git-bash on Windows.
|
||
|
||
### Phase 1 — Discovery (read-only)
|
||
|
||
Search, in order. Report only "found at <path>", never echo key values.
|
||
|
||
**Server source.** Check whether `~/projects/.common/lib/interns-mcp/pyproject.toml` exists.
|
||
|
||
- If present → report "found at ~/projects/.common/lib/interns-mcp/". Phase 4 will `pip install -e` (or skip if already importable).
|
||
- If absent → check whether `~/projects/.common/.git` exists (the `common` monorepo).
|
||
- If the monorepo exists but the subdirectory is missing → report "source subdir absent — will git pull". Phase 4 will `git -C ~/projects/.common pull --ff-only` to fetch the latest content, then verify the subdirectory appeared.
|
||
- If the monorepo is absent → report "source not found — will clone common monorepo from gitea". Phase 4 will `git clone https://git.kzntsv.site/OpeItcLoc03/common.git ~/projects/.common`.
|
||
|
||
If clone or pull fails (no network, no Gitea PAT), stop with a clear message:
|
||
|
||
```
|
||
Failed to clone/pull the common monorepo. Options:
|
||
1. Check network access to https://git.kzntsv.site
|
||
2. If you need a Gitea PAT: https://git.kzntsv.site/user/settings/applications
|
||
(scope: read:repository is sufficient)
|
||
3. If Gitea is unreachable, re-run setup-interns when it's back.
|
||
```
|
||
|
||
**Build artifact.** Run `python -c "import interns_mcp" 2>&1` against the candidate interpreter. If it fails with `ModuleNotFoundError`, Phase 4 will run `pip install -e ~/projects/.common/lib/interns-mcp/`. If it succeeds, capture the installed location and skip the install in Phase 4.
|
||
|
||
**Config catalog.** Read `~/projects/.common/config/interns/config.yaml`. Extract the unique set of `endpoints.<name>.api_key_env` values — these are the env var names the runtime expects to find. Capture for Phase 2.
|
||
|
||
**Existing endpoint keys.** Look in priority order, per `api_key_env` name from the config:
|
||
|
||
1. `~/.config/projects-secrets/interns.env` (`<NAME>=...` lines).
|
||
2. Process env (`os.environ[<NAME>]`).
|
||
3. `~/.config/projects-mcp/auth.toml` — only if the user has explicitly noted the key is shared with another local MCP server (rare).
|
||
|
||
The first hit wins per key. **Never echo key values in chat.**
|
||
|
||
**MCP registration.** Read `~/.claude.json` and check `mcpServers.interns`. Note the `command` and `args`. If args point at a stale interpreter, Phase 6 will fix it.
|
||
|
||
### Phase 2 — Plan + confirm
|
||
|
||
Present a single-block plan to the user:
|
||
|
||
```
|
||
Source: <found at ~/projects/.common/lib/interns-mcp/ | will clone/pull common monorepo>
|
||
Module: <interns_mcp importable | will pip install -e>
|
||
Config: <found at ~/projects/.common/config/interns/config.yaml> — endpoints: <names>
|
||
Missing keys: <list of <NAME> not yet present in interns.env | none>
|
||
MCP entry: <present in ~/.claude.json | will add | will fix interpreter path>
|
||
Backups: ~/.claude.json.bak-<ts>, ~/.config/projects-secrets/interns.env.bak-<ts> (if exists)
|
||
```
|
||
|
||
Wait for explicit confirmation ("ok", "go", "поехали"). Anything else → stop.
|
||
|
||
For each missing key, ask: "Paste a value for `<NAME>` (endpoint: `<endpoint_name>` — provider settings page: `<url-from-config-or-known-list>`), or skip and we'll leave the entry blank for you to fill later." Don't proceed past Phase 2 without resolving every required key — the runtime won't start with a missing API key.
|
||
|
||
### Phase 3 — Backup
|
||
|
||
Copy each file we will modify to `<file>.bak-YYYYMMDD-HHMMSS`:
|
||
|
||
```bash
|
||
TS=$(date +%Y%m%d-%H%M%S)
|
||
[ -f ~/.claude.json ] && cp ~/.claude.json ~/.claude.json.bak-$TS
|
||
[ -f ~/.config/projects-secrets/interns.env ] && cp ~/.config/projects-secrets/interns.env ~/.config/projects-secrets/interns.env.bak-$TS
|
||
```
|
||
|
||
Confirm both backups exist (when their source existed) before any further edit.
|
||
|
||
### Phase 4 — Clone (if needed) + Install Python module
|
||
|
||
**Clone or pull.** If Phase 1 found the source absent:
|
||
|
||
```bash
|
||
if [ -d ~/projects/.common/.git ]; then
|
||
# Monorepo exists but subdirectory missing — pull latest
|
||
git -C ~/projects/.common pull --ff-only
|
||
else
|
||
# Fresh clone of the common monorepo
|
||
mkdir -p ~/projects
|
||
git clone https://git.kzntsv.site/OpeItcLoc03/common.git ~/projects/.common
|
||
fi
|
||
```
|
||
|
||
Verify `~/projects/.common/lib/interns-mcp/pyproject.toml` exists after clone/pull. If the subdirectory is still missing after pull — the interns-mcp module may not have been pushed to the monorepo yet. Abort with a clear message.
|
||
|
||
If the source was already present and Phase 1 found `interns_mcp` importable, skip both clone/pull and install.
|
||
|
||
**Install.** If Phase 1 found `interns_mcp` not importable:
|
||
|
||
```bash
|
||
python -m pip install -e ~/projects/.common/lib/interns-mcp/
|
||
```
|
||
|
||
Capture the resolved `python` from Phase 0; use the same interpreter for both `pip install` and the later MCP `command:` field. Verify post-install:
|
||
|
||
```bash
|
||
python -c "import interns_mcp; print(interns_mcp.__file__)"
|
||
```
|
||
|
||
If import fails — abort. Ask the user to paste the `pip install` output so the failure mode is visible.
|
||
|
||
### Phase 5 — Write `interns.env`
|
||
|
||
Write `~/.config/projects-secrets/interns.env` (parent dir `mkdir -p ~/.config/projects-secrets` if missing). The file lives outside any git tree, so no `.gitignore` rule is needed. Per-key behavior:
|
||
|
||
- Existing key in the file with a non-empty value — leave it alone.
|
||
- Missing key — append `<NAME>=<value-from-Phase-2>` if the user pasted one, or `<NAME>=` (blank) if the user skipped. A blank entry will fail at runtime with a clear `KeyError`; that's acceptable for the "I'll fill it later" path.
|
||
|
||
Permissions: on Linux / macOS run `chmod 600 ~/.config/projects-secrets/interns.env`. On Windows the default ACL is per-user, no extra step.
|
||
|
||
### Phase 6 — Register in `~/.claude.json`
|
||
|
||
Edit `~/.claude.json`. Add or update the `mcpServers.interns` block:
|
||
|
||
```json
|
||
{
|
||
"mcpServers": {
|
||
"interns": {
|
||
"command": "<ABSOLUTE_PATH_TO_PYTHON>",
|
||
"args": ["-m", "interns_mcp.server"],
|
||
"cwd": "~/projects"
|
||
}
|
||
}
|
||
}
|
||
```
|
||
|
||
`cwd` is set so the runtime resolves `.common/config/interns/config.yaml` relative to the `~/projects` base directory regardless of where Claude Code was launched. Secrets are loaded from `~/.config/projects-secrets/interns.env` (overridable via `INTERNS_SECRETS_PATH` env var) — independent of `cwd`. On Windows, expand `~/projects` to the absolute path (e.g. `C:/Users/<USER>/projects`).
|
||
|
||
Absolute interpreter path comes from Phase 0 (`sys.executable`). Forward slashes work in JSON on Windows without escaping.
|
||
|
||
After each edit, validate JSON:
|
||
|
||
```bash
|
||
# Windows (git-bash)
|
||
powershell.exe -NoProfile -c "Get-Content '<file>' -Raw | ConvertFrom-Json | Out-Null"
|
||
# Linux / macOS
|
||
jq empty <file>
|
||
# fallback
|
||
python -c "import json; json.load(open('<file>'))"
|
||
```
|
||
|
||
If validation fails → restore from `.bak-*` and abort.
|
||
|
||
### Phase 7 — Smoke test (best-effort)
|
||
|
||
Best-effort: ask the user to call `mcp__interns__bulk_text_read` against a tiny benign input (e.g. read this file's `Phase 7` section, ask "what is this section about?"). A response that is structurally valid (text + usage) means the server is reachable.
|
||
|
||
**Important caveat to relay to the user:** in the *same* session that just ran setup, the active MCP connection was bound at session start. So a passing in-session smoke test only proves "an interns server is alive" — not "the registration we just wrote is what's serving it". The real test is after Claude Code restart.
|
||
|
||
If `mcp__interns__*` tools aren't registered in this session at all, skip the smoke test and rely on Phase 8.
|
||
|
||
### Phase 8 — Restart guidance + final report
|
||
|
||
Tell the user:
|
||
|
||
```
|
||
Setup complete. Restart Claude Code so the new mcpServers.interns
|
||
registration binds to a fresh stdio session.
|
||
|
||
After restart:
|
||
• mcp__interns__* tools serve from <python> -m interns_mcp.server
|
||
• Source at ~/projects/.common/lib/interns-mcp/
|
||
• Endpoint keys live in ~/.config/projects-secrets/interns.env (outside any git tree)
|
||
• Config catalog at ~/projects/.common/config/interns/config.yaml
|
||
• Backups saved at ~/.claude.json.bak-<ts> (and interns.env.bak-<ts>
|
||
if it existed before)
|
||
|
||
Runtime policy lives in `using-interns`. CLAUDE.md trigger:
|
||
delegate to interns when allowed
|
||
project-bootstrap 1.6.0+ adds it to new projects automatically.
|
||
|
||
If something breaks after restart:
|
||
• Restore from .bak-* and tell me — we'll roll back together.
|
||
```
|
||
|
||
## Rollback procedure
|
||
|
||
If a problem surfaces (now or after restart):
|
||
|
||
1. Stop. Don't try to fix forward.
|
||
2. Find the most recent `.bak-YYYYMMDD-HHMMSS` next to `~/.claude.json` (and `~/.config/projects-secrets/interns.env` if applicable).
|
||
3. `cp <file>.bak-<ts> <file>` for each.
|
||
4. Optional: `pip uninstall interns-mcp` if you want to remove the editable install.
|
||
5. Optional: `rm -rf ~/projects/.common/lib/interns-mcp` if you want to remove the cloned source.
|
||
6. Restart Claude Code.
|
||
7. Confirm `mcp__interns__*` is gone (or back to its pre-existing version).
|
||
8. Report what went wrong so we can fix the procedure.
|
||
|
||
## Cross-platform notes
|
||
|
||
The procedure is platform-agnostic. Only auxiliary tooling differs:
|
||
|
||
| | JSON validate | Backup | Permissions on `.env` |
|
||
|---|---|---|---|
|
||
| Windows (git-bash) | `powershell.exe -NoProfile -c "Get-Content '<f>' -Raw \| ConvertFrom-Json \| Out-Null"` | `cp` | per-user ACL by default |
|
||
| Linux | `jq empty <f>` (or `python -c "import json; json.load(open('<f>'))"`) | `cp` | `chmod 600` |
|
||
| macOS | same as Linux | `cp` | `chmod 600` |
|
||
|
||
Path forms (`~/projects/.common/...`, `~/.config/...`, `~/.claude.json`) are identical on all three.
|
||
|
||
## Common mistakes
|
||
|
||
- **Skipping Phase 1.** "User just said 'install interns' — let's go." No — find existing source / module / keys first; clobbering an existing `.env` over a working one loses keys you can't recover.
|
||
- **Echoing endpoint keys.** They're secrets. Edit / Write tool calls inevitably contain them (that's how they land in `.env`), but no chat output should.
|
||
- **Pinning `python` instead of `<sys.executable>`.** A bare `python` in the MCP `command:` resolves to whatever interpreter is first on `PATH` at session start — often a different env without the `interns_mcp` module. Always use the absolute interpreter path captured in Phase 0.
|
||
- **Forgetting `cwd: ~/projects`.** Without it the runtime can't find `.common/config/interns/config.yaml` and bombs at startup with a config-not-found error that looks like a Claude Code bug.
|
||
- **Writing `.env` with `0644` perms on Linux/macOS.** Token leak. Always `chmod 600` after write.
|
||
- **Treating in-session smoke test as proof.** Same as the context7 / projects-meta caveat — the active MCP connection was bound at session start. Real verification happens after restart.
|
||
- **Auto-running on every "use interns".** This skill is intrusive. Trigger only on explicit "install / set up / configure interns", or when MCP tools are missing and the user is blocked.
|
||
- **Cloning over an existing source directory.** If `~/projects/.common/lib/interns-mcp/` already exists with `pyproject.toml`, don't clone — use what's there. Clone is only for the "source not found" case.
|
||
- **Cloning the wrong repo.** `interns-mcp` lives inside the `common` monorepo at `OpeItcLoc03/common.git`, not as a separate `interns-mcp` repo. Always clone `common.git` and verify the subdirectory. |