mirror of
https://github.com/getpaseo/paseo.git
synced 2026-07-29 12:01:31 +00:00
Update skill CLI examples to use --provider provider/model format
Always specify the model in paseo run examples (e.g. --provider codex/gpt-5.4 instead of --provider codex) to prevent agents from launching with wrong defaults.
This commit is contained in:
Mohamed Boudra
@@ -77,8 +77,8 @@ $NO_EDITS"
|
||||
Same prompt to both, `[Committee]` prefix for identification:
|
||||
|
||||
```bash
|
||||
opus_id=$(paseo run -d --mode bypassPermissions --model opus --thinking on --name "[Committee] Task description" "$prompt" -q)
|
||||
gpt_id=$(paseo run -d --mode full-access --provider codex --model gpt-5.4 --thinking medium --name "[Committee] Task description" "$prompt" -q)
|
||||
opus_id=$(paseo run -d --mode bypassPermissions --provider claude/opus --thinking on --name "[Committee] Task description" "$prompt" -q)
|
||||
gpt_id=$(paseo run -d --mode full-access --provider codex/gpt-5.4 --thinking medium --name "[Committee] Task description" "$prompt" -q)
|
||||
```
|
||||
|
||||
### Wait for both
|
||||
@@ -129,7 +129,7 @@ paseo send "$gpt_id" "Merged plan: [plan]. Concerns? $NO_EDITS"
|
||||
Implement the plan yourself — unless the user said **"delegate"**, in which case launch an implementer:
|
||||
|
||||
```bash
|
||||
impl_id=$(paseo run -d --mode full-access --provider codex --name "[Impl] Task description" "Implement the following plan end-to-end. [plan]" -q)
|
||||
impl_id=$(paseo run -d --mode full-access --provider codex/gpt-5.4 --name "[Impl] Task description" "Implement the following plan end-to-end. [plan]" -q)
|
||||
paseo wait "$impl_id"
|
||||
```
|
||||
|
||||
|
||||
@@ -30,13 +30,13 @@ Parse `$ARGUMENTS` to determine:
|
||||
|
||||
### Provider Resolution
|
||||
|
||||
| User says | Provider | Model | Mode |
|
||||
|---|---|---|---|
|
||||
| *(nothing)* | `codex` | `gpt-5.4` | `full-access` |
|
||||
| `codex` | `codex` | `gpt-5.4` | `full-access` |
|
||||
| `claude` | `claude` | `opus` | `bypass` |
|
||||
| `opus` | `claude` | `opus` | `bypass` |
|
||||
| `sonnet` | `claude` | `sonnet` | `bypass` |
|
||||
| User says | --provider | Mode |
|
||||
|---|---|---|
|
||||
| *(nothing)* | `codex/gpt-5.4` | `full-access` |
|
||||
| `codex` | `codex/gpt-5.4` | `full-access` |
|
||||
| `claude` | `claude/opus` | `bypass` |
|
||||
| `opus` | `claude/opus` | `bypass` |
|
||||
| `sonnet` | `claude/sonnet` | `bypass` |
|
||||
|
||||
Default is **Codex** with `gpt-5.4`.
|
||||
|
||||
@@ -109,27 +109,27 @@ This is the critical step. The receiving agent has **zero context** about your c
|
||||
### Default (Codex, no worktree)
|
||||
|
||||
```bash
|
||||
paseo run -d --mode full-access --provider codex --name "[Handoff] Task description" "$prompt"
|
||||
paseo run -d --mode full-access --provider codex/gpt-5.4 --name "[Handoff] Task description" "$prompt"
|
||||
```
|
||||
|
||||
### Claude (Opus, no worktree)
|
||||
|
||||
```bash
|
||||
paseo run -d --mode bypassPermissions --model opus --name "[Handoff] Task description" "$prompt"
|
||||
paseo run -d --mode bypassPermissions --provider claude/opus --name "[Handoff] Task description" "$prompt"
|
||||
```
|
||||
|
||||
### Codex in a worktree
|
||||
|
||||
```bash
|
||||
base=$(git branch --show-current)
|
||||
paseo run -d --mode full-access --provider codex --worktree task-branch-name --base "$base" --name "[Handoff] Task description" "$prompt"
|
||||
paseo run -d --mode full-access --provider codex/gpt-5.4 --worktree task-branch-name --base "$base" --name "[Handoff] Task description" "$prompt"
|
||||
```
|
||||
|
||||
### Claude in a worktree
|
||||
|
||||
```bash
|
||||
base=$(git branch --show-current)
|
||||
paseo run -d --mode bypass --model opus --worktree task-branch-name --base "$base" --name "[Handoff] Task description" "$prompt"
|
||||
paseo run -d --mode bypass --provider claude/opus --worktree task-branch-name --base "$base" --name "[Handoff] Task description" "$prompt"
|
||||
```
|
||||
|
||||
## After Launch
|
||||
|
||||
@@ -39,8 +39,8 @@ Every loop needs at least one form of verification:
|
||||
|
||||
Choose the right provider/model for worker and verifier independently:
|
||||
|
||||
- `--provider`/`--model` — sets the worker's provider and model
|
||||
- `--verify-provider`/`--verify-model` — sets the verifier's provider and model
|
||||
- `--provider <provider/model>` — sets the worker (e.g. `codex/gpt-5.4`)
|
||||
- `--verify-provider <provider/model>` — sets the verifier (e.g. `claude/opus`)
|
||||
|
||||
Default: both use Claude/sonnet. For implementation loops, use Codex for the worker and Claude for the verifier — each catches the other's blind spots.
|
||||
|
||||
@@ -64,7 +64,7 @@ paseo loop run "Check PR #42. Review CI, comments, and branch status. Fix issues
|
||||
|
||||
```bash
|
||||
paseo loop run "Run the test suite, investigate failures, and fix the code." \
|
||||
--provider codex \
|
||||
--provider codex/gpt-5.4 \
|
||||
--verify "Run the test suite. Return done=true only if all tests pass. Cite the exact command and outcome." \
|
||||
--verify-check "npm test" \
|
||||
--max-iterations 10 \
|
||||
@@ -75,9 +75,9 @@ paseo loop run "Run the test suite, investigate failures, and fix the code." \
|
||||
|
||||
```bash
|
||||
paseo loop run "Implement issue #456. Make incremental progress each iteration." \
|
||||
--provider codex \
|
||||
--provider codex/gpt-5.4 \
|
||||
--verify "Verify issue #456 is complete. Check changed files, run typecheck and tests." \
|
||||
--verify-provider claude --verify-model sonnet \
|
||||
--verify-provider claude/sonnet \
|
||||
--max-iterations 8 \
|
||||
--max-time 2h \
|
||||
--archive \
|
||||
|
||||
@@ -78,7 +78,7 @@ Launch agents with lightweight initial prompts. Each agent gets:
|
||||
### Initial prompt template
|
||||
|
||||
```bash
|
||||
paseo run -d --mode full-access --provider codex \
|
||||
paseo run -d --mode full-access --provider codex/gpt-5.4 \
|
||||
--name "impl-<scope>" \
|
||||
"You are an implementation engineer on a team.
|
||||
|
||||
@@ -114,10 +114,10 @@ Pick the right provider for each role:
|
||||
|
||||
| Role | Provider | Why |
|
||||
|---|---|---|
|
||||
| Implementation | `codex` / `gpt-5.4` | Thorough, methodical, good at deep implementation |
|
||||
| Review / Audit | `claude` / `opus` | Good design instinct, catches over-engineering |
|
||||
| Investigation | `claude` / `opus` | Strong reasoning, good at tracing code paths |
|
||||
| Planning | `claude` / `opus` with `--thinking on` | Extended thinking for complex problems |
|
||||
| Implementation | `--provider codex/gpt-5.4` | Thorough, methodical, good at deep implementation |
|
||||
| Review / Audit | `--provider claude/opus` | Good design instinct, catches over-engineering |
|
||||
| Investigation | `--provider claude/opus` | Strong reasoning, good at tracing code paths |
|
||||
| Planning | `--provider claude/opus --thinking on` | Extended thinking for complex problems |
|
||||
|
||||
Cross-provider review: Codex implements → Claude reviews. Claude implements → Codex reviews. Each catches the other's blind spots.
|
||||
|
||||
@@ -179,7 +179,7 @@ paseo stop <old-agent-id>
|
||||
# (archiving happens automatically if the agent was part of a loop with --archive)
|
||||
|
||||
# Launch a fresh one
|
||||
paseo run -d --mode full-access --provider codex \
|
||||
paseo run -d --mode full-access --provider codex/gpt-5.4 \
|
||||
--name "impl-<scope>-v2" \
|
||||
"You are picking up work from a previous agent. Load the paseo-chat skill. Read room '<room>' from the beginning to catch up on the full history — the objective, what was done, what went wrong. Introduce yourself and continue from where the previous agent left off. @mention <orchestrator-id> when you've caught up." -q
|
||||
```
|
||||
@@ -191,7 +191,7 @@ The chat room has the full history. The new agent reads it and continues.
|
||||
After implementation is done, launch a review agent (opposite provider):
|
||||
|
||||
```bash
|
||||
paseo run -d --mode bypassPermissions --model opus \
|
||||
paseo run -d --mode bypassPermissions --provider claude/opus \
|
||||
--name "review-<scope>" \
|
||||
"You are a reviewer on a team. Load the paseo-chat skill. Read room '<room>' to understand the objective and what was implemented.
|
||||
|
||||
|
||||
@@ -14,8 +14,8 @@ paseo ls --json # JSON output for parsing
|
||||
# Create and run an agent (blocks until completion by default, no timeout)
|
||||
paseo run --mode bypassPermissions "<prompt>"
|
||||
paseo run --mode bypassPermissions --name "task-name" "<prompt>"
|
||||
paseo run --mode bypassPermissions --model opus "<prompt>"
|
||||
paseo run --mode full-access --provider codex "<prompt>"
|
||||
paseo run --mode bypassPermissions --provider claude/opus "<prompt>"
|
||||
paseo run --mode full-access --provider codex/gpt-5.4 "<prompt>"
|
||||
|
||||
# Wait timeout - limit how long run blocks (default: no limit)
|
||||
paseo run --wait-timeout 30m "<prompt>" # Wait up to 30 minutes
|
||||
@@ -86,10 +86,8 @@ paseo loop run "<worker prompt>" [options]
|
||||
--sleep <duration> # Delay between iterations (30s, 5m)
|
||||
--max-iterations <n> # Maximum number of iterations
|
||||
--max-time <duration> # Maximum total runtime (1h, 30m)
|
||||
--provider <provider> # Worker agent provider (claude, codex)
|
||||
--model <model> # Worker agent model
|
||||
--verify-provider <provider> # Verifier agent provider
|
||||
--verify-model <model> # Verifier agent model
|
||||
--provider <provider/model> # Worker agent provider/model (e.g. codex/gpt-5.4)
|
||||
--verify-provider <provider/model> # Verifier agent provider/model (e.g. claude/opus)
|
||||
--archive # Archive agents after each iteration
|
||||
|
||||
# Manage loops
|
||||
@@ -209,18 +207,18 @@ paseo terminal kill "$id"
|
||||
|
||||
## Available Models
|
||||
|
||||
**Claude (default provider)** — use aliases, CLI resolves to latest version:
|
||||
- `--model haiku` — Fast/cheap, ONLY for tests (not for real work)
|
||||
- `--model sonnet` — Default, good for most tasks
|
||||
- `--model opus` — For harder reasoning, complex debugging
|
||||
**Claude (default provider):**
|
||||
- `--provider claude/haiku` — Fast/cheap, ONLY for tests (not for real work)
|
||||
- `--provider claude/sonnet` — Good for most tasks
|
||||
- `--provider claude/opus` — For harder reasoning, complex debugging
|
||||
|
||||
**Codex** (`--provider codex`):
|
||||
- `--model gpt-5.4` — Latest frontier agentic coding model (default, preferred for all engineering tasks)
|
||||
- `--model gpt-5.1-codex-mini` — Cheaper, faster, but less capable
|
||||
**Codex:**
|
||||
- `--provider codex/gpt-5.4` — Latest frontier agentic coding model (preferred for all engineering tasks)
|
||||
- `--provider codex/gpt-5.1-codex-mini` — Cheaper, faster, but less capable
|
||||
|
||||
## Permissions
|
||||
|
||||
Always launch agents fully permissioned. Use `--mode bypassPermissions` for Claude and `--mode full-access` for Codex. Control behavior through **strict prompting**, not permission modes.
|
||||
Always launch agents fully permissioned. Use `--mode bypassPermissions` for Claude and `--mode full-access` for Codex. Always specify the model: `--provider claude/opus`, `--provider codex/gpt-5.4`, etc. Control behavior through **strict prompting**, not permission modes.
|
||||
|
||||
## Waiting for Agents
|
||||
|
||||
|
||||
Reference in New Issue
Block a user