puter/paseo
1
0
Fork 0
mirror of https://github.com/getpaseo/paseo.git synced 2026-07-29 12:01:31 +00:00
Code Issues Packages Projects Releases Wiki Activity

Update skill CLI examples to use --provider provider/model format

Browse Source 
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
2026-04-04 17:40:37 +07:00
parent 155c88254b
commit c5a69a1ad9
5 changed files with 38 additions and 40 deletions
Download Patch File Download Diff File Expand all files Collapse all files

6
skills/paseo-committee/SKILL.md
View File

@@ -77,8 +77,8 @@ $NO_EDITS"
Same prompt to both, `[Committee]` prefix for identification: Same prompt to both, `[Committee]` prefix for identification:
```bash ```bash
opus_id=$(paseo run -d --mode bypassPermissions --model opus --thinking on --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 --model gpt-5.4 --thinking medium --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" "$prompt" -q)
``` ```
### Wait for both ### Wait for both
@@ -129,7 +129,7 @@ paseo send "$gpt_id" "Merged plan: [plan]. Concerns? $NO_EDITS"
Implement the plan yourself — unless the user said **"delegate"**, in which case launch an implementer: Implement the plan yourself — unless the user said **"delegate"**, in which case launch an implementer:
```bash ```bash
impl_id=$(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" paseo wait "$impl_id"
``` ```

22
skills/paseo-handoff/SKILL.md
View File

@@ -30,13 +30,13 @@ Parse `$ARGUMENTS` to determine:
### Provider Resolution ### Provider Resolution
| User says | Provider | Model | Mode | | User says | --provider | Mode |
|---|---|---|---| |---|---|---|
| *(nothing)* | `codex` | `gpt-5.4` | `full-access` | | *(nothing)* | `codex/gpt-5.4` | `full-access` |
| `codex` | `codex` | `gpt-5.4` | `full-access` | | `codex` | `codex/gpt-5.4` | `full-access` |
| `claude` | `claude` | `opus` | `bypass` | | `claude` | `claude/opus` | `bypass` |
| `opus` | `claude` | `opus` | `bypass` | | `opus` | `claude/opus` | `bypass` |
| `sonnet` | `claude` | `sonnet` | `bypass` | | `sonnet` | `claude/sonnet` | `bypass` |
Default is **Codex** with `gpt-5.4`. Default is **Codex** with `gpt-5.4`.
@@ -109,27 +109,27 @@ This is the critical step. The receiving agent has **zero context** about your c
### Default (Codex, no worktree) ### Default (Codex, no worktree)
```bash ```bash
paseo run -d --mode full-access --provider codex --name "[Handoff] Task description" "$prompt" paseo run -d --mode full-access --provider codex/gpt-5.4 --name "[Handoff] Task description" "$prompt"
``` ```
### Claude (Opus, no worktree) ### Claude (Opus, no worktree)
```bash ```bash
paseo run -d --mode bypassPermissions --model opus --name "[Handoff] Task description" "$prompt" paseo run -d --mode bypassPermissions --provider claude/opus --name "[Handoff] Task description" "$prompt"
``` ```
### Codex in a worktree ### Codex in a worktree
```bash ```bash
base=$(git branch --show-current) 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" "$prompt"
``` ```
### Claude in a worktree ### Claude in a worktree
```bash ```bash
base=$(git branch --show-current) 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 ## After Launch

10
skills/paseo-loop/SKILL.md
View File

@@ -39,8 +39,8 @@ Every loop needs at least one form of verification:
Choose the right provider/model for worker and verifier independently: Choose the right provider/model for worker and verifier independently:
- `--provider`/`--model` — sets the worker's provider and model - `--provider <provider/model>` — sets the worker (e.g. `codex/gpt-5.4`)
- `--verify-provider`/`--verify-model` — sets the verifier's provider and model - `--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. 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 ```bash
paseo loop run "Run the test suite, investigate failures, and fix the code." \ 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 "Run the test suite. Return done=true only if all tests pass. Cite the exact command and outcome." \
--verify-check "npm test" \ --verify-check "npm test" \
--max-iterations 10 \ --max-iterations 10 \
@@ -75,9 +75,9 @@ paseo loop run "Run the test suite, investigate failures, and fix the code." \
```bash ```bash
paseo loop run "Implement issue #456. Make incremental progress each iteration." \ 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 "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-iterations 8 \
--max-time 2h \ --max-time 2h \
--archive \ --archive \

14
skills/paseo-orchestrator/SKILL.md
View File

@@ -78,7 +78,7 @@ Launch agents with lightweight initial prompts. Each agent gets:
### Initial prompt template ### Initial prompt template
```bash ```bash
paseo run -d --mode full-access --provider codex \ paseo run -d --mode full-access --provider codex/gpt-5.4 \
--name "impl-<scope>" \ --name "impl-<scope>" \
"You are an implementation engineer on a team. "You are an implementation engineer on a team.
@@ -114,10 +114,10 @@ Pick the right provider for each role:
| Role | Provider | Why | | Role | Provider | Why |
|---|---|---| |---|---|---|
| Implementation | `codex` / `gpt-5.4` | Thorough, methodical, good at deep implementation | | Implementation | `--provider codex/gpt-5.4` | Thorough, methodical, good at deep implementation |
| Review / Audit | `claude` / `opus` | Good design instinct, catches over-engineering | | Review / Audit | `--provider claude/opus` | Good design instinct, catches over-engineering |
| Investigation | `claude` / `opus` | Strong reasoning, good at tracing code paths | | Investigation | `--provider claude/opus` | Strong reasoning, good at tracing code paths |
| Planning | `claude` / `opus` with `--thinking on` | Extended thinking for complex problems | | 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. 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) # (archiving happens automatically if the agent was part of a loop with --archive)
# Launch a fresh one # 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" \ --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 "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): After implementation is done, launch a review agent (opposite provider):
```bash ```bash
paseo run -d --mode bypassPermissions --model opus \ paseo run -d --mode bypassPermissions --provider claude/opus \
--name "review-<scope>" \ --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. "You are a reviewer on a team. Load the paseo-chat skill. Read room '<room>' to understand the objective and what was implemented.

26
skills/paseo/SKILL.md
View File

@@ -14,8 +14,8 @@ paseo ls --json # JSON output for parsing
# Create and run an agent (blocks until completion by default, no timeout) # Create and run an agent (blocks until completion by default, no timeout)
paseo run --mode bypassPermissions "<prompt>" paseo run --mode bypassPermissions "<prompt>"
paseo run --mode bypassPermissions --name "task-name" "<prompt>" paseo run --mode bypassPermissions --name "task-name" "<prompt>"
paseo run --mode bypassPermissions --model opus "<prompt>" paseo run --mode bypassPermissions --provider claude/opus "<prompt>"
paseo run --mode full-access --provider codex "<prompt>" paseo run --mode full-access --provider codex/gpt-5.4 "<prompt>"
# Wait timeout - limit how long run blocks (default: no limit) # Wait timeout - limit how long run blocks (default: no limit)
paseo run --wait-timeout 30m "<prompt>" # Wait up to 30 minutes 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) --sleep <duration> # Delay between iterations (30s, 5m)
--max-iterations <n> # Maximum number of iterations --max-iterations <n> # Maximum number of iterations
--max-time <duration> # Maximum total runtime (1h, 30m) --max-time <duration> # Maximum total runtime (1h, 30m)
--provider <provider> # Worker agent provider (claude, codex) --provider <provider/model> # Worker agent provider/model (e.g. codex/gpt-5.4)
--model <model> # Worker agent model --verify-provider <provider/model> # Verifier agent provider/model (e.g. claude/opus)
--verify-provider <provider> # Verifier agent provider
--verify-model <model> # Verifier agent model
--archive # Archive agents after each iteration --archive # Archive agents after each iteration
# Manage loops # Manage loops
@@ -209,18 +207,18 @@ paseo terminal kill "$id"
## Available Models ## Available Models
**Claude (default provider)** — use aliases, CLI resolves to latest version: **Claude (default provider):**
- `--model haiku` — Fast/cheap, ONLY for tests (not for real work) - `--provider claude/haiku` — Fast/cheap, ONLY for tests (not for real work)
- `--model sonnet` — Default, good for most tasks - `--provider claude/sonnet` — Good for most tasks
- `--model opus` — For harder reasoning, complex debugging - `--provider claude/opus` — For harder reasoning, complex debugging
**Codex** (`--provider codex`): **Codex:**
- `--model gpt-5.4` — Latest frontier agentic coding model (default, preferred for all engineering tasks) - `--provider codex/gpt-5.4` — Latest frontier agentic coding model (preferred for all engineering tasks)
- `--model gpt-5.1-codex-mini` — Cheaper, faster, but less capable - `--provider codex/gpt-5.1-codex-mini` — Cheaper, faster, but less capable
## Permissions ## 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 ## Waiting for Agents