Skip to content
Skills Library
AI & agents · Automation

delegate

/delegate

Runs one delegated codex exec, codex review, claude -p or ccx task call with wipnote delegate run, and finds its result on the run page and in the delegations ledger. Preview: one-shot runs only. Use when handing a single prompt or review to another harness and recording the run.

Repository
htmlgraph ↗
Licence
MIT
Last repository change
27.10.2026

Assessment and security

100/ 100Class: good
Format25 / 25
Frontmatter with name and description, valid name, description up to 1,024 characters, name matching the folder.
Discoverability25 / 25
Description explains when to use the skill, has a reasonable length and uses third person.
Content35 / 35
At least 150 words and at most 500 lines, headings, step lists, examples or code.
Hygiene15 / 15
No placeholders such as TODO, no Windows paths, with a licence.
Riskno signals detected in the scan
Files in this package
1
Scripts
0
HTML comments
0
URLs in SKILL.md
0
Deprecation

No signals detected. Repository changed on 27.10.2026, without references to retired models or APIs.

Licence

MIT, open: use and modify while retaining author attribution.

What it does and when to use it

Runs one delegated codex exec, codex review, claude -p or ccx task call with wipnote delegate run, and finds its result on the run page and in the delegations ledger. Preview: one-shot runs only. Use when handing a single prompt or review to another harness and recording the run.

Original author description

Runs one delegated codex exec, codex review, claude -p or ccx task call with wipnote delegate run, and finds its result on the run page and in the delegations ledger. Preview: one-shot runs only. Use when handing a single prompt or review to another harness and recording the run.

How it works

  1. Two one-shot paths until Release 2
  2. Run one call
  3. Where the results live
  4. Settings
Original SKILL.md headings · 77 lines, 790 words
SKILL.md preview
---
name: delegate
description: "Runs one delegated codex exec, codex review, claude -p or ccx task call with wipnote delegate run, and finds its result on the run page and in the delegations ledger. Preview: one-shot runs only. Use when handing a single prompt or review to another harness and recording the run."
disable-model-invocation: true
---

# wipnote delegate (preview)

**Release 1 is a preview.** It has one-shot runs only: one tool call that starts, runs and ends. Interactive workers (`spawn`, `send`, `wait`, `result`, `stop`, `questions`, `tree`, `list`, `inbox`, `doctor`) come in Release 2. Do not call those verbs; they do not exist yet.

## Two one-shot paths until Release 2

1. **`wipnote delegate run`** (this skill). Use it for new work. It records every run in the delegations ledger.
2. **The codex-herdr-pane mod.** It stays installed in Release 1. It wraps a bare `codex exec`, `codex review`, `claude -p` or `ccx task` call that you type in the Bash tool. Release 2 removes it, and this skill then covers the full delegate command.

The mod does not wrap a `wipnote delegate run` call, so a run never goes through both paths.

## Run one call

Copy this checklist and tick it off:

```
Delegate run:
- [ ] 1. Tool and prompt chosen (codex exec, codex review, claude -p or ccx task)
- [ ] 2. Command written: wipnote delegate run [flags] -- <tool argv>
- [ ] 3. Run finished; status line and answer read
- [ ] 4. Run page shown to the user, or its path given
- [ ] 5. Ledger row checked when the run is for a work item
```

The form is:

```bash
wipnote delegate run [--label L] [--work-item ID] [--no-pane] -- <tool argv>
```

Examples:

```bash
wipnote delegate run --label "review auth" -- codex review --base main
wipnote delegate run -- codex exec "Explain why TestFoo fails. Do not edit files."
wipnote delegate run --work-item feat-1234abcd -- claude -p "Summarise the open TODOs in core/"
wipnote delegate run -- ccx task "Run the slow integration tests and report failures"
```

| Flag | What it does |
|---|---|
| `--label L` | The pane title. It is the only label the ledger keeps. Without it, a title made from the prompt goes to the run folder only. |
| `--work-item ID` | The work item of the ledger row. The default is your active claim. |
| `--no-pane` | Run headless, also inside herdr. |

Rules:

- Put every wipnote flag before `--`. After `--`, all words go to the tool.
- Give one tool argv. Pipes, `;`, `&&` and redirects are refused. A prompt with spaces must be one quoted word.
- `--help` and `--version` are refused: they are not runs. Call the tool directly for them.
- `claude -p` must not set its own `--output-format` (only `stream-json` is accepted). The run adds `--output-format stream-json --verbose` itself.
- For `codex exec`, the run adds `--json` and `--output-last-message` (unless you set `-o`), and `-p <leanProfileName>` (default `lean`) when you set no profile and that profile file exists in the Codex home. `codex review` and `ccx task` run as given.
- Inside herdr (`HERDR_ENV=1`) the call runs in a herdr pane. Otherwise it runs headless.
- The command exits with the tool's exit status, or 130 when its pane was closed.
- A long run blocks until it ends. Run the command in the background when the harness lets you, and read the report when it ends.

## Where the results live

**The report.** When the run ends, the command prints:

- a status line: `codex exited 0 after 42s, ...; raw log <dir>/raw.log, answer file <dir>/last.md` (ccx prints its own status line instead);
- the answer from `last.md` when the run succeeded, or the end of `clean.log` when it failed. Long sections are cut, and a line names the file with the rest;
- the run page: `run page: <dir>/run.html`.

**The run page** (`run.html`) is the full run as one HTML page: status, answer and log. Show it to the user, or give them its path. To follow a live run in a terminal, use `wipnote delegate view <run-id>`.

**The run folder** is `.wipnote/delegate/runs/<run-id>/`. It holds `raw.log`, `clean.log`, `clean.md`, `last.md`, `usage`, `exit` and `run.html`. It is not committed. Finished runs are removed after `keepDays` (7 days by default).

**The delegations ledger** is `.wipnote/delegations-ledger.html`. It is committed. Each run is one row: run id (`dlg-...`), mode `oneshot`, harness (`codex`, `codex-review`, `claude-print` or `ccx`), label, work item, start and end, exit, end reason (`exit`, `stop`, `pane_closed` or `gone`) and token counts. Read it to see which runs a work item had. Never edit it by hand.

## Settings

The `delegate` object in the wipnote config sets run behaviour: `layout`, `maxPanes`, `closePane`, `closeDelay`, `tailLines`, `maxReturnLines`, `leanProfile`, `leanProfileName`, `ccxRunsDir`, `ccxWaitSeconds` and `keepDays`. Each key is merged from `~/.wipnote/config.json`, then `.wipnote/config.json`, then `.wipnote/config.local.json`. `ccxRunsDir` is a host path, so it is read only from the user file and the local file. `CCX_RUNS_DIR` overrides it.

`wipnote delegate run --help` prints the same facts.

Versions

RepositoryScoreLicence
This page · shakestzd/htmlgraph100MIT
aayushpokhrel1/delegation-pipeline100MIT
Filipeno/ai-hub100MIT
shakestzd/htmlgraph100MIT
easeit-cz/vornik100AGPL-3.0
hugrverk/riggverk100MIT
easeit-cz/vornik100AGPL-3.0
aayushpokhrel1/delegation-pipeline100MIT
erikmay/amp-tandem100MIT

Identical content appears in 1 other GitHub folders. We show one copy with the highest score.

Database snapshot: 13.11.2026 · package version 56ee583dc896 (SHA-256 digest of the entire package)

Downloads in the last 30 days: 0 · ranking

Report a problem with this skill: harmful content, incorrect descriptions or an author’s removal request.

Similar skills

  • 100codex-exec
    Run one prompt through headless Codex and capture the result. Use when: wanting a one-shot `codex exec` run or CI step. Not for batches or retries.
  • 100codex-rescue
    Delegate an implementation task to Codex, then Claude reviews the result. Use when asked \"codex rescue\", \"delegate to codex\", \"have codex do it\", or wants Codex to implement or fix something.
  • 95codex-delegate
    Delegate code implementation and verification to the OpenAI Codex CLI (`codex exec`) while Claude keeps design, planning and review. Use when the user wants Codex to write code, run builds/tests, or do a read-only repo analysis, or says "let Codex implement it". Covers locating…
  • 100codex
    Use the local Codex CLI as an independent second agent. Two branches — (1) proactively run `codex review` for a second opinion after completing a substantive change, before presenting it as done or committing; (2) delegate a well-defined implementation task via `codex exec`,…
  • 100local-codex
    Launches and manages the local OpenAI Codex CLI as a non-interactive coding sub-agent via ChatGPT OAuth, never API keys. Use to delegate coding tasks to Codex, run codex exec, generate or refactor code, or get a Codex code review; phrases like 'codex', 'run codex', 'codex exec', 'delegate to codex'.
  • 95codex-exec
    Run OpenAI Codex CLI non-interactively to execute tasks, generate code, or get a second opinion. Use this skill whenever the user says "run codex", "ask codex", "codex exec", "have codex do", "send to codex", "pipe to codex", or wants to delegate a task to Codex for a second…

Feedback and reports

Your message goes to Bartosz Sokoliński. An email address is needed only for a reply. See the privacy policy.