Agent skill

Herald Autopilot

by herald-email in herald-email/herald-mail-app

A skill your agent uses when you want one repo-local Herald workflow to take a single bug, feature, or workflow improvement from intake through planning, isolated worktree setup, implementation…

Custom licenceAuto-check passedDevelopment

Install Herald Autopilot

skills CLI
$ npx skills add herald-email/herald-mail-app --skill herald-autopilot -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install herald-email/herald-mail-app herald-autopilot --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/herald-email/herald-mail-app.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.agents/skills/herald-autopilot .claude/skills/herald-autopilot && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
herald-autopilot
GitHub stars
146
Token cost
~4.9k tokens
SKILL.md length
1,935 words
Files
47 (incl. scripts, references)
Skills in repo
7
Repo updated
First seen
Licence
Custom licence

At a glance

A skill your agent uses when you want one repo-local Herald workflow to take a single bug, feature, or workflow improvement from intake through planning, isolated worktree setup, implementation…

  • Works in 12 steps: Treat one invocation as one task. → Ask only critical questions that change… → Show a concise plan summary, then… → …
  • You want one repo-local Herald workflow to take a single bug
  • SKILL.md covers When To Use, Do Not Use, Required Reads and Default Contract, plus 11 more sections
  • Runs Python scripts from its folder; calls python3 and git

What it does

Herald Autopilot is an agent skill from herald-email/herald-mail-app. Use when you want one repo-local Herald workflow to take a single bug, feature, or workflow improvement from intake through planning, isolated worktree setup, implementation, impact-based verification, branch handoff, and GEPA-style run logging.

Its SKILL.md is about 4.9k tokens, which your agent loads only when the skill is triggered. The skill folder holds 48 other files, including scripts and reference files (for example `references/gepa-improvement.md`, `references/product-truth.md` and `references/remediation-templates.json`).

It sits in Development, covering Git worktrees. The repository describes itself as: Herald is a terminal email client and inbox cleanup tool with IMAP, AI-assisted triage, MCP tools, and SSH/browser-friendly app modes.

When your agent uses it

  • You want one repo-local Herald workflow to take a single bug
  • Workflow improvement from intake through planning
  • Isolated worktree setup
  • Impact-based verification

Example prompts

  • “/herald-autopilot”

Requirements

  • Python 3

Workflow steps

12 steps, taken from the first numbered list in SKILL.md.

  1. Treat one invocation as one task.
  2. Ask only critical questions that change implementation or safety.
  3. Show a concise plan summary, then proceed unless a risky or non-obvious tradeoff needs the user's decision.
  4. Before tracked-file edits, explicitly ask whether the plan intentionally degrades, removes, or weakens existing behavior. No degradation…
  5. Record the degradation review gate with preserved behaviors and regression checks. If degradation is approved, record the approved…
  6. Select and record a verification budget before implementation: focused, package, visual/TUI, surface smoke, or release/hardening. Use the…
  7. Prefer deterministic internal/testmail virtual lab scenarios for realistic mail shapes before using private live mailboxes. Report whether…
  8. Run preflight for docs, SSH, and media prerequisites before baseline or implementation work begins.
  9. Verify baseline, then create and switch into a dedicated worktree under .worktrees/ before any tracked-file edits. Creating only a branch…
  10. Keep all raw machine-readable artifacts under .superpowers/autopilot/runs//.
  11. Stop at local branch + worktree + report. Do not push, create a PR, or merge unless the user asks.
  12. If the user asks to commit, merge, push, or open a PR, do that requested publish step and then surface a visible self-reflection report…

What it can do on your machine

Read from SKILL.md and the folder at commit b097c04. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Ships 11 files in scripts/ (Python, from the files we listed), which the agent can run.

    Shell commands in SKILL.md call:

    • python3
    • git

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md. Its commands use git, which can reach the network depending on how they are called.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Herald Autopilot loads about 4.9k tokens when it runs, and up to ~15k if it reads all its reference files. Until then it costs about 66 tokens; SKILL.md has 1,935 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~66
When it runs · the whole SKILL.md, loaded when a task matches
~4.9k
With references · SKILL.md plus every file in references/, read only if the agent opens them
~15k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); the scripts in this folder are not scanned.

SKILL.md

Its licence (Custom licence) doesn't allow us to republish the file, so here is its outline and opening line. It has 1,935 words (~4,946 tokens).

“Use this skill when the user wants to hand off one Herald task and come back later to a branch, verification evidence, and a readable report. This skill is intentionally single-task and single-worktree in v1 so it stays predictable while…”

— opening of SKILL.md by herald-email, Custom licence
name
herald-autopilot

Read the full SKILL.md on GitHub

Files

SKILL.md and 46 other files (scripts, references) in .agents/skills/herald-autopilot of herald-email/herald-mail-app.

  • SKILL.md
  • references/gepa-improvement.md
  • references/product-truth.md
  • references/remediation-templates.json
  • references/run-schema.md
  • references/two-candidate-worktree-trial.md
  • references/verification-routing.md
  • references/workflow-contract.md
  • scripts/analyze_recent_runs.py
  • scripts/append_improvement_log.py
  • scripts/artifact_io.py
  • scripts/bootstrap_run.py
  • scripts/build_frontier.py
  • scripts/capture_evidence.py
  • scripts/degradation_review.py
  • scripts/extract_feedback_patterns.py
  • scripts/input_routing.py
  • scripts/measure_phase_impact.py
  • scripts/measure_template_adoption.py
  • … and 28 more

Open the folder on GitHubat commit b097c04

Compare with similar skills

Herald Autopilot next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Herald Autopilot compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Herald Autopilot this skillherald-email/herald-mail-app146—~4.9kAutomated safety check: PassCustom licence
Finishing a Development Branchobra/superpowers297k5 repos~1.9kAutomated safety check: PassMIT
Migrate Core Code to Submodulestinyhumansai/openhuman42k—~2.6kAutomated safety check: PassGPL-3.0
Finishing A Development Branchfarm-fe/farm5.6k35 repos~1.8kAutomated safety check: PassMIT
Git Worktree Cleanuplobehub/lobehub83k—~2.8kAutomated safety check: PassCustom licence
Keep Codex Fastvibeforge1111/keep-codex-fast1.6k—~3.1kAutomated safety check: PassMIT

Similar skills

  • Walks the last step of a branch: confirm tests pass, detect the git environment, ask how to integrate, carry out your choice and clean up the worktree.

    297k GitHub starsUsed in 5 repos~1.9k tokens
    DevelopmentAuto-check passed
  • Migrate Core Code to Submodules

    tinyhumansai/openhuman

    Plans and carries out moving non-host-specific code and its tests from the OpenHuman core into vendored tiny submodule libraries, then releases the submodule and re-pins the host.

    42k GitHub stars~2.6k tokensUpdated today
    DevelopmentAuto-check passed
  • A skill your agent uses when implementation is complete, all tests pass, and you need to decide how to integrate the work - guides completion of development work by presenting structured options for…

    5.6k GitHub starsUsed in 35 repos~1.8k tokens
    DevelopmentAuto-check passed
  • Git Worktree Cleanup

    lobehub/lobehub

    Audits stale Git worktrees and branches with a bundled script, classifies each one, and deletes only after you approve the exact candidates.

    83k GitHub stars~2.8k tokensUpdated today
    DevelopmentAuto-check passed
  • Keep Codex Fast

    vibeforge1111/keep-codex-fast

    A skill your agent uses when Codex feels slow or bloated, when local sessions/logs/worktrees/config have grown over time, or when a user wants safe maintenance for Codex Desktop/CLI state.

    1.6k GitHub stars~3.1k tokensUpdated 5 mo ago
    DevelopmentAuto-check passed
  • Pre-Release PR Triage

    jamiepine/voicebox

    Sorts a backlog of open pull requests into must-merge, candidate, superseded and deferred, writes a triage doc and works the merge loop before a release.

    57k GitHub stars~3.1k tokensUpdated 4 days ago
    DevelopmentAuto-check passed

More from herald-email/herald-mail-app

  • Pre Release Test

    herald-email/herald-mail-app

    A skill your agent uses when preparing a Herald beta release, checking release readiness, or running broad deterministic integration gates across TUI themes, inline images, SSH, and MCP before…

    146 GitHub stars~448 tokensUpdated 3 mo ago
    Auto-check passed
  • Approve Gepa Changes

    herald-email/herald-mail-app

    A skill your agent uses when approving, rejecting, or marking implemented Herald GEPA pending approval items, including requests like "approve GEPA changes", "approve all pending GEPA", or approval…

    146 GitHub stars~881 tokensUpdated 3 mo ago
    Auto-check passed
  • Finish Development

    herald-email/herald-mail-app

    Herald-specific completion workflow for requests such as "finish-development", "nice" as a repo completion command, "wrap this branch", "fast merge", "fastpass", "quick merge", "fast mode", or…

    146 GitHub stars~2.4k tokensUpdated 3 mo ago
    Auto-check passed
  • Release

    herald-email/herald-mail-app

    Herald beta release workflow for requests to cut, tag, publish, or repair a Herald release.

    146 GitHub stars~2.2k tokensUpdated 3 mo ago
    Auto-check passed
  • Tui Test

    herald-email/herald-mail-app

    Battle-test terminal UIs such as Herald via tmux and ttyd: reset states, compare visible hotkeys with actual behavior, capture ANSI/PNG evidence, run resize soaks, and verify terminal raster image…

    146 GitHub stars~3.1k tokensUpdated 3 mo ago
    Auto-check: notes
  • Tui Test

    herald-email/herald-mail-app

    Battle-test the Herald TUI — automated exploratory testing that captures screens, detects visual defects programmatically, and digs into anything suspicious.

    146 GitHub stars~3.5k tokensUpdated 3 mo ago
    Auto-check: notes

Categories

Questions about Herald Autopilot

What does Herald Autopilot do?

A skill your agent uses when you want one repo-local Herald workflow to take a single bug, feature, or workflow improvement from intake through planning, isolated worktree setup, implementation…. Herald Autopilot is an agent skill from herald-email/herald-mail-app. Use when you want one repo-local Herald workflow to take a single bug, feature, or workflow improvement from intake through planning, isolated worktree setup, implementation, impact-based verification, branch handoff, and GEPA-style run logging.

When should I use Herald Autopilot?

Herald Autopilot fits situations like: you want one repo-local Herald workflow to take a single bug; workflow improvement from intake through planning; isolated worktree setup; impact-based verification.

How do I install Herald Autopilot in Claude Code?

Run `npx skills add herald-email/herald-mail-app --skill herald-autopilot -a claude-code`. Or copy the skill folder (.agents/skills/herald-autopilot in herald-email/herald-mail-app) into .claude/skills/herald-autopilot in your project. Claude Code loads it when a task matches its description.

How do I install Herald Autopilot in Codex?

Run `npx skills add herald-email/herald-mail-app --skill herald-autopilot -a codex`. Or copy the skill folder (.agents/skills/herald-autopilot in herald-email/herald-mail-app) into .agents/skills/herald-autopilot in your project. Codex loads it when a task matches its description.

Can I use Herald Autopilot in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add herald-email/herald-mail-app --skill herald-autopilot -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/herald-autopilot, .gemini/skills/herald-autopilot, .github/skills/herald-autopilot and .opencode/skills/herald-autopilot in your project.

What does Herald Autopilot need to run?

Going by SKILL.md and its folder, Herald Autopilot needs Python for the scripts in its folder and the command-line tools its instructions call (python3 and git). Our summary lists: Python 3.

Does Herald Autopilot access the network?

SKILL.md contains no URLs. Its commands use git, which can reach the network depending on how they are called. This is read from the text; nothing was executed.

Is Herald Autopilot safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. The check reads SKILL.md only: the scripts in the folder are not scanned, so read them before running anything.

What licence does Herald Autopilot use?

Herald Autopilot has a licence file (the repository's licence) that doesn't match a standard licence. Read it on GitHub before reusing the skill.

How many tokens does Herald Autopilot use?

About 4.9k tokens (SKILL.md is roughly 20k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 9.6k tokens, read only when the agent opens those files.

What are the alternatives to Herald Autopilot?

Skills that share tags, products or a category with Herald Autopilot: Finishing a Development Branch (obra/superpowers, 297k stars), Migrate Core Code to Submodules (tinyhumansai/openhuman, 42k stars), Finishing A Development Branch (farm-fe/farm, 5.6k stars) and Git Worktree Cleanup (lobehub/lobehub, 83k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Herald Autopilot?

herald-email (a GitHub organization) maintains it in herald-email/herald-mail-app, which has 146 GitHub stars. The repository holds 7 skills in this directory. The repository was last updated on July 13, 2026.

Source: herald-email/herald-mail-app on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.