agentleFS
karloowskarloows/orchraft/skills/warchief/SKILL.md

warchief

Skill1 starsChanged 52 days agoApache-2.0View on GitHub

Have the AI choose the next orchraft lifecycle step and hand off to the right skill, without performing git or GitHub mutations. Use when the user says warchief, asks what should happen next, or wants orchraft to route the work.

The file

Show its rules and text

We split this skill into the rules it gives an agent

25 rules. About 0 are common, 7 are distinctive, and 18 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈7

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 18

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Use this skill when the user wants the clan to decide what should happen next across the software lifecycle, instead of naming a specific …

    line 8
  2. Distinctive:

    Read the user's goal and the current repo state.

    line 13
  3. Distinctive:

    Stop before every git, PR, issue, or release mutation unless the current message explicitly approves that exact mutating workflow, or the …

    line 19
  4. Distinctive:

    Treat user-facing role names as portable workflow roles.

    line 29
  5. Very specific:

    Use Forgehand for implementation and tests.

    line 34
  6. Very specific:

    Use Warpath when the user explicitly asks to repeat fix → ship → roast until the latest roast reports zero findings.

    line 36
  7. Very specific:

    Use Trialmaster for read-only review findings.

    line 39
  8. Very specific:

    Use Tactician / warplan when the work needs a grounded implementation plan before code changes.

    line 41
  9. Very specific:

    Use Quest-Giver / quest when the next useful artifact is an issue or issue update.

    line 43
  10. Very specific:

    Use Raid Captain / ship only when the user explicitly asks to branch, commit, push, or open/update a PR in the current turn.

    line 45
  11. Very specific:

    Use Trialmaster / roast when the user asks for PR review or the PR is ready for review.

    line 47
  12. Very specific:

    Use Rune-Reader / runes when the user asks for status, resume, or where work stands.

    line 49
  13. Very specific:

    Use Scout / yap when the user asks to explain a file, diff, PR, policy, or error.

    line 51
  14. Very specific:

    Use Loremaster / lore when the user asks to add or clean up comments/docstrings.

    line 53
  15. Very specific:

    Use Chronicler / chronicle when the user asks to write or update a standalone Markdown document.

    line 55
  16. Very specific:

    Use Haulmaster / land only when the user explicitly asks to merge/land in the current turn.

    line 57
  17. Very specific:

    Use Herald / herald when the user asks for release notes or what a release shipped.

    line 59
  18. Very specific:

    Use Reckoner / reckoning when the user asks which review findings were declined rather than fixed.

    line 61
  19. Distinctive:

    If more than one route fits, choose the earliest lifecycle step that removes real uncertainty.

    line 66
  20. Very specific:

    Read context/policies/approval-policy.md before any route that could mutate git, PRs, issues, or releases.

    line 72
  21. Very specific:

    Never treat the warchief request itself as approval to commit, push, open/update/merge a PR, resolve a thread, mutate an issue, or write a …

    line 74
  22. Very specific:

    Do not create a stored state file.

    line 77
  23. Very specific:

    Do not chain multiple mutating skills from one approval.

    line 78
  24. Distinctive:

    If that role is mutating and neither the current turn nor a verified Autonomous Mode entry authorizes it, ask for the exact go-ahead …

    line 92
  25. Distinctive:

    If a non-mutating role fits and no approval is needed, run it directly.

    line 95

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Warchief Workflow

Use this skill when the user wants the clan to decide what should happen next across the software lifecycle, instead of naming a specific skill.

At A Glance

  1. Read the user's goal and the current repo state.
  2. Choose the next fitting orchraft role: Quest-Giver, Tactician, Forgehand, Warpath, Raid Captain, Trialmaster, Haulmaster, Herald, Rune-Reader, Reckoner, Scout, Loremaster, or Chronicler.
  3. Explain the handoff briefly, then run only the step the approval policy says is authorized.
  4. Stop before every git, PR, issue, or release mutation unless the current message explicitly approves that exact mutating workflow, or the verified Autonomous Mode from the applicable approval policy or active config names that exact action. For configs, apply the shared verification rules, including the trusted exact-path ignore check for a local config absent from the default branch. A failed or mismatched verification is not authorization.

Routing

  • Treat user-facing role names as portable workflow roles. Run the matching skill on every host; when the host exposes a compatible named subagent, delegate to its adapter: forgehand, tactician, scout, loremaster, trialmaster, chronicler, or rune-reader. These agents stop before mutations that require separate approval.
  • Use Forgehand for implementation and tests. It may edit files but never commits, pushes, opens a PR, posts a review, merges, or changes an issue.
  • Use Warpath when the user explicitly asks to repeat fix → ship → roast until the latest roast reports zero findings. It re-reads live state after each cycle, pauses at approval gates, and hands off a clean PR to land.
  • Use Trialmaster for read-only review findings. It may inspect code and use roast's policy, but never posts the review.
  • Use Tactician / warplan when the work needs a grounded implementation plan before code changes.
  • Use Quest-Giver / quest when the next useful artifact is an issue or issue update.
  • Use Raid Captain / ship only when the user explicitly asks to branch, commit, push, or open/update a PR in the current turn.
  • Use Trialmaster / roast when the user asks for PR review or the PR is ready for review.
  • Use Rune-Reader / runes when the user asks for status, resume, or where work stands.
  • Use Scout / yap when the user asks to explain a file, diff, PR, policy, or error.
  • Use Loremaster / lore when the user asks to add or clean up comments/docstrings.
  • Use Chronicler / chronicle when the user asks to write or update a standalone Markdown document.
  • Use Haulmaster / land only when the user explicitly asks to merge/land in the current turn.
  • Use Herald / herald when the user asks for release notes or what a release shipped.
  • Use Reckoner / reckoning when the user asks which review findings were declined rather than fixed.

Direct skill names remain supported alongside these role aliases.

If more than one route fits, choose the earliest lifecycle step that removes real uncertainty. For example, plan before editing, status before shipping an unknown branch, and review before landing.

Guardrails

  • Read context/policies/approval-policy.md before any route that could mutate git, PRs, issues, or releases.
  • Never treat the warchief request itself as approval to commit, push, open/update/merge a PR, resolve a thread, mutate an issue, or write a release.
  • Do not create a stored state file. Use runes for live status.
  • Do not chain multiple mutating skills from one approval. A clean roast may make land the next recommendation, but land still needs its own current-turn go-ahead.
  • Warpath is the explicit exception for orchestration, not for approval: it may coordinate repeated lifecycle steps, but each mutation remains gated by the approval policy.

Handoff

  • Unless the user asked for plain output, open with a fresh one-line phrase in the orc voice, speaking as the Warchief from context/personality.md (the target repo's copy when it exists, otherwise ${CLAUDE_PLUGIN_ROOT}/context/personality.md).
  • Name the selected next role and why.
  • If that role is mutating and neither the current turn nor a verified Autonomous Mode entry authorizes it, ask for the exact go-ahead instead of running it.
  • If a non-mutating role fits and no approval is needed, run it directly.

Examples

Chief, the council calls for `runes` first: this branch's PR state is unknown.
Reading the board before we swing.
Chief, `ship` is the next march, but that means branch/commit/push/PR work.
Say "ship it" and we move.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.