Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add skills/transparent-pegasus/herdrpowers/pane-driven-developmentnpx skills add transparent-pegasus/herdrpowers --skill pane-driven-developmentgit clone --depth 1 https://github.com/transparent-pegasus/herdrpowersWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/transparent-pegasus/herdrpowers/pane-driven-development)<a href="https://agentmods.dev/skills/transparent-pegasus/herdrpowers/pane-driven-development"><img src="https://agentmods.dev/badge/skills/transparent-pegasus/herdrpowers/pane-driven-development.svg" alt="Measured on agentmods" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00024 | $0.12058 |
| Opus 5 | $0.00012 | $0.06029 |
| Sonnet 5 | $0.00005 | $0.02412 |
| Haiku 4.5 | $0.00002 | $0.01206 |
Grade C, and why
pane-driven-development scanned grade C with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 4d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Recursive force deletehighDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
delete this plan's workspace (`rm -rf <workspace>`) — the git history is How it starts
The opening of the file, as written. The whole thing — 810 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Pane-Driven Development
Placeholder resolution: <KEY> placeholders in this file (such as <BASE_BRANCH> or <REPORT_DIRECTORY>) resolve from the Herdrpowers Configuration section of the repository's CLAUDE.md / AGENTS.md. If that section is missing, initialize it with the pack's init workflow (/herdrpowers:init on Claude Code plugin installs; commands/init.md otherwise).
Delegation Model (READ FIRST)
Every task in this skill is delegated to a herdr sibling agent pane, never to an in-process subagent — the sole exception is a review task whose resolved mode is orchestrator, which the orchestrator runs in a fresh spawned subagent. The orchestration skill decides which role takes a task; using-herdr-sibling-panes is the transport that submits it and waits for the completion marker. Read both before delegating anything.
Two boundaries override anything below:
- No in-process subagents. Wherever this document says "dispatch," read "delegate to an idle sibling pane through
using-herdr-sibling-panes." Named subagent types are not used by this pack, and the Agent tool is dispatched only for a review task whose resolved mode isorchestrator, per "Reviews inmode: orchestrator" inorchestration. - The pane that writes tests owns RED-GREEN-REFACTOR, and the resolved
test-authoring/fix-round-test-authoringassignments say which pane that is. Withmode: delegatea separate pane writes them from the task brief alone (see "Parallel test authoring" below); withmode: implementerthe implementing or fixing pane writes its own pertest-driven-development. Either way the pane that writes a test produces its RED evidence, and your report names which pane wrote the tests. Review independence itself comes from the reset session of each reviewing delegation, not from a named role or a different pane ID, and is never configurable.
Execute the plan by delegating a fresh implementer pane per task, the task's tests per test-authoring, a task review (spec compliance + code quality) after each, and a broad whole-branch review at the end.
What ships with it
7 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 4d ago First seen · 810 lines · 24 tokens per session scan C d9f4f41173cf
pane-driven-development is a skill published in the GitHub repository transparent-pegasus/herdrpowers (11 stars, last pushed 7d ago), licensed Apache-2.0. It adds 24 tokens to every session and 12,058 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it C with 1 finding (recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
plannotator-tui
Open a Markdown plan or document for the human to review and annotate in a Herdr pane; their feedback arrives as your next message. Use when you have written a plan, spec, or design document that needs human review before you act on it.
compound-v
Use when superpowers:brainstorming is about to begin (pre-brainstorm recon), OR has produced a spec, OR when superpowers:writing-plans has produced a plan, OR when about to invoke superpowers:subagent-driven-development or superpowers:executing-plans. Sidekick that intercepts these four Superpowers transitions — runs…
backend-launcher
Use when Compound V's dispatcher needs to run one file-scoped job on a chosen backend (Claude subagent, headless Codex worker, headless Antigravity worker, headless Cursor worker, headless Devin worker, or headless opencode worker) and get back a canonical jobresult. The single jobspec → jobresult contract every…
subagent-driven-development
Use when executing implementation plans with independent tasks in the current session.
write-documentation
Use when writing or substantially rewriting human-facing prose: documentation, README, guides, blog posts, emails, Slack messages, PR descriptions, release notes, or any text a human will read. Not for code comments, commit messages, or agent-to-agent communication.
research-driven-development
Use when the user asks a question about a topic, requests research, or when understanding something is needed before planning. Triggers on "research this", "what is X", "how does Y work", "compare A vs B", "investigate", "deep dive", "look into".