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/memorysaver/dotfiles/herdr-cockpitnpx skills add memorysaver/dotfiles --skill herdr-cockpitgit clone --depth 1 https://github.com/memorysaver/dotfilesWrote 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/memorysaver/dotfiles/herdr-cockpit)<a href="https://agentmods.dev/skills/memorysaver/dotfiles/herdr-cockpit"><img src="https://agentmods.dev/badge/skills/memorysaver/dotfiles/herdr-cockpit.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 | $0.00036 | $0.03141 |
| Opus 5 | $0.00018 | $0.01571 |
| Sonnet 5 | $0.00007 | $0.00628 |
| Haiku 4.5 | $0.00004 | $0.00314 |
Grade A, and why
herdr-cockpit scanned grade A with 0 findings 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 today.
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.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 264 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Herdr Cockpit
This skill defines the operating model for the user's six-pane Herdr coding cockpit. It is guidance for the main agent after the human starts the layout; it is not a second Herdr launcher and it must never start a nested Herdr session. The main agent treats the cockpit as a context-management system: workflow is the unit of delegation, not the pane or model identity. Read references/workflow-routing.md when selecting a workflow or writing a helper prompt.
The human startup flow is:
outside Herdr: herdr
inside Herdr: choose a workspace and any tab, cd to the project, type hc
hc is the zsh entrypoint in config/zsh/cockpit.zsh. It uses the current
workspace, current tab, and current $PWD for the active project, then expands
a single-pane tab into this layout. The left column has two large controller
panes; the right column has four stacked worker/utility panes. Claude is always
launched from ~/Work/github/idea. Every named worker/Claude agent
receives a workspace-qualified live name, for example w1-idea-center:
┌──────────────────────┬──────────────────────┐
│ main / Codex │ lazygit / utility │
│ orchestrator │ lazygit │
│ ├──────────────────────┤
│ │ w1-worker-1 / Agy │
│ │ agy │
├──────────────────────┼──────────────────────┤
│ w1-idea-center / │ w1-worker-2 / Pi │
│ Claude │ │
│ claude │ pi │
│ ├──────────────────────┤
│ │ w1-worker-3 / Pi │
│ │ pi │
└──────────────────────┴──────────────────────┘
The w1 prefix above is illustrative. At runtime hc uses the current
HERDR_WORKSPACE_ID as a lowercase namespace, so wC becomes wc and a
second workspace gets a separate name such as w2-worker-1 instead of
colliding with w1-worker-1. The role labels idea-center, worker-1,
worker-2, and worker-3 remain logical roles; use the workspace-qualified
live name for Herdr commands.
It is idempotent for the expected six-pane layout and fails closed when the
current tab already contains an unrelated multi-pane layout. Existing four- and
five-pane layouts are not upgraded automatically because doing so would require
stopping or moving running agents. Open a new single-pane tab for the new
layout. Do not run bare
herdr from a managed pane: Herdr's nested-launch guard is intentional. For
control calls, require HERDR_ENV=1 and use the existing Herdr CLI/socket API.
What ships with it
2 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.
- today Changed 4b572613dca2
- 4d ago First seen · 264 lines · 36 tokens per session scan A a34eea0e5dfc
herdr-cockpit is a skill published in the GitHub repository memorysaver/dotfiles (7 stars, last pushed yesterday), licensed MIT. It adds 36 tokens to every session and 3,141 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
brainstorming
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
auto-perf-optimize
Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.
chat-perf
Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…