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 skills add memorysaver/dotfiles --skill herdr-dispatchgit 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-dispatch)<a href="https://agentmods.dev/skills/memorysaver/dotfiles/herdr-dispatch"><img src="https://agentmods.dev/badge/skills/memorysaver/dotfiles/herdr-dispatch/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/memorysaver/dotfiles/herdr-dispatch"><img src="https://agentmods.dev/badge/skills/memorysaver/dotfiles/herdr-dispatch.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00034 | $0.02268 |
| Opus 5.5 | $0.00014 | $0.00907 |
| Sonnet 5.5 | $0.00007 | $0.00454 |
| Haiku 4.5 | $0.00003 | $0.00227 |
Grade A, and why
herdr-dispatch 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 10d 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.
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 — 171 lines — stays where its author put it; the contents beside it link to each section on GitHub.
herdr-dispatch
Load and select the destination
For managed role startup, registered project dispatch, Dagu delivery, or a supplied orchestrator callback, run
herdr-dispatch --skills and read its complete stdout as this skill. This exports the embedded
SKILL.md; it does not install a global skill, start services, or submit work. A $herdr-dispatch
shortcut is available only if a skill has separately been registered with the agent product.
Direct project development does not need this dispatch workflow.
Use the destination computer's CLI/config. HERDR_COMPUTER_HOME defaults to ~/Work when unset;
explicit empty or relative values fail. --config selects YAML, defaulting to
<Computer home>/projects.yaml. Relative project paths resolve from Computer home, including
when YAML is symlinked from private idea. Help, version and --skills need no config/server.
herdr-dispatch --skills
herdr-dispatch --help
herdr-dispatch event --help
herdr-dispatch paths
herdr-dispatch check
herdr-dispatch check --live
herdr-dispatch projects list
check validates config/locations; check --live also reads configured role identity without
starting agents. projects list exposes project/task IDs, scope, input_env names and has_verifier.
Inspect the selected YAML task for argv and required inputs: ${env:NAME} references require a
nonempty input; unreferenced allowlisted inputs may be absent. YAML is the registry, not another
CLI-supplied executable or free-form prompt. Do not infer projects from available workspaces.
For a custom root/config, pin both on each command; a split shell need not inherit them:
env HERDR_COMPUTER_HOME=/srv/computer "$HOME/.local/bin/herdr-dispatch" \
--config /srv/computer/projects.yaml projects list
Computer uses computer-orchestrator at Computer home. Project uses
project-orchestrator-<key> at its registered Git root. CLI/broker bind name, kind, canonical cwd,
ownership and native terminal generation. Dispatch by project ID; labels, pane order and focus
cannot select the receiver. Role presence does not grant publication or project permissions.
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.
- 10d ago First seen · 171 lines · 34 tokens per session scan A 2df6a19bc28b
herdr-dispatch is a skill published in the GitHub repository memorysaver/dotfiles (7 stars, last pushed 4d ago), licensed MIT. It adds 34 tokens to every session and 2,268 once invoked, about $0.0001 per session on Opus 5.5. 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 2026-10-03.
Other skills, from other repositories
story-readiness
Is a story implementation-ready? Checks clear acceptance criteria, open questions, ADR refs. READY/NEEDS WORK/BLOCKED/NOT ASSESSED.
recipe-create-meet-space
Create a Google Meet meeting space and share the join link.
workthreads
SpecStory Workthreads - a weekly work-thread rollup across a team's repos from SpecStory coding histories (any agent - Claude Code, Codex, Cursor, Gemini, and more). It groups the window's sessions into threads of work per project and labels each new / open / recently closed, so a lead sees what shipped, what is still…
atmos-config
Atmos root configuration: atmos.yaml discovery, precedence, deep merging, basepath, imports, minimal bootstrap, and routing to narrower Atmos skills.
remove
Remove a deployed framework or addon from the current workspace.
handle-linkedin-connection-request-signal
Use this skill when someone sends a team member an inbound LinkedIn connection request. An inbound request is a deliberate, ACTIVE first-party intent signal — meaningfully stronger than a passive profile view — and it deserves different scoring rules. The skill resolves and enriches the requester, gates them through…