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/derio-net/super-fr/fr-dispatchnpx skills add derio-net/super-fr --skill fr-dispatchgit clone --depth 1 https://github.com/derio-net/super-frWrote 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/derio-net/super-fr/fr-dispatch)<a href="https://agentmods.dev/skills/derio-net/super-fr/fr-dispatch"><img src="https://agentmods.dev/badge/skills/derio-net/super-fr/fr-dispatch.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 | $0.00054 | $0.01396 |
| Opus 5 | $0.00027 | $0.00698 |
| Sonnet 5 | $0.00011 | $0.00279 |
| Haiku 4.5 | $0.00005 | $0.00140 |
Grade A, and why
fr-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 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.
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 — 120 lines — stays where its author put it; the contents beside it link to each section on GitHub.
fr-dispatch
Wraps the fr apply CLI. The single command renders the plan, observes
GitHub state, diffs, and emits the mutations needed to bring GitHub in line
with the plan. Works for first-time creation, incremental updates, and
ongoing reconciliation — there's no separate "first dispatch" verb in v2.
v3: tracking vs queue
Plain fr apply is TRACKING-ONLY (attribute labels, no queue
lifecycle). Queueing is explicit: fr apply <dir> --to vk --yes
adds fr:ready + runner:vk, validates the runner against the
fr.runners registry, and enforces the reachability gate (remote
runners pull the repo; tracking-only applies never pay it). The runner
choice lives ON THE ISSUE as labels — never in plan files.
fr undispatch dequeues; per-phase mixing is legal.
Pre-flight (mandatory)
- Audit first, with the read-only verb:
fr status <plan-dir>— safely allowlistable, never mutates. Read the header line (created date + age, tick counts, dispatch state) and the per-phase table. A locally-complete plan shows "would refuse create"; if the plan is genuinely done, runfr archive <plan-dir>instead of dispatching. Spec rows Unreachable for plans that exist locally = stale refs —fr repair --yesnormalizes them (File cells are bare slugs as of the 2026-06-06 spec-path-repair design). - Never-dispatched plan? Search the target repo for evidence the
work already landed (the stoa incident: 0/59 steps ticked, but 15
merged PRs and the deliverable tree existed in the target repo).
Check merged PRs mentioning the plan/spec slug and the plan's
deliverable paths:
gh pr list --repo <target> --state merged --search "<slug>",gh api repos/<target>/contents/<path>. Evidence found → STOP and reconcile with the operator; do not dispatch. - The plan and its referenced spec MUST be merged to the default
branch before running
fr apply --yes. The CLI refuses with exit 2 otherwise, listing the unreachable paths. If you've just written the plan, open a PR for spec+plan and merge it before running this workflow. The dispatch + writeback is then a separate (small) PR — see step 5.
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 · 120 lines · 54 tokens per session scan A a49e412d8b5c
fr-dispatch is a skill published in the GitHub repository derio-net/super-fr (1 stars, last pushed 4d ago), licensed MIT. It adds 54 tokens to every session and 1,396 once invoked, about $0.0003 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
using-grove
Use when orchestrating a fleet of independent coding agents with Grove from OUTSIDE — isolated per-task workspaces (tmux plus git worktree, host or container) across model providers and harnesses. Triggers on: spinning up, steering, pausing, resuming or killing workspaces, grove create/fleet/show/message/tickets, the…
working-in-grove
Use when you are the coding agent running INSIDE a Grove workspace — a git worktree Grove created for one task, on the host or in a container. Triggers on: reporting or updating your task phase or progress, GROVEPHASEFILE or .grove/phase.json, grove phase, grovesetworkspacephase, naming this workspace or setting its…
configuring-grove
Use when a user wants to set up or change Grove's configuration, for a host/user or for a project. Covers the global user config, the committed project config, machine-local overrides, agents, init scripts, containers, tmux and peek tuning, the TUI theme, the daemon auth, notifications, and ticket providers (Gitea…
reinstalling-grove
Use when a user wants to reinstall, update, or upgrade Grove after pulling new code, or when they report seeing the OLD UI / stale behavior after an update ("I still see the old dashboard", "the redesign isn't showing", "I reinstalled but nothing changed"). Covers the editable uv-tool install model, the…
review
5-pass structured code review — correctness, security, performance, readability, consistency.
alive:system-upgrade
Upgrade ALIVE to the current version. Handles v1/v2/v3.x source states, multi-surface aware (alive-mcp / Hermes / Codex), retroactive version detection, partial-failure resume, dry-run previews, and rollback inspection.