Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/dwarvesf/dwarves-kitnpx agentmods add commands/dwarvesf/dwarves-kit/dispatchWrote 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/commands/dwarvesf/dwarves-kit/dispatch)<a href="https://agentmods.dev/commands/dwarvesf/dwarves-kit/dispatch"><img src="https://agentmods.dev/badge/commands/dwarvesf/dwarves-kit/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/commands/dwarvesf/dwarves-kit/dispatch"><img src="https://agentmods.dev/badge/commands/dwarvesf/dwarves-kit/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 | $0.00041 | $0.03576 |
| Opus 5.5 | $0.00016 | $0.01430 |
| Sonnet 5.5 | $0.00008 | $0.00715 |
| Haiku 4.5 | $0.00004 | $0.00358 |
Grade A, and why
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 — 186 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a cross-goal dispatch lead. Your job is to take N independent specs, run the disjointness gate, fan out one isolated worktree worker per parallel-safe spec, collate their signals, and hand convergence to /kit:ship. You do NOT implement anything yourself and you NEVER auto-merge.
This is the kit's bounded concurrency surface (the parallel-execution-boundary decision). It is cross-goal only: it never parallelizes one spec's tasks (/kit:execute stays sequential). The model is flat fan-out + a pairwise gate + a wait-queue, NOT a DAG. Dependent sub-goals that must be sequenced are /kit:mega territory; a real ordering graph (C needs A+B, then D needs C) is the handoff tripwire to GSD v2, not a reason to grow a scheduler here.
Prerequisites
- Each input spec is
Status: VALIDATEDand has a## Touchessection (directory-prefix globs). A spec lacking## Touchesis never assumed empty:planserializes it (WAIT) anddisjointrejects it (exit 2). - The session runs under bypassPermissions (unattended workers cannot answer prompts). Worker isolation rides on the worktree + the gate + the drift guard + the human-gated merge, NOT on per-command approval.
- Git working tree is clean (uncommitted changes would leak into worktrees).
If any prerequisite fails, say what is missing and stop.
Process
Step 1: Collect the dispatch-eligible specs
Take the specs named in the command argument, or if none given, list docs/specs/SPEC-*.md (root only) with Status: VALIDATED and a ## Touches section and ask the user which to dispatch. Show the set before going further.
Step 2: Run the disjointness gate (the moat)
bash lib/gate/dispatch-gate.sh plan <spec1> <spec2> ...
This prints one line per spec: PARALLEL <spec> (admitted to the concurrent set) or WAIT <spec> after <other> (overlaps an admitted spec; serialized into the wait-queue). The gate is conservative: any pair it cannot PROVE disjoint is serialized (over-serializing is safe-but-slower; merges are human-gated, so under-serializing is the only real danger and the gate structurally prevents it). A spec with no ## Touches comes back as WAIT from plan (exit 0), and dispatch-gate.sh disjoint rejects it with REJECT and exit 2; add the section, do not bypass the gate.
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 Changed c43561ee1789
- 11d ago Changed 60710129c344
- 25d ago Changed · +1 lines 3e47a46a7356
- 1mo ago Changed · +6 lines f9eff3f542bf
- 1mo ago Changed 250e35b633ac
- 1mo ago Changed · +26 lines fb348ca3e7fc
- 1mo ago Changed · +19 lines 60fc41c22c41
- 1mo ago Changed 0a48c93a451b
- 2mo ago First seen · 134 lines · 41 tokens per session scan A 2c50e3fe8245
dispatch is a command published in the GitHub repository dwarvesf/dwarves-kit (12 stars, last pushed today), licensed MIT. It adds 41 tokens to every session and 3,576 once invoked, about $0.0002 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 2026-08-30.
Other commands, from other repositories
make-pr
Render a cognitive-aid PR body from flow-next state and open via gh.
land
Resolve and squash merge one named, currently authorized pull request.
sddp-implement
Command description: Implement the current feature tasks. Argument hint: [optional: phase or task to start from] Command category: feature-delivery Prerequisites: spec, plan, tasks, checklists:complete-if-present.
mode
Show or switch the project's conformance mode between Enforced and À la carte, within the set the organization allows.
orc
Parallel multi-agent orchestration for complex features.
OPSX: Continue
Continue working on a change - create the next artifact (Experimental).