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 commands/rhan1/crewline/dispatch-geminigit clone --depth 1 https://github.com/rhan1/crewlineWhat 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 | $0.00014 | $0.00843 |
| Opus 5 | $0.00007 | $0.00421 |
| Sonnet 5 | $0.00003 | $0.00169 |
| Haiku 4.5 | $0.00001 | $0.00084 |
Grade A, and why
dispatch-gemini scanned grade A 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 2d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
- UI component → dev server + browser/curl verification How it starts
The opening of the file, as written. The whole thing — 57 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Run the Gemini dispatch workflow for the task below, even if the auto-dispatch heuristics wouldn't have fired. Do NOT shortcut the spec-writing or smoke-test steps.
When to prefer Gemini over Codex
Gemini is the right executor when ANY of these apply:
- Long-context — input > ~150k tokens (whole repo dump, large logs, big CSV/JSON, long PDFs). Codex's ~200k window can't fit; Gemini's 2M can.
- Multi-modal — input includes images, PDFs, screenshots, or video. Codex CLI is text-only.
- Parallel batch — 5+ similar sub-tasks to fire concurrently. Codex Plus caps at ~30 msg / 3h; Gemini Pro has more headroom.
- Codex rate-limited — existing fallback behavior.
~/.claude/codex-last.jsonshows a recent rate-limit failure.
For tight pattern-following on a single file (mirror this Vercel serverless style exactly), prefer Codex.
Task
$ARGUMENTS
Workflow
-
Plan. Read the referenced files, pattern sources, and data endpoints yourself. If anything essential is missing (target path, output shape, data-source URL, attachment paths), ask before writing the spec — thin specs produce thin code.
-
Write the spec to
/tmp/gemini-dispatch-<short-task-name>-<unix-ts>.{txt,json}.Text spec (most cases) —
.txtfile containing the full prompt. Cover:- Exact target file path (if writing code)
- 2–3 pattern files to mirror (style + error-handling conventions)
- Data sources and expected fields
- Output shape (JSON for APIs, component signature for UI, markdown for analyses)
- Explicit "do not do" constraints — no npm/git/vercel/deploy, no tests/READMEs, no modifying other files, no network validation
Multi-modal spec —
.jsonmanifest:{ "prompt": "Compare these two dashboard screenshots and list every visual difference you see.", "attachments": ["/absolute/path/to/before.png", "/absolute/path/to/after.png"] }The wrapper appends
@/path/...references inline so Gemini reads them as part of the prompt context.
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.
- 2d ago First seen · 57 lines · 14 tokens per session scan A 5389b0934773
dispatch-gemini is a command published in the GitHub repository rhan1/crewline (2 stars, last pushed 8d ago), licensed MIT. It adds 14 tokens to every session and 843 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other commands, from other repositories
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
constitution
Create or update the project constitution from interactive or provided principle inputs.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.