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.
git clone --depth 1 https://github.com/Inakitajes/convoyWrote 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/inakitajes/convoy/pipeline)<a href="https://agentmods.dev/commands/inakitajes/convoy/pipeline"><img src="https://agentmods.dev/badge/commands/inakitajes/convoy/pipeline/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/inakitajes/convoy/pipeline"><img src="https://agentmods.dev/badge/commands/inakitajes/convoy/pipeline.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 | $0.00000 | $0.00460 |
| Opus 5.5 | $0.00000 | $0.00184 |
| Sonnet 5.5 | $0.00000 | $0.00092 |
| Haiku 4.5 | $0.00000 | $0.00046 |
Grade A, and why
pipeline 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.
What it actually says
Run the Convoy {{pipeline}} pipeline from this session, headless: {{summary}}
Request: $ARGUMENTS
Follow the convoy skill for every step (load it now if it isn't loaded; convoy skill show prints it). This command only fixes the pipeline to {{pipeline}}, launched as convoy -p {{pipeline}}; everything else works as the skill says.
- Inspect. In the repository this session works in, run
convoy pipelines show {{pipeline}}. A project pipeline of the same name replaces the built-in, so describe what will actually run. Its first line saysread-onlyorwrites code; that, not the name, sets the permission mode below. - Choose the contract. If the repository has active OpenSpec changes (the directories under
openspec/changes/other thanarchive/), follow "Choose the contract" in the skill: a change id named in the request becomes--change <id>(repeatable, in that order); otherwise list the active changes, say which one fits (the one named like the current branch, or the only one), and ask the user whether to run against it, against others, or without one (--manual). Never pick a change or fall back to--manualwithout asking. Without OpenSpec, pass--manual. - Prompt. {{prompt}}
- Plan.
convoy -p {{pipeline}} <--change <id> … | --manual> [--prompt-file <file>] <--yolo | --smart> --plan < /dev/null, then summarize the plan for the user. {{permissions}} - Launch. {{launch}} Launch the same command with
--detachin place of--plan(never without it) and keep the run id. - Follow it through. Follow the run in the background as the skill's section 6 describes, so this session stays free: tell the user the run id and roughly how long it takes, then check back at the cadence the run calls for. Relay anything it asks and report the results, as sections 7 and 8 describe.
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 b35ed13b9b95
- 5d ago First seen · 13 lines · 0 tokens per session scan A 2803892ceb38
pipeline is a command published in the GitHub repository Inakitajes/convoy (116 stars, last pushed 4d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 460 tokens. 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 2026-10-20.
Other commands, from other repositories
template
Manage issue templates for streamlined issue creation.
fest-show
Show festival progression (in-progress tasks, roadmap, and dependency view).
add-note
Add an internal or external note to a ConnectWise PSA ticket.
dispatcher
Use when you want the orchestrator to pick the next repo to work on across your whole portfolio — it enumerates candidate repos below the confinement root, resolves free/busy from each repo's session.lock lease, ranks the FREE ones by backlog priority × staleness × readiness, recommends the single most worthwhile one…
sync-linear
Sync current work with Linear ticket status.
plc-project-status
Read .claude/skills/plc-project-status/SKILL.md and execute its official procedure. Target: $ARGUMENTS.