convoy-end

convoy-end is a skill for Codex from Deploy-Forward/convoy. It costs 53 tokens per session (440 once invoked), scanned A, original, MIT.

A Convoy task-completion skill that records a task's final heartbeat and can optionally push a clean branch to its existing upstream Git remote. A heartbeat is a record that the task is still being tracked; an upstream is the remote branch it normally syncs with.

In plain words
What is it for?
Use it to close a Convoy task, add a short summary, or explicitly finish by pushing the current clean branch.
Why use it?
It prevents a task from being marked as pushed when no push happened, and avoids changing Git state without explicit permission. It refuses unsafe cases such as a dirty worktree or detached branch.

Skill for Codex

Written for Codex: agents/openai.yaml present. Also seen: reads .claude/ paths; mentions Codex; $skill-name invocation.

Good fit Use it to close a Convoy task, add a short summary, or explicitly finish by pushing the current clean branch.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/deploy-forward/convoy/convoy-end
Install

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.

Any agent
npx skills add Deploy-Forward/convoy --skill convoy-end
Clone the repo
git clone --depth 1 https://github.com/Deploy-Forward/convoy

Made for: Codex.

Wrote 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.

agentmods badge for convoy-end

README.md
[![agentmods](https://agentmods.dev/badge/skills/deploy-forward/convoy/convoy-end/github.svg)](https://agentmods.dev/skills/deploy-forward/convoy/convoy-end)
Your own site
<a href="https://agentmods.dev/skills/deploy-forward/convoy/convoy-end"><img src="https://agentmods.dev/badge/skills/deploy-forward/convoy/convoy-end/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.

agentmods 80×15 button for convoy-end

Your own site · 80×15
<a href="https://agentmods.dev/skills/deploy-forward/convoy/convoy-end"><img src="https://agentmods.dev/badge/skills/deploy-forward/convoy/convoy-end.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 53 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 440 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00053 $0.00440
Opus 5 $0.00026 $0.00220
Sonnet 5 $0.00011 $0.00088
Haiku 4.5 $0.00005 $0.00044

Measured 12d ago against content hash 653b144150d3, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-17, from the pricing page.

Security

Grade A, and why

convoy-end 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 12d 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.

plugins/convoy/skills/convoy-end/SKILL.md · 39 lines

What it actually says

End a Convoy task

This skill is an explicit completion action. Never invoke it implicitly when the user merely says that a substep is done.

Run the portable CLI from the current worktree:

convoy end [--summary "one line"] [--push]
  • Preserve --push only when the user supplied it in this invocation.
  • Never add --push on the user's behalf and never turn an automatic heartbeat into push authorization.
  • Do not commit, stage, set an upstream, force-push, or select a different remote. convoy end --push permits exactly one plain git push after the command verifies a clean attached branch with an existing upstream.
  • Treat push_status: pushed as proof of push. A heartbeat row by itself is not proof that git changed remotely.
  • If identity is ambiguous, the worktree is dirty, HEAD is detached, or no upstream exists, report the refusal and leave git unchanged.

Codex's native invocation is $convoy-end --push; there is no supported arbitrary /end extension point. Claude receives a project command at .claude/commands/end.md, so /end --push is available there after the command is installed/reloaded.

The Codex and Claude Stop hooks use convoy end --hook. That automatic path records a turn-end heartbeat only, emits no transcript or vendor identifiers, and can never push.

Files

What ships with it

1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

Changes

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.

  1. 12d ago First seen · 39 lines · 53 tokens per session scan A 653b144150d3

Subscribe to this mod's changes

convoy-end is a skill published in the GitHub repository Deploy-Forward/convoy (0 stars, last pushed yesterday), licensed MIT. It adds 53 tokens to every session and 440 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 2026-09-05.