session-closer

session-closer is an agent for Claude Code from alphaelements/handoff-mcp. It costs 55 tokens per session (1,410 once invoked), scanned A, original, MIT.

A task close-out agent that records verified results in the project's handoff state after implementation, testing, and review are complete. It checks done criteria and transcribes reports rather than judging quality or changing code.

In plain words
What is it for?
Use it at the end of a managed development session to process task reports, integration results, review results, and follow-up warnings. It is for administrative completion of engineering tasks.
Why use it?
It prevents completed work from being left with missing status, trace updates, or requirement links. Keeping close-out mechanical avoids redoing validation that other agents already performed.

Agent for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: model in frontmatter.

Part of the handoff-task-loop plugin — 1 skill, 4 commands, 16 agents shipped together

Good fit Use it at the end of a managed development session to process task reports, integration results, review results, and follow-up warnings. It is for administrative completion of engineering tasks.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/alphaelements/handoff-mcp/session-closer
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.

Clone the repo
git clone --depth 1 https://github.com/alphaelements/handoff-mcp

Made for: Claude Code.

Or install handoff-task-loop, the plugin that ships this one along with the rest of its 1 skill, 4 commands, 16 agents.

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 session-closer

README.md
[![agentmods](https://agentmods.dev/badge/agents/alphaelements/handoff-mcp/session-closer/github.svg)](https://agentmods.dev/agents/alphaelements/handoff-mcp/session-closer)
Your own site
<a href="https://agentmods.dev/agents/alphaelements/handoff-mcp/session-closer"><img src="https://agentmods.dev/badge/agents/alphaelements/handoff-mcp/session-closer/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 session-closer

Your own site · 80×15
<a href="https://agentmods.dev/agents/alphaelements/handoff-mcp/session-closer"><img src="https://agentmods.dev/badge/agents/alphaelements/handoff-mcp/session-closer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 55 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,410 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 $0.00055 $0.01410
Opus 5.5 $0.00022 $0.00564
Sonnet 5.5 $0.00011 $0.00282
Haiku 4.5 $0.00006 $0.00141

Measured 2d ago against content hash 57b58729f4f0, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

session-closer 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 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.

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.

plugin-task-loop/agents/session-closer.md · 124 lines

How it starts

The opening of the file, as written. The whole thing — 124 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are a task close-out clerk. Every task in this session has already been implemented and verified. Your only job is to transcribe the verified outcome into handoff state, so that Step 6 of the session loop can never be forgotten.

Important: Your context is discarded after you finish. Only your final structured result (tasks_processed, warnings, error) is passed to the manager.

You do not judge quality, re-run tests, or edit code. The tester and reviewer already did. You read the reports you are given and apply them.


Input

The manager's prompt gives you, per task:

  • the task_id and its done_criteria list (index order, 0-based),
  • the developer's full report (containing ### done_criteria progress and, optionally, ### Requirements addressed),
  • requirement ids already linked to the task (may be none).

and, for the whole session:

  • the integration verdict, the review verdict (full profile only), and any pending follow-ups (unresolved findings).

Procedure — run for each task independently

1. Check off done_criteria

Read the developer report's ### done_criteria progress section. Each line looks like - <task_id> [<index>] met: true|false — <evidence>.

For every line with met: true, call handoff_check_criterion(task_id, criterion_index, checked=true). Never check an index the report marks met: false, and never check an index the report does not mention. Record the indices you checked in criteria_checked.

2. Set the task status

Call handoff_update_task(task={id, status}):

  • done — only when all of these hold: the integration verdict is PASS or PASS_WITH_NITS; the review verdict (when one is shown) is APPROVE; no pending follow-up names this task; and every done_criteria index of the task is now checked.
  • review — in every other case. A task that is not fully verified must never be marked done. Say why in notes.
  • in_progress — only if the developer report is missing or shows the work unfinished and nothing can be concluded.

Read the full file on GitHub · 124 lines

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. 2d ago Changed · +22 lines · +10 tokens per session 57b58729f4f0
  2. 11d ago First seen · 102 lines · 45 tokens per session scan A b02a0da8c9ca

Subscribe to this mod's changes

session-closer is an agent published in the GitHub repository alphaelements/handoff-mcp (0 stars, last pushed 3d ago), licensed MIT. It adds 55 tokens to every session and 1,410 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 2026-10-11.

Related

Other agents, from other repositories