summary

summary is a command for Claude Code from stolostron/jira-mcp-server. It costs 0 tokens per session (642 once invoked), scanned A, original, Apache-2.0.

A command that produces a formal summary of the work completed during an AI coding session.

In plain words
What is it for?
Use it to summarize diffs, recent commits, the current branch, referenced Jira work, decisions, and tools used.
Why use it?
It gathers repository changes and session context so the final handoff records what changed, why, and what remains relevant.

Command for Claude Code

Written for Claude Code: installed under .claude/. Also seen: names the AskUserQuestion tool.

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.

agentmods
npx agentmods add commands/stolostron/jira-mcp-server/summary
Clone the repo
git clone --depth 1 https://github.com/stolostron/jira-mcp-server

Made for: Claude Code.

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 summary

README.md
[![agentmods](https://agentmods.dev/badge/commands/stolostron/jira-mcp-server/summary.svg)](https://agentmods.dev/commands/stolostron/jira-mcp-server/summary)
Your own site
<a href="https://agentmods.dev/commands/stolostron/jira-mcp-server/summary"><img src="https://agentmods.dev/badge/commands/stolostron/jira-mcp-server/summary.svg" alt="Measured on agentmods" height="20"></a>
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 642 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00000 $0.00642
Opus 5 $0.00000 $0.00321
Sonnet 5 $0.00000 $0.00128
Haiku 4.5 $0.00000 $0.00064

Measured 5d ago against content hash f3e611e4a7cf, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

summary 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 5d 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.

.claude/commands/summary.md · 77 lines

How it starts

The opening of the file, as written. The whole thing — 77 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Work Summary Command

Generate a formal summary of work performed in the current AI session, based on repository changes and conversation context.

Instructions

Step 1: Gather Repository Changes

Run the following git commands in parallel using Bash:

  1. git diff --stat — Get a summary of changed files
  2. git diff — Get the full diff of all changes
  3. git log --oneline -5 — Get recent commits for context
  4. git branch --show-current — Get the current branch name

Step 2: Gather Session Context

Review the full conversation history to identify:

  • Which Jira issues were referenced, created, updated, transitioned, or commented on
  • What tasks were performed (code changes, bug fixes, new features, refactoring, etc.)
  • Any decisions made or trade-offs discussed
  • Any tools or MCP servers used

Step 3: Generate the Formal Work Summary

Present a Formal Work Summary in this format:

## Work Summary — <current date>

**Branch:** <branch name>
**Session scope:** <1-line description of overall work>

### Changes
- <bullet list of meaningful changes, grouped by area/file>

### Notes
- <any relevant decisions, trade-offs, or follow-ups>

Step 4: Generate Git Commit Message Version

Generate a plain-text version suitable for a git commit message:

  • No markdown formatting, no special characters (no backticks, asterisks, pipes, or angle brackets)
  • First line is a concise summary under 72 characters
  • Followed by a blank line and bullet points describing the changes
  • Use only ASCII characters, hyphens, and standard punctuation
  • This message will be used directly in CLI commands (e.g., git commit -m), so avoid characters that interfere with shell interpretation (quotes, backticks, dollar signs, parentheses, etc.)

Present it in a code block labeled Git Commit Message.

Step 5: Offer to Add Summary to Jira

Use AskUserQuestion to ask the user:

"Would you like to add this summary as a comment to a Jira issue? If so, provide the issue key (e.g., ACM-12345)."

Read the full file on GitHub · 77 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. 5d ago First seen · 77 lines · 0 tokens per session scan A f3e611e4a7cf

Subscribe to this mod's changes

summary is a command published in the GitHub repository stolostron/jira-mcp-server (2 stars, last pushed 5d ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 642 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 2026-08-31.