progress-update

A command that collects information about an active sprint, a short planned period of development work, and writes a progress report.

In plain words
What is it for?
Use it to report commits, changed files, code differences, test results, completed work, and remaining sprint tasks.
Why use it?
It gathers delivery and testing details in one place instead of requiring a manual status summary.

Command for Claude Code

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/vishnu2kmohan/mcp-server-langgraph/progress-update
Clone the repo
git clone --depth 1 https://github.com/vishnu2kmohan/mcp-server-langgraph

Made for: Claude Code.

Per session 7 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,153 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 $0.00007 $0.02153
Opus 5 $0.00003 $0.01077
Sonnet 5 $0.00001 $0.00431
Haiku 4.5 $0.00001 $0.00215

Measured 2d ago against content hash 252c97661503, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

progress-update 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.

.claude/commands/progress-update.md · 371 lines

How it starts

The opening of the file, as written. The whole thing — 371 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Generate Sprint Progress Update

Usage: /progress-update or /progress-update <sprint-date>

Purpose: Generate comprehensive progress update for active sprint


📊 Progress Update Generation

Step 1: Identify Active Sprint

Find the most recent sprint tracking document:

# Find latest sprint progress file
ls -t docs-internal/SPRINT_PROGRESS_*.md | head -1

# Or use provided date
SPRINT_FILE=docs-internal/SPRINT_PROGRESS_$ARGUMENTS.md

If no sprint file found:

  • Check if sprint was started with /start-sprint
  • Look for sprint plan: docs-internal/SPRINT_PLAN_*.md
  • Ask user which sprint to update

Step 2: Collect Sprint Metrics

Gather current metrics from repository:

Code Metrics:

# Recent commits since sprint start
git log --oneline --since="$(date -d 'sprint start date' +%Y-%m-%d)" | wc -l

# Files modified
git diff --name-only <sprint-start-commit>..HEAD | wc -l

# Lines changed
git diff --stat <sprint-start-commit>..HEAD

Test Metrics:

# Run tests and capture results
pytest --collect-only -q | tail -1  # Total test count

# Run tests with verbose output
pytest -v --tb=short 2>&1 | tee /tmp/test_results.txt

# Parse results
grep -E "(passed|failed|skipped)" /tmp/test_results.txt | tail -1

Coverage Metrics:

# Generate coverage report
pytest --cov=src --cov-report=term-missing 2>&1 | grep "TOTAL"

TODO Status:

# Count remaining TODOs in source code
grep -r "TODO" src/ | wc -l

# Compare with catalog
cat docs-internal/TODO_CATALOG.md | grep -E "^(###|####)" | wc -l

Step 3: Analyze TodoWrite Status

Check current todo list status:

From TodoWrite tool:

  • Total items created
  • Completed count
  • In progress count
  • Blocked count
  • Pending count

Calculate:

  • Completion rate: (completed / total) * 100%
  • Velocity: completed items / days elapsed

Step 4: Check Git Activity

Review git activity since sprint start:

# Commits per day
git log --since="sprint start" --pretty=format:"%ad" --date=short | sort | uniq -c

# Commit types (feat, fix, docs, test, refactor)
git log --oneline --since="sprint start" | grep -oE "^[a-z0-9]+ (feat|fix|docs|test|refactor|chore)" | cut -d' ' -f2 | sort | uniq -c

# Files most modified
git log --since="sprint start" --name-only --pretty=format: | sort | uniq -c | sort -rn | head -10

Read the full file on GitHub · 371 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 First seen · 371 lines · 7 tokens per session scan A 252c97661503

Subscribe to this mod's changes

progress-update is a command published in the GitHub repository vishnu2kmohan/mcp-server-langgraph (4 stars, last pushed 9d ago), licensed MIT. It adds 7 tokens to every session and 2,153 once invoked, about $0.0000 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 2026-08-31.