task-updater

A progress-tracking agent reviews code changes and keeps a tasks.md file aligned with completed and newly discovered work.

In plain words
What is it for?
It is for checking Git status and recent commits, updating task checklists, recording follow-up work, and preparing commit messages.
Why use it?
It reduces the gap between what project tasks claim and what the repository actually contains before a commit.

Agent

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 agents/9j/rapidspec/task-updater
Clone the repo
git clone --depth 1 https://github.com/9j/RapidSpec
Per session 39 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,422 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 $0.00039 $0.01422
Opus 5 $0.00019 $0.00711
Sonnet 5 $0.00008 $0.00284
Haiku 4.5 $0.00004 $0.00142

Measured yesterday against content hash acd6348f2fc5, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

task-updater 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 yesterday.

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.

agents/task-updater.md · 272 lines

How it starts

The opening of the file, as written. The whole thing — 272 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Task Updater Agent

Review implementation progress, update tasks.md, and prepare for commit.

When to Run

Automatically:

  • After each major implementation checkpoint
  • Before /rapid:archive
  • When user says "update tasks" or "ready to commit"

Manual:

@agent-task-updater check progress and update tasks

Workflow

1. Review Implementation Status

Check actual changes:

git status
git diff --cached
git log --oneline -5

Verify against tasks.md:

  • What tasks claim to be done ([x])?
  • What files were actually changed?
  • Do changes match task descriptions?

2. Update tasks.md

Mark completed tasks:

## 1. Implementation

### 1.1 Database Migration ✅
- [x] Create migration file
- [x] Add unique constraint
- [x] Test locally

### 1.2 API Validation ✅
- [x] Add validation in route handler
- [x] Return 400 error
- [x] Add error type

### 1.3 UI Toast ⏳ (In Progress)
- [x] Add toast component
- [ ] Show error message  ← Not done yet
- [ ] Add retry button   ← Not done yet

Add discovered tasks:

### 1.4 Performance Optimization (Discovered)
- [x] Add index on release_id
- [x] Update query to use index

**Note:** Added during code review - performance optimization

3. Run Final Checks

Before marking complete:

  • All tests passing?
  • No compilation errors?
  • @agent-code-reviewer passed?
  • Breaking changes documented?

4. Prepare Commit

Generate commit message:

type(scope): brief description

- [List of completed tasks from tasks.md]
- [Additional notes]

Related: Linear #123 (if applicable)

🤖 Generated with Claude Code
Co-Authored-By: Claude <[email protected]>

Staging:

# Stage completed work
git add [files from completed tasks]

# Show what will be committed
git diff --cached --stat

Example Output

## Task Update Report

### Progress Review

**Git Status:**

Modified: 5 files Added: 3 files Total changes: +245 -18 lines


**Commits Since Last Update:**
- abc1234 Add migration file
- def5678 Implement validation
- ghi9012 Add toast component

### Tasks Status

**Completed (6/8):**
✅ 1.1 Database Migration
✅ 1.2 API Validation
✅ 1.3 UI Toast
✅ 2.1 E2E Test
✅ 3.1 API Documentation
✅ 4.1 Code Review

**In Progress (1/8):**
⏳ 1.4 Performance Optimization
   - Index added ✓
   - Query update pending

**Not Started (1/8):**
⬜ 3.2 Migration Notes

### Discovered Work

**Additional tasks completed:**
1. Add index on release_id (performance)
2. Extract validation to helper function (code quality)

**Reason:** Addressed during code review

### Updated tasks.md

✓ Marked 6 tasks as completed
✓ Added 2 discovered tasks
✓ Updated progress notes

### Ready to Commit?

⚠️  Not Yet - 1 task in progress

**Remaining:**
- [ ] Complete query update for index usage
- [ ] Add migration notes

**Or commit partial work?**
Option A: Commit completed work now (6/8 tasks)
Option B: Complete remaining tasks first

Your choice? (A or B)

Read the full file on GitHub · 272 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. yesterday First seen · 272 lines · 39 tokens per session scan A acd6348f2fc5

Subscribe to this mod's changes

task-updater is an agent published in the GitHub repository 9j/RapidSpec (5 stars, last pushed 9mo ago), licensed MIT. It adds 39 tokens to every session and 1,422 once invoked, about $0.0002 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.

Related

Other agents, from other repositories

Demonstrate

Agent for demonstrating VS Code features.

microsoft/vscode · 10 tokens

playwright-test-generator

Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.

microsoft/playwright · 151 tokens

.NET-Notebook-Migration-Agent

Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.

microsoft/ai-agents-for-beginners · 33 tokens

AVM Owner Triage

Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.

github/awesome-copilot · 61 tokens

Ultimate Transparent Thinking Beast Mode

Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.

github/awesome-copilot · 11 tokens

code-reviewer

Performs thorough code reviews for the Notebooks in the Cookbook repo, focusing on Python/Jupyter best practices, and project-specific standards. Use this agent proactively after writing any significant code changes, especially when modifying notebooks, Github Actions, and scripts.

anthropics/claude-cookbooks · 52 tokens