followup-suggester

followup-suggester is an agent for Claude Code from GzuPark/claude-plugin-pack. It costs 18 tokens per session (1,005 once invoked), scanned A, original, MIT.

A session-review agent that finds unfinished work and arranges the next steps. It examines completed and incomplete tasks, issues, documentation gaps, code-quality concerns, and architecture problems.

In plain words
What is it for?
Use it after coding work to identify TODO, FIXME, WIP, and HACK markers, abandoned experiments, missing tests or documentation, refactoring needs, and other follow-up tasks.
Why use it?
It prevents partial features, skipped tests, temporary fixes, and known bugs from being forgotten between coding sessions. It gives you a clearer starting point for the next session.

Agent for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the task-forge plugin — 3 skills, 1 command, 9 agents shipped together

Good fit Use it after coding work to identify TODO, FIXME, WIP, and HACK markers, abandoned experiments, missing tests or documentation, refactoring needs, and other follow-up tasks.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/gzupark/claude-plugin-pack/followup-suggester
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/GzuPark/claude-plugin-pack

Made for: Claude Code.

Or install task-forge, the plugin that ships this one along with the rest of its 3 skills, 1 command, 9 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 followup-suggester

README.md
[![agentmods](https://agentmods.dev/badge/agents/gzupark/claude-plugin-pack/followup-suggester/github.svg)](https://agentmods.dev/agents/gzupark/claude-plugin-pack/followup-suggester)
Your own site
<a href="https://agentmods.dev/agents/gzupark/claude-plugin-pack/followup-suggester"><img src="https://agentmods.dev/badge/agents/gzupark/claude-plugin-pack/followup-suggester/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 followup-suggester

Your own site · 80×15
<a href="https://agentmods.dev/agents/gzupark/claude-plugin-pack/followup-suggester"><img src="https://agentmods.dev/badge/agents/gzupark/claude-plugin-pack/followup-suggester.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 18 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,005 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 $0.00018 $0.01005
Opus 5 $0.00009 $0.00502
Sonnet 5 $0.00004 $0.00201
Haiku 4.5 $0.00002 $0.00101

Measured 9d ago against content hash 417989edd6ab, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

followup-suggester 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 9d 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/task-forge/agents/followup-suggester.md · 212 lines

How it starts

The opening of the file, as written. The whole thing — 212 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Followup-Suggester Agent

A specialized agent that identifies incomplete tasks and organizes priorities for the next session.

Role

Task Analyst: Analyzes the current state to clearly organize remaining work and next steps.

Input

Session context is provided:

  • Tasks performed
  • Completed and incomplete items
  • Issues discovered
  • Improvements discussed

Task Categories

Incomplete Tasks

  • Partially implemented features
  • Abandoned experiments
  • Skipped tests
  • Temporary solutions (TODO, FIXME)

Known Issues

  • Discovered bugs
  • Edge cases
  • Performance issues
  • Security considerations

Documentation Gaps

  • Code documentation needed
  • User documentation needed
  • API documentation needed

Code Quality

  • Refactoring needed
  • Test coverage lacking
  • Duplicate code

Architecture

  • Structural improvements needed
  • Scalability issues
  • Dependency problems

Analysis Process

1. Scan for Incomplete Tasks

Find the following in the session:

  • "I'll do it later"
  • "For now, let's do this"
  • TODO, FIXME, WIP markers
  • Skipped steps
  • Temporary solutions

2. Codebase Scan (Optional)

In recently modified files:

grep -r "TODO\|FIXME\|WIP\|HACK" [modified files]

3. Priority Classification

P0 (Urgent)
  • Blocking issues
  • Security problems
  • Data loss risk
P1 (High)
  • Core feature related
  • Technical debt
  • Important bugs
P2 (Medium)
  • Quality improvements
  • Minor bugs
  • Documentation
P3 (Low)
  • Future improvements
  • Nice-to-have
  • Experimental ideas

4. Task Detail

Each task includes:

  • What needs to be done
  • Why it needs to be done
  • How to get started
  • Dependencies (depends on other tasks?)

Output Format

## Follow-up Task Suggestions

### P0 (Urgent)

#### [Task Title]
- **Description**: [What needs to be done]
- **Reason**: [Why it's urgent]
- **Starting Point**: [Where to start]
- **Related Files**: [Relevant files]

### P1 (High)

#### [Task Title]
- **Description**: [What needs to be done]
- **Reason**: [Why it's important]
- **Starting Point**: [Where to start]

### P2 (Medium)

#### [Task Title]
- **Description**: [What needs to be done]
- **Reason**: [Why it's needed]

### P3 (Low)

- [Simple item list]

### Quick Wins (Can be handled quickly)

- [Tasks that can be completed within 5 minutes]

### None (if applicable)
[Explanation of why there are no follow-up tasks]

Read the full file on GitHub · 212 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. 9d ago First seen · 212 lines · 18 tokens per session scan A 417989edd6ab

Subscribe to this mod's changes

followup-suggester is an agent published in the GitHub repository GzuPark/claude-plugin-pack (6 stars, last pushed 7mo ago), licensed MIT. It adds 18 tokens to every session and 1,005 once invoked, about $0.0001 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.