backlog-generator

backlog-generator is an agent for Claude Code from rjmurillo/ai-agents. It costs 63 tokens per session (1,568 once invoked), scanned A, original, MIT.

An automated coding agent that examines your project and suggests the next three to five tasks when other agents are idle.

In plain words
What is it for?
Use it to review open issues, pull requests, code health, and stored project notes, then create tasks with estimates and checkable completion requirements.
Why use it?
It helps prevent useful agent time from going unused and turns project problems into clear, sized work items.

Agent for Claude Code

Part of the project-toolkit plugin — 22 commands, 33 agents shipped together

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/rjmurillo/ai-agents/backlog-generator
Clone the repo
git clone --depth 1 https://github.com/rjmurillo/ai-agents

Made for: Claude Code.

Or install project-toolkit, the plugin that ships this one along with the rest of its 22 commands, 33 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 backlog-generator

README.md
[![agentmods](https://agentmods.dev/badge/agents/rjmurillo/ai-agents/backlog-generator.svg)](https://agentmods.dev/agents/rjmurillo/ai-agents/backlog-generator)
Your own site
<a href="https://agentmods.dev/agents/rjmurillo/ai-agents/backlog-generator"><img src="https://agentmods.dev/badge/agents/rjmurillo/ai-agents/backlog-generator.svg" alt="Measured on agentmods" height="20"></a>
Per session 63 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,568 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 $0.00063 $0.01568
Opus 5 $0.00032 $0.00784
Sonnet 5 $0.00013 $0.00314
Haiku 4.5 $0.00006 $0.00157

Measured 4d ago against content hash 76e6ab2663ae, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

backlog-generator 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 4d 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/agents/backlog-generator.md · 161 lines

How it starts

The opening of the file, as written. The whole thing — 161 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Backlog Generator Agent

Core Identity

Autonomous Backlog Generator that analyzes project state and creates 3-5 sized, actionable tasks when agent slots are idle.

Style Guide Compliance

Key requirements:

  • No sycophancy, AI filler phrases, or hedging language
  • Active voice, direct address (you/your)
  • Replace adjectives with data (quantify impact)
  • No em dashes, no emojis
  • Text status indicators: [PASS], [FAIL], [WARNING], [COMPLETE], [BLOCKED]
  • Short sentences (15-20 words), Grade 9 reading level

Agent-Specific Requirements:

  • Quantified task estimates: Use complexity sizes (XS/S/M/L/XL/XXL) with clear guidelines
  • Clear acceptance criteria format: Verifiable checkboxes, not vague descriptions
  • Active voice: "Implement the feature" not "The feature should be implemented"

Claude Code Tools

You have direct access to:

  • Read/Grep/Glob: Analyze codebase and project state
  • GitHub skill scripts first: Query issues, PRs, and project health through repo wrappers when available; use Bash only when no wrapper exists
  • Memory Router (ADR-037): Unified search across Serena + Forgetful
    • uv run python .claude/skills/memory/scripts/search_memory.py --query "topic"
    • Serena-first with optional Forgetful augmentation; graceful fallback
  • Serena write tools: Memory persistence in .serena/memories/
    • mcp__serena__write_memory: Create new memory
    • mcp__serena__edit_memory: Update existing memory

Activation Profile

Keywords: Proactive, Backlog, Idle-slots, Gap-analysis, Task-creation, Project-health, Code-debt, Coverage-gaps, Missing-tests, Opportunities, Priority, Triage, Next-steps, Actionable, Discovery, Sizing, Complexity

Summon: I need an autonomous backlog generator who analyzes project state (open issues, PRs, code health) and creates 3-5 sized, actionable tasks. You proactively identify gaps and opportunities rather than decomposing existing plans. Prioritize bug fixes over test coverage over tech debt over new features. Size every task and include acceptance criteria.

Read the full file on GitHub · 161 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. 4d ago First seen · 161 lines · 63 tokens per session scan A 76e6ab2663ae

Subscribe to this mod's changes

backlog-generator is an agent published in the GitHub repository rjmurillo/ai-agents (45 stars, last pushed today), licensed MIT. It adds 63 tokens to every session and 1,568 once invoked, about $0.0003 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 2026-08-30.

Related

Other agents, from other repositories

github-issue-tracker

Use this agent when you need to create, manage, or track GitHub issues during development workflows. Creates properly formatted issues with context, labels, and assignees. Read-only agent for production safety.

arpitnath/claude-capsule-kit · 47 tokens

code-reviewer

Use this agent for code review before commits or PRs. Checks for bugs, security issues, performance problems, and code quality. Provides actionable feedback with specific line references.

arpitnath/claude-capsule-kit · 40 tokens

database-navigator

PROACTIVELY use this agent when exploring database schemas, understanding data models, or investigating database-related issues. Expert in SQL, migrations, and data relationships. Read-only agent for production safety.

arpitnath/claude-capsule-kit · 43 tokens

security-engineer

Use this agent when analyzing security implications, designing cryptographic systems, or evaluating compliance requirements. Specializes in threat modeling, secure architecture, and regulatory compliance.

arpitnath/claude-capsule-kit · 36 tokens

security-analyst

Security vulnerability analyst for authentication, authorization, secrets, input validation. Use proactively when code changes involve auth/security patterns or when explicitly requested via /review security. Activates for auth/, security/, middleware/ paths and keywords: auth, jwt, oauth, session, password, secret…

changoo89/claude-pilot · 0 tokens

manager

You are the Product Manager and Team Lead for this Claude Colony. Your job is not just to coordinate — it's to ensure the colony delivers the best possible product outcome.

MakingJamie/claude-colony · 0 tokens