create-backlog

A workflow that creates large issue-tracker items called epics from a specification document, optionally breaking them into smaller tasks.

In plain words
What is it for?
Use it to create or update epics from a file or directory, optionally decompose them into subtasks, or preview changes without applying them.
Why use it?
It reduces the manual work of turning a written specification into an organized backlog.

Skill for Claude CodeCodex

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 skills/asysta-act/agent-flow/create-backlog
Any agent
npx skills add asysta-act/agent-flow --skill create-backlog
Clone the repo
git clone --depth 1 https://github.com/asysta-act/agent-flow

Made for: Claude Code, Codex.

Per session 15 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,900 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. 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 $0.00015 $0.03900
Opus 5 $0.00008 $0.01950
Sonnet 5 $0.00003 $0.00780
Haiku 4.5 $0.00002 $0.00390

Measured 2d ago against content hash 1c84bf063ffb, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

create-backlog scanned grade A with 1 finding 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

// Gitea: use Bash curl REST API (MCP Gitea does not guarantee epic label support)
skills/create-backlog/SKILL.md · 391 lines

How it starts

The opening of the file, as written. The whole thing — 391 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Create Backlog

Input: $ARGUMENTS = spec path (positional) + optional flags (--decompose, --update, --dry-run, --yolo)

If $ARGUMENTS contains --yolo, activate YOLO mode: auto-approve human gates. Note: Gate 3 confirmation can still be overridden by --dry-run.

Configuration

Read Automation Config from CLAUDE.md section ## Automation Config. Follow ../../core/config-reader.md.

Required:

  • Issue Tracker: Type, Instance, Project

Optional:

  • Sprint Planning: Epic template (path to custom template file — overrides default Epic Card Template)
  • Agent Overrides: Path (default: customization/)
  • Decomposition: Max subtasks (default: 7) — used only with --decompose

Flag Parsing

Parse $ARGUMENTS:

  • Remove --decompose, --update, --dry-run, --yolo from the arguments string
  • Remainder = spec path (file or directory)
  • If spec path is empty: STOP with "Usage: /agent-flow:create-backlog [--decompose] [--update] [--dry-run] [--yolo]"
  • --decompose and --update are mutually exclusive. If both present: STOP with "Cannot use --decompose with --update."
  • --dry-run can combine with any other flag.

Orchestration

0. MCP pre-flight check

If --dry-run, skip MCP check (no tracker writes will occur).

Otherwise, follow ../../core/mcp-preflight.md:

  • Read Type from Automation Config (Issue Tracker section)
  • Check that at least one mcp__* tool matching the tracker type is accessible
  • If not accessible → BLOCK with:
    [agent-flow] 🔴 Pipeline Block
    Agent: create-backlog
    Step: MCP pre-flight check
    Reason: Cannot connect to your {Type} issue tracker.
    Detail: Expected tool prefix: mcp__{Type}__*. No matching tool is registered in this session.
    Recommendation: Run /agent-flow:check-setup for diagnostics, or /agent-flow:setup-mcp to configure the {Type} integration.
    

0b. State initialization

Create .agent-flow/backlog-{YYYYMMDD-HHmmss}/ directory. Initialize state.json with:

{
  "schema_version": "1.0",
  "run_id": "backlog-{YYYYMMDD-HHmmss}",
  "parent_run_id": null,
  "mode": "backlog-creation",
  "pipeline": "create-backlog",
  "status": "running",
  "started_at": "{ISO-8601}",
  "updated_at": "{ISO-8601}",
  "config": {
    "profile": null,
    "flags": [],
    "retry_limits": {
      "fixer_iterations": 5,
      "test_attempts": 3,
      "build_retries": 3
    }
  },
  "backlog": {
    "spec_path": "{spec-path}",
    "epics_total": 0,
    "epics_created": 0,
    "epics_failed": 0,
    "subtasks_created": 0,
    "created_issues": []
  }
}

Follow atomic write protocol from ../../core/state-manager.md.

Read the full file on GitHub · 391 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 · 391 lines · 15 tokens per session scan A 1c84bf063ffb

Subscribe to this mod's changes

create-backlog is a skill published in the GitHub repository asysta-act/agent-flow (12 stars, last pushed 1mo ago), licensed MIT. It adds 15 tokens to every session and 3,900 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other skills, from other repositories

team-up

Orchestrate persistent agent teams with TeamCreate. Use when the user says "team up", "spin up a team", or invokes /team-up.

nvandessel/team-up · 34 tokens

cortivex-pipeline

Build and run AI agent pipelines that decompose complex tasks into coordinated agent workflows.

AhmedRaoofuddin/Cortivex · 22 tokens

project-graveyard

Scans the developer's machine for dead side projects, autopsies each one from its git history (died at the payments wall, killed by a newer project, finished but never shipped), surfaces their personal death patterns, and picks the corpse most worth resurrecting — then helps ship it. Use when the user mentions…

Shubhamsaboo/awesome-llm-apps · 127 tokens

web-app-penetration-testing

Pentest a web app or website end to end — black-box testing of a live URL, staging environment, or local dev server that finds and exploits real vulnerabilities (auth bypass, broken access control, IDOR, injection, XSS, SSRF, business logic) and proves each one with a working proof-of-concept instead of a signature…

usestrix/strix · 129 tokens

haiku

When writing a haiku for this bot, follow these conventions.

agno-agi/agno · 0 tokens

deploy-docker-compose

Run the Omnigent server as a Docker compose stack (server + Postgres) on any Docker host — your laptop, a VPS, EC2 by hand, or as the base layer of any container-platform deploy. Invoke when the user wants to build the image, bring up the compose stack, debug the stack on a host they already have, or extend the stack…

omnigent-ai/omnigent · 84 tokens