plan-to-backlog

plan-to-backlog is a skill for Claude Code from flurdy/agent-skills. It costs 54 tokens per session (4,176 once invoked), scanned A, original, MIT.

A planning tool that turns an explicitly approved implementation plan into a small set of Beads tasks. Beads is a system for tracking durable engineering work.

In plain words
What is it for?
It helps decide whether a plan needs no task, one task, or a bounded group of tasks, check ownership and duplicates, and create the confirmed tracking items.
Why use it?
It prevents vague plans from becoming oversized or duplicate backlog items and shows proposed changes before writing them.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: model in frontmatter; names the AskUserQuestion tool.

Good fit It helps decide whether a plan needs no task, one task, or a bounded group of tasks, check ownership and duplicates, and create the confirmed tracking items.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/flurdy/agent-skills/plan-to-backlog
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.

Any agent
npx skills add flurdy/agent-skills --skill plan-to-backlog
Clone the repo
git clone --depth 1 https://github.com/flurdy/agent-skills

Made for: Claude Code.

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 plan-to-backlog

README.md
[![agentmods](https://agentmods.dev/badge/skills/flurdy/agent-skills/plan-to-backlog.svg)](https://agentmods.dev/skills/flurdy/agent-skills/plan-to-backlog)
Your own site
<a href="https://agentmods.dev/skills/flurdy/agent-skills/plan-to-backlog"><img src="https://agentmods.dev/badge/skills/flurdy/agent-skills/plan-to-backlog.svg" alt="Measured on agentmods" height="20"></a>
Per session 54 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 4,176 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. Third-party audits
  • NVIDIA SkillSpector warn 7 Sept 2026
SkillSpector: 6 findings, up to medium

These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →

  • medium Excessive Agency · line 6
    Skill selects an external model or provider that may use a different account or billing plan than the operator expects. Undisclosed model switches can cause unexpected cost or quota consumption.
    Fix: Remove the model/provider override or disclose it prominently and require explicit operator approval before invoking an external coding CLI or billed model.
  • medium Excessive Agency · line 14
    Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.
    Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
  • medium Rogue Agent · line 18
    Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.
    Fix: Remove any persistence mechanisms (cron jobs, startup scripts, state files). Skills should not maintain state across sessions without explicit user consent.
  • medium Excessive Agency · line 188
    Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.
    Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
  • medium Rogue Agent · line 188
    Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.
    Fix: Remove any persistence mechanisms (cron jobs, startup scripts, state files). Skills should not maintain state across sessions without explicit user consent.
  • medium Rogue Agent · line 250
    Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.
    Fix: Remove any persistence mechanisms (cron jobs, startup scripts, state files). Skills should not maintain state across sessions without explicit user consent.
How audits are shown
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 $0.00054 $0.04176
Opus 5 $0.00027 $0.02088
Sonnet 5 $0.00011 $0.00835
Haiku 4.5 $0.00005 $0.00418

Measured today against content hash 53dce01c85e5, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

plan-to-backlog 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 today.

The scan reads SKILL.md. This mod also ships 6 executable files (scripts/confirmed-bd.sh, scripts/sha256-stdin.sh, scripts/utc-now.sh, …), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

skills/plan-to-backlog/SKILL.md · 452 lines

How it starts

The opening of the file, as written. The whole thing — 452 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Plan to Backlog

Proposal-first. May recommend no backlog change. Never writes without confirmation.

Turn an approved architecture or implementation plan into the smallest justified durable Beads structure. Inspect the cited plan and existing work, decide whether no item, one focused item, or a bounded epic is warranted, preview the exact write set, then apply only that confirmed proposal.

The canonical behavior and thresholds are defined in the plan-to-backlog contract.

When to use

Select this skill dynamically, or through /plan-to-backlog, only when:

  • an /architect or implementation plan has been explicitly approved;
  • the plan has a stable source or exact capturable session text;
  • the user explicitly asks to create or reconcile durable Beads ownership rather than continue planning; and
  • no-item versus single-item versus epic is still a meaningful decision.

The existence or approval of a plan alone is not a trigger. Do not use this skill for raw ideas or Jira intake (/triage), plan refinement (/architect), retrospective backlog quality (/backlog-groom), or cross-system reconciliation (/tracking-sweep or /trello-beads).

Usage

/plan-to-backlog <plan-source>

Accepted sources:

  • repository or workspace Markdown path;
  • Bead ID whose description, design, notes, or linked specification contains the plan;
  • Jira or Confluence key/URL when the runtime can retrieve the complete plan; or
  • the exact current-session /architect result.

There is no invocation that bypasses preview. An initial request to "apply" still follows the full source, proposal, and confirmation procedure.

Ownership boundary

  • /architect owns technical planning and remains read-only.
  • /triage owns unstructured prompt/Jira intake and explicit --human-review tracking of pending human decisions; it hands approved implementation plans here without creating children.
  • /plan-to-backlog alone owns approved implementation-plan disposition, proposal, confirmation, apply, and recovery. It does not establish ownership of an unapproved human decision.
  • /backlog-groom remains retrospective and read-only by default.

Read the full file on GitHub · 452 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. today Changed · +19 lines · -7 tokens per session 53dce01c85e5
  2. 8d ago First seen · 433 lines · 61 tokens per session scan A 1037fe8d8fa3

Subscribe to this mod's changes

plan-to-backlog is a skill published in the GitHub repository flurdy/agent-skills (9 stars, last pushed yesterday), licensed MIT. It adds 54 tokens to every session and 4,176 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 2026-08-31.

Related

Other skills, from other repositories

recipe-create-meet-space

Create a Google Meet meeting space and share the join link.

googleworkspace/cli · 18 tokens

atmos-config

Atmos root configuration: atmos.yaml discovery, precedence, deep merging, basepath, imports, minimal bootstrap, and routing to narrower Atmos skills.

cloudposse/atmos · 31 tokens

workthreads

SpecStory Workthreads - a weekly work-thread rollup across a team's repos from SpecStory coding histories (any agent - Claude Code, Codex, Cursor, Gemini, and more). It groups the window's sessions into threads of work per project and labels each new / open / recently closed, so a lead sees what shipped, what is still…

specstoryai/getspecstory · 126 tokens

story-readiness

Validate that a story file is implementation-ready. Checks for embedded GDD requirements, ADR references, engine notes, clear acceptance criteria, and no open design questions. Produces READY / NEEDS WORK / BLOCKED verdict with specific gaps. Use when user says 'is this story ready', 'can I start on this story', 'is…

Donchitos/Claude-Code-Game-Studios · 77 tokens

autotask-creator

Rules for automation CRUD from the group-chat commander. The commander does not call mutation tools and does not edit cloud/autotasks files directly. It emits one or more top-level ... containers in its final text; the bus parses and applies them after the turn.

Orkas-AI/Orkas · 5 tokens

monorepo-management

Master monorepo management with Turborepo, Nx, and pnpm workspaces to build efficient, scalable multi-package repositories with optimized builds and dependency management. Use when setting up monorepos, optimizing builds, or managing shared dependencies.

wshobson/agents · 54 tokens