backlog-compiler

backlog-compiler is a skill for Claude Code from krzysztofsurdy/code-virtuoso. It costs 69 tokens per session (3,378 once invoked), scanned A, original, MIT.

A guide that turns a product requirements document, ticket, or feature description into a saved, ordered work plan. Each step includes a command that can objectively verify completion.

In plain words
What is it for?
Use it to prepare backlog files for the iteration loop, break specifications into steps, order the work, and define checks for each step.
Why use it?
It makes vague feature requests suitable for an automated delivery loop and avoids relying on an agent's claim that work is done. It also reuses project settings when creating the plan.

Skill for Claude Code

Written for Claude Code: user-invocable in frontmatter. Also seen: mentions subagents; mentions Claude Code.

Part of the loop-virtuoso plugin — 2 skills, 4 commands, 2 hooks shipped together

Good fit Use it to prepare backlog files for the iteration loop, break specifications into steps, order the work, and define checks for each step.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/krzysztofsurdy/code-virtuoso/backlog-compiler
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 krzysztofsurdy/code-virtuoso --skill backlog-compiler
Clone the repo
git clone --depth 1 https://github.com/krzysztofsurdy/code-virtuoso

Made for: Claude Code.

Or install loop-virtuoso, the plugin that ships this one along with the rest of its 2 skills, 4 commands, 2 hooks.

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-compiler

README.md
[![agentmods](https://agentmods.dev/badge/skills/krzysztofsurdy/code-virtuoso/backlog-compiler/github.svg)](https://agentmods.dev/skills/krzysztofsurdy/code-virtuoso/backlog-compiler)
Your own site
<a href="https://agentmods.dev/skills/krzysztofsurdy/code-virtuoso/backlog-compiler"><img src="https://agentmods.dev/badge/skills/krzysztofsurdy/code-virtuoso/backlog-compiler/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 backlog-compiler

Your own site · 80×15
<a href="https://agentmods.dev/skills/krzysztofsurdy/code-virtuoso/backlog-compiler"><img src="https://agentmods.dev/badge/skills/krzysztofsurdy/code-virtuoso/backlog-compiler.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 69 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,378 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 $0.00069 $0.03378
Opus 5.5 $0.00028 $0.01351
Sonnet 5.5 $0.00014 $0.00676
Haiku 4.5 $0.00007 $0.00338

Measured 2d ago against content hash 61a43ca6dbfb, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

backlog-compiler 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 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.

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/loop-virtuoso/skills/backlog-compiler/SKILL.md · 160 lines

How it starts

The opening of the file, as written. The whole thing — 160 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Backlog Compiler

Converts an existing spec (PRD, ticket, or freeform feature description) into .code-virtuoso/loop/backlog.json - the committed plan that iteration-loop executes one step at a time, with completion gated by an objective verifyCommand, never by self-report. Each item is a sequence of steps; a simple item is a single step.

Step 0: Reuse saved project settings

Before asking the user anything, read the merged Code Virtuoso config (spec/config-spec.md): the user file ($CODE_VIRTUOSO_CONFIG_HOME/config.json, else ${XDG_CONFIG_HOME:-$HOME/.config}/code-virtuoso/config.json), then <git root>/.code-virtuoso/config.json, then <git root>/.code-virtuoso/config.local.json. Later files win; objects merge, arrays and scalars replace. Missing files are normal.

root=$(git rev-parse --show-toplevel 2>/dev/null || pwd)
home="${CODE_VIRTUOSO_CONFIG_HOME:-${XDG_CONFIG_HOME:-$HOME/.config}/code-virtuoso}"
files=(); for f in "$home/config.json" "$root/.code-virtuoso/config.json" "$root/.code-virtuoso/config.local.json"; do [ -f "$f" ] && files+=("$f"); done
[ ${#files[@]} -gt 0 ] && jq -s 'reduce .[] as $x ({}; . * $x)' "${files[@]}" || echo '{}'

Two namespaces matter here:

  • ticket-delivery: commands.test and commands.staticAnalysis answer the test and static analysis questions below; branchPattern, ticketIdPattern and mainBranch shape the branch (Step 1). The legacy ticket-delivery supplement file is not read here; if the namespace is empty, run the ticket-delivery setup once to save it.
  • loop: defaults for config in Step 6 (maxIterations, permissionMode, allowedTools, allowedPaths, protectedPaths, and the other limits). Seed the backlog's config from these values instead of the table in Step 6. Never save a credential there.

For each answer the config does not give, ask the user directly:

  1. What command runs the test suite for a single file/class (the answer becomes the basis for each step's verifyCommand)?
  2. What command runs static analysis / type-checking, if any (append to verifyCommand with &&)?
  3. Which directories or files must never be modified by the loop (test directories, CI config, fixtures) - these become config.protectedPaths?
  4. Primary stack, to pick a sensible config.allowedTools base (see Step 6).

Read the full file on GitHub · 160 lines

Files

What ships with it

4 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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 · 160 lines · 69 tokens per session scan A 61a43ca6dbfb

Subscribe to this mod's changes

backlog-compiler is a skill published in the GitHub repository krzysztofsurdy/code-virtuoso (36 stars, last pushed yesterday), licensed MIT. It adds 69 tokens to every session and 3,378 once invoked, about $0.0003 per session on Opus 5.5. 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 2026-10-22.