backlog

A workflow that examines one code repository, finds work worth doing, ranks it, and turns the results into GitHub issues on a Project board. It is designed for building and ordering a development backlog.

In plain words
What is it for?
Use it for backlog creation, sprint planning, repository audits, feature planning, and ranking fixes or improvements by value and return on effort.
Why use it?
It replaces scattered audits and manual prioritisation with one review of the repository, helping you decide what to work on within a time budget.

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/lucassantana-dev/sharekit/backlog
Any agent
npx skills add LucasSantana-Dev/sharekit --skill backlog
Clone the repo
git clone --depth 1 https://github.com/LucasSantana-Dev/sharekit

Made for: Claude Code, Codex.

Per session 62 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,341 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 $0.00062 $0.01341
Opus 5 $0.00031 $0.00671
Sonnet 5 $0.00012 $0.00268
Haiku 4.5 $0.00006 $0.00134

Measured 2d ago against content hash f976448cf8e7, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

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 2d ago.

The scan reads SKILL.md. This mod also ships 3 executable files (scripts/board.sh, scripts/dedup.sh, scripts/discover.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.

sharekit-profile/.claude/skills/backlog/SKILL.md · 126 lines

How it starts

The opening of the file, as written. The whole thing — 126 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/backlog

End-to-end backlog builder for a single repo. Turns "what's wrong or missing here?" into a curated, ROI-ranked, deduped set of GitHub issues on a Project board — with full specs for new features and a propose-then-confirm gate before any GitHub write.

Replaces: /audit-deep, /repo-state-snapshot, /ecosystem-health, /adt-specs-spec-new, /plan-to-issues, and manual board management.

When this fires

Auto-invoked on: "build a backlog", "what should I work on", "audit and plan", "sprint planning", "I have N days", and similar queries. Also auto-queued by /onboard-new-repo and auto-queues /next-priority at completion.

See references/workflow.md § Triggers for the full auto-invoke list.

Eight-phase workflow

Runs sequentially with parallel discovery in Phase 1. Each phase has explicit stop/skip conditions and a reconciliation line — never silently omit.

Phase summary:

  • Phase 0: RAG pre-flight + cache check for prior snapshot. Load approval history for category urgency penalties. See references/memory-integration.md.

  • Phase 1: Parallel discovery via audit-deep, ecosystem-health, repo-state-snapshot. Collect code markers and git history. Abort if not in a git repo.

  • Phase 2: Normalize findings, assign value_score (1–5), compute ROI: (severity × urgency × value_score) / effort. Dedup against open issues. Group into 3–6 themed bundles. See references/workflow.md § Ranking.

  • Phase 3: Interactive propose gate. Display findings by theme with Val column and justification. Support --budget 2d greedy knapsack. No GitHub writes before approval. See references/workflow.md § Propose.

  • Phase 4: Generate specs for approved features only (via adt-specs-spec-new). Skip if no features approved.

  • Phase 5: Write .claude/backlog/<YYYY-MM-DD>.md plan file with phased task list grouped by severity.

Read the full file on GitHub · 126 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 · 126 lines · 62 tokens per session scan A f976448cf8e7

Subscribe to this mod's changes

backlog is a skill published in the GitHub repository LucasSantana-Dev/sharekit (1 stars, last pushed 2d ago), licensed MIT. It adds 62 tokens to every session and 1,341 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.