Skip to content
SkillMixed1,626 tokens in use

sidebar-prioritizer

Relabel and reorder Codex sidebar tasks with P0 to P4 priorities, work categories and B7 age markers, based on evidence from task history.

3,862 stars on the repository MIT Licenseericosiu/ai-marketing-skills · sidebar-prioritizer
npx skills add ericosiu/ai-marketing-skills -s sidebar-prioritizer
View source

Install command as written in the repository's README

Skill label

measured from its files

What installing sidebar-prioritizer costs

31tokens idle
1,626tokens in use
2,929tokens, up to

Idle is what sits in context while the skill is installed. In use is its instructions, loaded when it runs. Up to adds the files its instructions link. Counts are approximate, made offline with cl100k_base.

Model dependence Mixed

Script-ledMixedModel-led

Scripts do part of the work and the model's judgement does the rest.

This describes the skill's structure, how much of it is scripts. It does not say how well it works. Scripts: scripts/plan_labels.py.

Touches

Nothing detected: no shell, network, file writes, git or credentials in its files.

Declared tags come from the skill's frontmatter; detected ones from its scripts, its code blocks and the commands it names in inline code. This is detected, not audited.

How it scores

Quality

How well the skill is written, counted from its own files: its frontmatter, its steps, examples, stated output and constraints, its size and whether every file it ships is one it names.How we score it →
Good
  • Frontmatter8/15
  • Structure11/25
  • Examples6/15
  • Output15/15
  • Size15/15
  • Resources9/15

Security

Starts at 100 and loses points for each thing in the skill's files that a reader should look at first.How we score it →
Excellent

No findings.

Repository health

Pre-computed score based on development activity, maintenance, community, maturity, and trend momentum.How we score it →
Good
  • Development activity88
  • Maintenance44
  • Community56
  • Maturity28
  • Momentum40

Sidebar Prioritizer makes the Codex sidebar show what work each task belongs to and what needs attention. It has three modes: refresh categories and age markers, reset priorities from current evidence, or audit and prepare a plan without applying changes.

Labels follow a short format such as P2B7 - Revenue - Renewals review, where B7 means more than seven days since substantive activity. A local Python planner validates and formats label records.

What You Get

  • Labels in the form priority, age marker, category and short description
  • A P0 to P4 rubric from immediate incident to done or reference-only
  • A private before and after ledger separating agent-solvable, human decision, approval needed, waiting, scheduled and done work
  • plan_labels.py, a local planner that formats labels and flags unknown or future activity
  • A verified count, a B7 count, coverage gaps and an ordered list of real follow-ups
  • A suggested routine of a weekday refresh and a weekly full reset

Common Use Cases

  • Resetting a crowded sidebar at the start of the week
  • Marking tasks that have sat for more than seven days without work
  • Auditing priorities without changing anything
  • Keeping category names consistent across projects

What Makes It Unique

It treats task titles and transcripts as data and not as instructions, separates idle from done and old from low priority, and requires a readback after every change. Repeating a refresh against unchanged evidence produces no mutations. Weekday refreshes preserve priorities and weekly resets reassess them.

Under The Hood

This is a prose workflow with one reference file and one Python script. plan_labels.py reads a private JSON inventory and prints formatted labels to the terminal. The agent uses Codex sidebar tools to list tasks, set titles and move items between sections. When the tools omit older entries, a fallback reads the local Codex state database in read-only mode and the matching session files for activity times. It does not write to the app database. Inside the AI Marketing Skills repository it can run an optional version check and telemetry logger that follows the saved consent setting.

Join founders building with open source

Opinionated takes, migration guides, cost-saving tips, and insights from the open source ecosystem.

Subscribe on SubstackJoin 750+ subscribers