weekly-backfill

weekly-backfill is a skill for Claude Code from DanialDaeHyunNam/omniscitus. It costs 95 tokens per session (2,098 once invoked), scanned A, original, MIT.

A backfill command that creates narrative weekly summaries for past completed weeks of project history. It reads existing work files and records what was built, decided, discussed, blocked, or left pending.

In plain words
What is it for?
Use it after migrating project history or when you need summaries for all earlier weeks that do not already have one.
Why use it?
It fills gaps when older weeks have no summary, especially after moving history into a new system. The summaries provide context rather than just a list of session files.

Skill for Claude Code

Written for Claude Code: ${CLAUDE_PLUGIN_ROOT} variable. Also seen: names the AskUserQuestion tool.

Runs only inside its plugin — its command needs a path that Claude Code sets for a plugin’s own hooks and for nothing else. Install the plugin, not this.

Part of the omniscitus plugin — 16 skills, 3 hooks shipped together

Good fit Use it after migrating project history or when you need summaries for all earlier weeks that do not already have one.

Compare 6 skills from other repositories ↓
Install

Getting it into your agent

This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.

Claude Code
/plugin marketplace add DanialDaeHyunNam/omniscitus
Claude Code
/plugin install omniscitus

Made for: Claude Code.

Or install omniscitus, the plugin that ships this one along with the rest of its 16 skills, 3 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 weekly-backfill

README.md
[![agentmods](https://agentmods.dev/badge/skills/danialdaehyunnam/omniscitus/weekly-backfill/github.svg)](https://agentmods.dev/skills/danialdaehyunnam/omniscitus/weekly-backfill)
Your own site
<a href="https://agentmods.dev/skills/danialdaehyunnam/omniscitus/weekly-backfill"><img src="https://agentmods.dev/badge/skills/danialdaehyunnam/omniscitus/weekly-backfill/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 weekly-backfill

Your own site · 80×15
<a href="https://agentmods.dev/skills/danialdaehyunnam/omniscitus/weekly-backfill"><img src="https://agentmods.dev/badge/skills/danialdaehyunnam/omniscitus/weekly-backfill.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 95 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,098 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 $0.00095 $0.02098
Opus 5 $0.00048 $0.01049
Sonnet 5 $0.00019 $0.00420
Haiku 4.5 $0.00010 $0.00210

Measured 10d ago against content hash 2cc59162df5d, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

weekly-backfill 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 10d 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/omniscitus/skills/weekly-backfill/SKILL.md · 241 lines

How it starts

The opening of the file, as written. The whole thing — 241 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Weekly Backfill — Rich Narrative Weekly Summaries

/wrap-up already auto-generates a summary of the last completed week on the first run after the week flips. This skill backfills all earlier weeks that don't have one yet — useful right after /omniscitus-migrate on a project with months of history.

The output is rich narrative, not a list. Each week's summary includes:

  • One-line headline (the arc of the week)
  • Per-domain narrative (what was actually built/decided, in flowing prose)
  • Key decisions (with the why — what options were considered, what was chosen)
  • Cross-domain coordination (multi-member work, hand-offs)
  • Blockers / constraints encountered
  • Pending items at week's end
  • Light metrics

When to Use

  • User types /weekly-backfill
  • Right after /omniscitus-migrate on a long-history project
  • User says "주간 요약 백필", "past weeks summary", "지난 주 다 정리"

Instructions

Step 1: Discover candidates

Run the helper to get a JSON list of weeks that need a rich summary:

node "${CLAUDE_PLUGIN_ROOT}/scripts/weekly-backfill.cjs" candidates "$(pwd)"

The JSON looks like:

{
  "candidates": [
    {
      "week": "2026-W14",
      "start": "2026-03-30",
      "end": "2026-04-05",
      "action": "create" | "upgrade",
      "already_in_index": false,
      "file_path_abs": "/.../.omniscitus/history/_weekly/2026-W14.md",
      "unit_count": 29,
      "domains": ["content", "design", "marketing", "native", "product", "server", "web"],
      "units": [
        {
          "id": "...",
          "title": "...",
          "domain": "web",
          "status": "closed",
          "author": "aria-web",
          "unit_file_abs": "/.../.omniscitus/history/web/2026-04-02-tile-review-v0-implementation.md",
          "source_abs": "/.../.claude/member/aria-web/done/01-20260402-tile-review-v0-implementation.md"
        },
        ...
      ]
    }
  ],
  "summary": {
    "total_candidates": 18,
    "to_create": 17,
    "to_upgrade": 1,           // existing fast-mode files
    "skipped_in_progress": 0,
    "skipped_already_rich": 0,
    "skipped_user_authored": 0
  }
}

Read the full file on GitHub · 241 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. 10d ago First seen · 241 lines · 95 tokens per session scan A 2cc59162df5d

Subscribe to this mod's changes

weekly-backfill is a skill published in the GitHub repository DanialDaeHyunNam/omniscitus (5 stars, last pushed 1mo ago), licensed MIT. It adds 95 tokens to every session and 2,098 once invoked, about $0.0005 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.