repurpose

A command that turns an approved long article, research report, or weekly report into several formats for different publishing channels.

In plain words
What is it for?
Use it to create X threads and posts, LinkedIn articles, newsletter snippets, and quote cards from a source piece.
Why use it?
It removes the need to rewrite the same source material separately for each channel and checks the results against the source.

Command

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 commands/saigonxiii/evc/repurpose
Clone the repo
git clone --depth 1 https://github.com/SaigonXIII/evc
Per session 56 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 3,233 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 $0.00056 $0.03233
Opus 5 $0.00028 $0.01617
Sonnet 5 $0.00011 $0.00647
Haiku 4.5 $0.00006 $0.00323

Measured 3d ago against content hash fa8f2a8a26c5, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

repurpose 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 3d 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.

_templates/commands/repurpose.md · 355 lines

How it starts

The opening of the file, as written. The whole thing — 355 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Repurpose

Take one long-form piece and generate a full multi-channel content pack from it. Extracts the thesis, supporting points, quotes, stats, and CTA; drafts native formats for each channel; runs QA on each; and stages everything for side-by-side review.

Usage

/project:repurpose [slug]                    # blog (default source type)
/project:repurpose blog [slug]
/project:repurpose research [slug]
/project:repurpose report w15

Source Types

Type Input path
blog (default) {{CONTENT_OUTPUT_DIR}}/blog/[slug]/copy.html + metadata.json + qa-report.md
research {{CONTENT_OUTPUT_DIR}}/research/[slug]/report.md
report {{CONTENT_OUTPUT_DIR}}/reports/[slug]/weekly-report.md

Prerequisites

For blog source:

  • copy.html exists and has been through /blog-qa with verdict = READY
  • metadata.json present

For research source:

  • report.md exists
  • At least one cited source present

For report source:

  • Weekly report file exists
  • Note: weekly reports are often internal — /repurpose report produces LinkedIn + internal Slack formats only, not public X content

Steps

1. Gate Check

Read the source file(s). If they don't exist or (for blog) the QA verdict is not READY, stop with a clear message:

Source not READY. Blog QA verdict: NOT READY. Fix the issues in qa-report.md and re-run /blog-qa before repurposing.

2. Load Canon + Mode

  • Read {{CANON_DIR}}/canon-rules.json — brand voice, banned phrases, USPs
  • Load content-mode context — X character limits, link placement rules, no hashtags
  • Read {{CONTENT_ENGINE_DIR}}/memory/learning-log.md if present — use winning patterns from past performance

3. Extract Key Elements

Read the source and extract what's actually there — never invent an element the piece doesn't contain:

  • Thesis — the one-sentence claim
  • Supporting points — the strongest arguments or data
  • Pull quotes — verbatim lines strong enough to stand alone (if present)
  • Hero stat — the most compelling number, with source (if present)
  • Contrarian take — where the piece disagrees with conventional wisdom (only if it genuinely does)
  • CTA — what should the reader do next?

Read the full file on GitHub · 355 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. 3d ago First seen · 355 lines · 56 tokens per session scan A fa8f2a8a26c5

Subscribe to this mod's changes

repurpose is a command published in the GitHub repository SaigonXIII/evc (56 stars, last pushed 2mo ago), licensed MIT. It adds 56 tokens to every session and 3,233 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 2026-08-30.