A command that turns a shipped customer-facing feature into a reviewable brief for a blog post or pull request. It follows the project's defined handoff process and can place the brief in a local content inbox.

Use it after releasing a new feature, major improvement, or launch to record the audience, topic angle, and search keyword for the related content work.

It prevents marketing content from being forgotten after a feature ships and keeps internal changes from being treated as launch material. It also makes external publishing a deliberate, reviewable step.

content — Command by vijayatechlabs

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/vijayatechlabs/openstart/content

Clone the repo

git clone --depth 1 https://github.com/vijayatechlabs/openstart

Made for: Claude Code.

Per session 20 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 513 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.

Model	Per session	Once invoked
Fable 5	$0.00020	$0.00513
Opus 5	$0.00010	$0.00257
Sonnet 5	$0.00004	$0.00103
Haiku 4.5	$0.00002	$0.00051

Measured 2d ago against content hash 4147d8750839, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

content 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.

.claude/commands/content.md · 45 lines

What it actually says

You are running the OpenStart content handoff for the current project.

Follow .ai/framework/CONTENT-HANDOFF.md exactly. It is the canonical description of the ship → blog pipeline.

When to run

Only for user-facing / marketable changes — a new feature, a notable improvement, a launch. Skip internal refactors, infra, and most bug fixes (those go in CHANGELOG.md only). This is step 5 of the Definition of Done (AGENT-GUIDE.md §10).

Steps

Run the capture script with what shipped and any angle the user gave:
```
bash .ai/framework/content.sh "<what shipped>" [--audience "<who>"] [--angle "<hook>"] [--keyword "<seo term>"]
```
If the user didn't specify audience/angle/keyword, infer sensible values from the change and pass them — but never invent a feature that didn't ship.
Show the output — the local brief path, where it was delivered, and the brief text — so the user can review.
Ask before any external write. In Local mode the brief is just written to the blog's CONTENT-INBOX.md — no confirmation needed. In GitHub mode, do NOT run gh issue create automatically (external write, AGENT-GUIDE.md §9). Ask:

"Shall I file this brief as a content issue on <blog-repo>?"
If confirmed (GitHub mode), run the gh issue create one-liner that content.sh printed and report the returned issue URL.

Notes

The blog target is configured once in .ai/docs/CONTENT-PIPELINE.md: **Content path:** ../blog (Local) or **Content repo:** owner/blog (GitHub). The CONTENT_DIR / CONTENT_REPO env vars override it for one-offs. If neither is set, tell the user how to set the line; the brief is still logged locally.
The brief is a seed — the actual post is written in the blog/content project following the AEO framework.

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.

2d ago First seen · 45 lines · 20 tokens per session scan A 4147d8750839

Subscribe to this mod's changes

content is a command published in the GitHub repository vijayatechlabs/openstart (5 stars, last pushed 4d ago), licensed MIT. It adds 20 tokens to every session and 513 once invoked, about $0.0001 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.

Code review Research Writing and docs aeo

content

Getting it into your agent

What it costs to keep this loaded

Grade A, and why

Nothing flagged

What it actually says

When to run

Steps

Notes

What this file has done since we first saw it

Other commands, from other repositories

seo-audit

content-engine

performance-report

backlink-gap

seo-drift

geo