post-week

A weekly workflow for creating and reviewing a batch of written content, including newsletters, blog posts, and social-media carousel decks. A carousel is a post made of several swipeable slides.

In plain words
What is it for?
Use it to draft the week's planned content, collect approval, and hand newsletters, blog posts, and supported carousel posts to their publishing systems.
Why use it?
It puts a week of content into one review session instead of spreading the work across separate tasks. It also reflects that LinkedIn is no longer used as an outbound publishing channel in this workflow.

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/jared833/claude-code-hooks/post-week
Any agent
npx skills add jared833/claude-code-hooks --skill post-week
Clone the repo
git clone --depth 1 https://github.com/jared833/claude-code-hooks

Made for: Claude Code, Codex.

Per session 63 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 12,273 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 $0.00063 $0.12273
Opus 5 $0.00032 $0.06136
Sonnet 5 $0.00013 $0.02455
Haiku 4.5 $0.00006 $0.01227

Measured 2d ago against content hash 463bd0e50eb9, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

post-week 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.

skills/post-week/SKILL.md · 580 lines

How it starts

The opening of the file, as written. The whole thing — 580 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Weekly written-content batch

Draft a week of everything Jared writes, get it approved in one sitting, and hand each piece to the thing that publishes it. Jared's attention: one review page, one pass.

CORRECTION 2026-08-18: LinkedIn is not a posting channel

Jared's call, same shape as the 2026-07-26 X retirement. Nothing outbound goes to LinkedIn by any route: no longforms, no carousel PDF, no Buffer create_post to the LinkedIn channel. Everything below that describes drafting a LinkedIn longform, rendering a LinkedIn carousel PDF, or queueing either to Buffer is dead. It stays in this file as history, marked inline, rather than deleted outright, the same way the X correction above it was handled.

What survives, unchanged: the Content Bank harvest, the newsletter (still buildlog/MailerLite, never touched Buffer), the blog posts (still buildlog/daily-publish, never touched Buffer), and all fourteen carousel decks a week (now Instagram + TikTok only, every day including Sunday, none of them rendering a LinkedIn PDF or riding the /api/session review flow the old LinkedIn leg used).

This skill now makes zero Buffer API calls. The only Buffer activity left anywhere in the pipeline is /vid-batch pushing carousels and videos to Instagram and TikTok; its budget arithmetic near the bottom of this file is unaffected and still correct.

CORRECTION 2026-08-19: nl-/blog- items no longer route through an Engage session

The bug this closes: newsletter 2026-w33 was approved in Engage on 2026-08-18 but the buildlog write-back (old step 7.5) only ran if the drafting session was still alive polling /api/session/<id>/decisions. It wasn't, so the file never got written, and newsletter-send.yml silently skipped its Tuesday send. This was the second time this exact shape of failure cost real content, after 14 blog posts plus a newsletter rotted in buildlog's own /review in July.

The fix: this skill now writes the newsletter and blog files straight into buildlog's content directories at status: draft, commits, and pushes them as part of drafting itself, in the same session, with no Engage session in between. Review no longer depends on any session's lifetime: Jared reviews and approves whenever he wants on Engage's /written page, which reads and writes buildlog's GitHub repo directly. Old steps 6 (the buildlog review session), 6.5 (dates, now moved earlier), 7.5 (ship the buildlog items), and 8 (close the session) are replaced below by new steps 5.6 and 6. POST /api/session is untouched for /x-engage and /linkedin-engage, this correction only removes nl-/blog- items from that path.

Read the full file on GitHub · 580 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 · 580 lines · 63 tokens per session scan A 463bd0e50eb9

Subscribe to this mod's changes

post-week is a skill published in the GitHub repository jared833/claude-code-hooks (2 stars, last pushed 13d ago), licensed MIT. It adds 63 tokens to every session and 12,273 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.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

brainstorming

You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.

obra/superpowers · 37 tokens

auto-perf-optimize

Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.

microsoft/vscode · 62 tokens

chat-perf

Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.

microsoft/vscode · 51 tokens

chat-pet-sprite-creation

Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.

microsoft/vscode · 53 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens