Getting it into your agent
There is no command for this one: it runs only inside a plugin, and the catalogue could not identify which plugin ships it. The source is linked below.
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.
[](https://agentmods.dev/commands/thewaywithin/agent-11/blog)<a href="https://agentmods.dev/commands/thewaywithin/agent-11/blog"><img src="https://agentmods.dev/badge/commands/thewaywithin/agent-11/blog.svg" alt="Measured on agentmods" height="20"></a>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 5.1 | $0.00034 | $0.09021 |
| Opus 5 | $0.00017 | $0.04510 |
| Sonnet 5 | $0.00007 | $0.01804 |
| Haiku 4.5 | $0.00003 | $0.00902 |
Grade A, and why
blog 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 yesterday.
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.
How it starts
The opening of the file, as written. The whole thing — 710 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/blog Command
Generate a long-form post and the matching social package (X thread, LinkedIn post,
WIP.co line, image specs) on any topic you specify. Unlike /dailyreport — which turns a
structured progress log into a build-in-public update — /blog is for free-form writing:
thought pieces, tutorials, opinion posts, deep dives, explainers, anything that isn't tied
to a daily changelog.
/blog is Claude-native. No Python script, no API key required. Claude reads the voice
guide, pulls relevant context from the repo, and drafts all five artifacts directly.
/dailyreport works the same way — both commands share the same voice guide, the same
package shape and the same publish handoff.
Canonical spec. When ~/shared/reference/content-standard.md is present on this
machine, it is the source of truth for the package: the five outputs, the frontmatter, the
social shapes and the publish handoff. This command implements it. Where this file
deliberately differs, the divergence is marked DIVERGENCE and says why. Anything else
that disagrees with the standard is a bug in this file, not a local exception
(A11-ISS-29).
USAGE
# Inline topic — quick ideas
/blog why I stopped using feature flags for small teams
# Brief file — longer, structured inputs
/blog briefs/refactor-postmortem.md
# Topic with explicit context files
/blog the coffee button bug story --context progress/2025-11-19.md src/coffee.ts
Argument forms:
- Inline topic — a short phrase describing what to write about
- Brief file — path to a markdown file containing a longer brief (bullet points, outline, supporting notes, quotes, whatever you want to feed in)
- Optional
--context <files...>— extra files Claude should read before drafting (code, logs, notes, prior posts). Claude will also autoloadREADME.mdandCLAUDE.mdif present.
WHAT IT DOES
When you run /blog <topic>, Claude will:
- Resolve the voice guide — same chain as
/dailyreport, ending at thejamie-voiceskill, which is the voice authority - Resolve the staging directory — the synced vault drafts folder by default
- Gather context — read
README.md,CLAUDE.md, the brief file (if given), any--contextfiles, and anything the topic obviously depends on (e.g. if you're writing about a bug, Claude readsprogress.mdfor the fix history) - Title the piece through
jamie-titles— five scored candidates, one recommendation - Draft the long-form post — voice guide applied to the letter
- Derive the X thread — 6-10 tweets, each standing alone
- Derive the LinkedIn post — 200-400 words, complete read on its own
- Derive the WIP.co line — one build-in-public todo
- Write the image specs — placement, purpose, how each image gets made, alt, filename
- Write all five files to the staging directory and print the blog publish command
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.
- yesterday First seen · 710 lines · 34 tokens per session scan A 77cae5539410
blog is a command published in the GitHub repository TheWayWithin/agent-11 (15 stars, last pushed 13d ago), licensed MIT. It adds 34 tokens to every session and 9,021 once invoked, about $0.0002 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 2026-09-04.
Other commands, from other repositories
ensemble:generate-project-router-rules
Generate project-specific router rules by analyzing the project's tech stack.
ensemble:generate-router-rules
Generate router rules by introspecting installed agents and skills.
brainstorm
Facilitate a structured brainstorming session for feature development using Scrum Master techniques.
generate-prp
Generate comprehensive PRP (Product Requirements & Plans) with thorough research and validation.
execute-task
Execute individual development tasks from task breakdown documents.
execute-prp
Implement features from PRP specifications with comprehensive validation and testing.