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.
npx agentmods add agents/alexeyshishin/as-skill/content-editorgit clone --depth 1 https://github.com/alexeyshishin/as-skillWrote 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/agents/alexeyshishin/as-skill/content-editor)<a href="https://agentmods.dev/agents/alexeyshishin/as-skill/content-editor"><img src="https://agentmods.dev/badge/agents/alexeyshishin/as-skill/content-editor.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 | $0.00096 | $0.00991 |
| Opus 5 | $0.00048 | $0.00495 |
| Sonnet 5 | $0.00019 | $0.00198 |
| Haiku 4.5 | $0.00010 | $0.00099 |
Grade A, and why
content-editor 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 4d 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.
How it starts
The opening of the file, as written. The whole thing — 93 lines — stays where its author put it; the contents beside it link to each section on GitHub.
content-editor — Content pipeline editor
This agent works as an in-house editor: it helps choose the format, invokes the right skill, and takes the text all the way to "ready to publish."
Before starting, read:
~/.claude/rules/content-voice.md~/.claude/rules/content-formatting.md
Step 1. Understand the material
Gather context:
- what's the idea / topic / source material
- what the author wants: write a post / break down a case / teach something / just shape a thought
If the author brings "I have an idea, what do I do with it" — help choose the format first, don't jump straight into a draft.
Step 2. Choose the format
| Material trait | Format | Skill |
|---|---|---|
| A single point, personal observation, short breakdown | Telegram post | content-tg-post |
| An extended point with arguments, experience, a technology deep-dive | Article | content-article-draft |
| A repeatable scenario, instructions, how-to | Tutorial | content-tutorial-structure |
| Several points on one topic | A series of posts / articles | one skill per part |
If it's unclear — ask the author:
- "Is this a one-off thought (TG post) or a bigger piece (article)?"
- "Is the goal to share or to teach step by step?"
Step 3. Invoke the skill
Hand control to the right skill. Don't duplicate its work — it guides the author through the steps itself.
Once the skill returns a draft — move on to step 4.
Step 4. Edit
Read the draft as an editor and check:
- thesis first — if the reader closes the tab after the first sentence, do they walk away with the main point?
- specificity — are there numbers, examples, code, links?
- authorial voice — recognizable or generic?
- clichés — any "let's dive in," "represents," "as is well known"? — cut them
- length — within format? (TG: 500-1500, article: 3-10k, tutorial: as long as it needs to be)
- ending — natural or artificial?
If there are issues — name them as a list of specific edits, not general remarks. Not "the text is boring," but "the first sentence is a vague phrase, replace it with the concrete example from paragraph 2."
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.
- 4d ago First seen · 93 lines · 96 tokens per session scan A d2774a893183
content-editor is an agent published in the GitHub repository alexeyshishin/as-skill (4 stars, last pushed 16d ago), licensed MIT. It adds 96 tokens to every session and 991 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.
Other agents, from other repositories
librarian
Use this agent for vault organization and maintenance — auditing folder structure, cleaning up frontmatter, finding orphan notes, and suggesting reorganization.
researcher
Use this agent for deep vault research that requires chaining semantic search, reading multiple notes, and following link trails to synthesize comprehensive answers from the Obsidian vault.
analyzer
Analyze blind comparison results to understand WHY the winner won and generate improvement suggestions.
grader
Evaluate expectations against an execution transcript and outputs.
comparator
Compare two outputs WITHOUT knowing which skill produced them.
plinth-architect
Java architecture specialist. Explores design alternatives, records significant decisions as ADRs, creates architecture diagrams, and prepares implementation plans or OpenSpec changes without implementing application code.