Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/revaya-ai/revaya-aios-workspace-templatenpx agentmods add commands/revaya-ai/revaya-aios-workspace-template/draft-postWrote 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/revaya-ai/revaya-aios-workspace-template/draft-post)<a href="https://agentmods.dev/commands/revaya-ai/revaya-aios-workspace-template/draft-post"><img src="https://agentmods.dev/badge/commands/revaya-ai/revaya-aios-workspace-template/draft-post/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/commands/revaya-ai/revaya-aios-workspace-template/draft-post"><img src="https://agentmods.dev/badge/commands/revaya-ai/revaya-aios-workspace-template/draft-post.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00000 | $0.01434 |
| Opus 5 | $0.00000 | $0.00717 |
| Sonnet 5 | $0.00000 | $0.00287 |
| Haiku 4.5 | $0.00000 | $0.00143 |
Grade A, and why
draft-post 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 10d 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 — 146 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Draft Post
LinkedIn post copywriter agent. Invokes the linkedin-content-creator skill to draft a publish-ready post in your voice. Use for all LinkedIn content — story posts, operational problem posts, lead magnet promos, hot takes.
Variables
request: $ARGUMENTS (topic, angle, or post type — e.g., "operational problem: founders can't delegate", "transformation story", "lead magnet promo")
Instructions
You are drafting a LinkedIn post for you. Invoke the linkedin-content-creator skill and follow it exactly.
Step 1: Load context
Before drafting, read:
context/content-engine/content-strategy.md— your positioning, voice rules, pillar systemcontext/content-engine/calendar.md— what's already been posted or planned (avoid repeating themes)
If a research brief path was provided in the request, read that file and pull the top content angles and hook phrases before drafting.
Step 2: Invoke linkedin-content-creator skill
Use the Skill tool to invoke linkedin-content-creator. Follow all instructions in the skill exactly, including:
- your voice rules (non-negotiable)
- Authority signal stack (at least 2 of 4)
- 5-part story framework
- Hook formula (8 words or fewer)
- Quality checklist before presenting
Step 3: Pre-publish quality gate
Before presenting the draft, run these checks. Flag any that fail — do not silently fix them, surface them so you can decide.
Hook check:
- 8 words or fewer
- Creates an information gap (not a statement, not a question without stakes)
- Could NOT apply to anyone — specific enough to your experience
Calendar check (read calendar.md):
- This pillar hasn't been overrepresented in the last 2 weeks (if 3+ posts in same pillar recently, flag it)
- This theme/angle hasn't been used in the last 30 days
- IFP/ICP balance — check current month's split. Flag if pushing past 70/30 in either direction.
Voice check:
- No banned words (leverage, synergy, delve, unlock, cutting-edge, game-changer, seamless, robust, revolutionize, streamlined, real results, empower, transform your business, in today's world, craft/crafting, realm, furthermore, disruptive, utilize)
- No em dashes, semicolons, or asterisks in body copy
- Sounds like you talking, not a content template
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.
- 10d ago First seen · 146 lines · 0 tokens per session scan A d249e2c7269c
draft-post is a command published in the GitHub repository revaya-ai/revaya-aios-workspace-template (2 stars, last pushed 6mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,434 tokens. 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 commands, from other repositories
deps-audit
Audit project dependencies for vulnerabilities, outdated packages, license conflicts, and supply chain risks — then provide actionable remediation strategies.
README
Git workflow and quality assurance commands for the claude-skills repository.
merge-conflict-analysis
You are analyzing merge conflicts for PR #${{ pr-number }}.
dispatcher
Pick the next-best repo to work on across the portfolio — rank free repos, recommend one, claim its lease atomically, and route to the entry command.
growth-seo
SEO audit and optimization for organic search ranking.
growth-ab-test
Command "growth-ab-test" from christopherlouet/claude-base, covering growth-ab-test agent, context, objective, workflow and expected output.