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 skills add markoblogo/abvx-agent-skills --skill social-publishing-gategit clone --depth 1 https://github.com/markoblogo/abvx-agent-skillsWrote 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/skills/markoblogo/abvx-agent-skills/social-publishing-gate)<a href="https://agentmods.dev/skills/markoblogo/abvx-agent-skills/social-publishing-gate"><img src="https://agentmods.dev/badge/skills/markoblogo/abvx-agent-skills/social-publishing-gate/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/skills/markoblogo/abvx-agent-skills/social-publishing-gate"><img src="https://agentmods.dev/badge/skills/markoblogo/abvx-agent-skills/social-publishing-gate.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00086 | $0.00839 |
| Opus 5 | $0.00043 | $0.00419 |
| Sonnet 5 | $0.00017 | $0.00168 |
| Haiku 4.5 | $0.00009 | $0.00084 |
Grade A, and why
social-publishing-gate 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 9d 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 — 103 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Social Publishing Gate
Gate social distribution work so agents draft useful content without silently posting, spamming, or flattening brand voice.
Core Rule
Treat every external post, reply, comment, DM, schedule, or reaction as a side effect. Drafts are safe. Publishing requires explicit approval.
Default path:
source -> draft -> audit -> approval -> publish -> monitor
Workflow
- Source
- identify the source idea, artifact, product update, thread, transcript, or link;
- capture the intended audience, channel, goal, and non-goals;
- preserve the user's point of view instead of inventing generic thought leadership.
- Draft
- create channel-native drafts, not one generic post copied everywhere;
- keep one clear claim or insight per post;
- mark assumptions, missing proof, and claims that need checking.
- Audit
- check factual claims, dates, numbers, links, names, and attribution;
- remove generic AI phrasing, empty hype, fake certainty, and engagement bait;
- check brand voice, privacy, legal, client confidentiality, and platform norms;
- verify that calls to action are appropriate and not spammy.
- Approval
- show the final draft and the audit notes;
- ask for explicit approval before any external write action;
- if the user approves with edits, re-audit the changed draft.
- Publish
- use only approved channels, accounts, and tools;
- preserve a record of the final text, destination, timestamp or schedule, and tool used;
- stop if credentials, account identity, or target destination are ambiguous.
- Monitor
- collect read-only response signals when available;
- draft follow-ups for review instead of auto-replying;
- route reusable lessons into
agent-learning-layer-triage.
Channel Notes
- LinkedIn: be extra strict about over-optimized hooks, fake virality language, engagement bait, and automated comment behavior.
- X / Threads: split long ideas into native threads only when each post still has standalone value.
- Telegram / MediaHub: distinguish posting to owned channels from replying in communities; use approvals for both.
- Newsletters: check subject, preview text, links, unsubscribe/compliance expectations, and source attribution.
What ships with it
2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 9d ago First seen · 103 lines · 86 tokens per session scan A facb63d2f859
social-publishing-gate is a skill published in the GitHub repository markoblogo/abvx-agent-skills (16 stars, last pushed yesterday), licensed MIT. It adds 86 tokens to every session and 839 once invoked, about $0.0004 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 2026-09-03.
Other skills, from other repositories
cli-e2e
Write, modify, or debug Docker-based Composio CLI end-to-end tests under ts/e2e-tests/cli, including binary invocation, fixture isolation, output assertions, and package manifests. Use for CLI E2E test suites only; use cli-command for CLI source implementation.
trace
Dispatch trace subagent to investigate unknown issues — reproduces, traces, and reports root cause for fix handoff.
codex-agent
Use when you want a second-opinion review via Codex CLI, cross-verification after another agent implements changes, debugging help, or alternative implementation proposals. Requires Codex CLI to be installed and authenticated.
css-debug
Use this skill to diagnose CSS and frontend layout issues such as positioning, overflow clipping, Tailwind class conflicts, z-index stacking, and React rendering visibility problems.
openlore-analyze-codebase
Run a full static OpenLore analysis and summarize architecture, call graph, refactoring issues, and duplicate code. Use when asked to analyze, map, or assess a codebase without LLM inference.
config-validator
Validate AIWG configuration files and project setup for correctness and completeness.