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 conorbronsdon/agent-context-os --skill social-postgit clone --depth 1 https://github.com/conorbronsdon/agent-context-osWrote 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/conorbronsdon/agent-context-os/social-post)<a href="https://agentmods.dev/skills/conorbronsdon/agent-context-os/social-post"><img src="https://agentmods.dev/badge/skills/conorbronsdon/agent-context-os/social-post.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 | $0.00061 | $0.00576 |
| Opus 5 | $0.00030 | $0.00288 |
| Sonnet 5 | $0.00012 | $0.00115 |
| Haiku 4.5 | $0.00006 | $0.00058 |
Grade A, and why
social-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 6d 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 — 49 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Social Post — Musician
Write a social media post for the artist. Load their artist context and promotion strategy before writing.
Before writing
- Read
projects/example-musician/artist-context.md— understand the sound, audience, and voice - Read
projects/example-musician/promotion-strategy.md— understand what's being promoted and what's worked before - Read
writing/skills/avoid-ai-writing/SKILL.md— apply its writing audit - Note the platform — Instagram, TikTok, Twitter/X, and LinkedIn all require different approaches
Platform guidelines
- Caption can be longer but front-load the most interesting line — it's what shows before "more"
- 1-3 hashtags max, at the end or in a comment — not sprinkled throughout
- No "link in bio" as the opener unless that's genuinely their voice
- Can be a story, an observation, a behind-the-scenes detail, or a direct announcement
- Avoid the "excited to share" opener — just share it
TikTok
- The caption is secondary to the video, but it should add context or a hook that drives saves/shares
- Shorter is better — 1-3 sentences
- Trending sounds, challenges, or formats can be referenced but don't force them
Twitter/X
- 280 characters or a thread if the story warrants it
- Punchy, direct — cut everything soft
- Can be more casual and real-time than Instagram
Writing rules
- Write in the artist's voice based on their context file — specific to them, not generic musician content
- No AI-isms (see
writing/skills/avoid-ai-writing/SKILL.md) - Avoid: "excited to share," "thrilled to announce," "I've been working so hard on this," "dream come true"
- Lead with something specific — a lyric, a detail, a moment, a question — not a label ("NEW MUSIC OUT NOW")
- Match energy to the release: a quiet introspective track gets a different tone than a high-energy single
Output
Provide 2-3 versions at different tones or lengths. Label each by platform or approach (e.g., "Instagram — story-driven," "Instagram — direct announcement," "Twitter/X"). Let the artist choose.
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.
- 6d ago First seen · 49 lines · 61 tokens per session scan A 94c04f8cbb3a
social-post is a skill published in the GitHub repository conorbronsdon/agent-context-os (22 stars, last pushed yesterday), licensed MIT. It adds 61 tokens to every session and 576 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 2026-08-30.
Other skills, from other repositories
pace-bridge
Use to bridge a confirmed Superpowers/native plan into PACEflow CHG/HOTFIX artifacts, create artifact-writer prompts, and mark the specific plan as synced.
pace-knowledge
Use for PACEflow knowledge/thoughts notes, finding-to-knowledge extraction, correction knowledge links, and Obsidian frontmatter/L0-L2 note structure.
platform-specific-paths
Generic browser automation skill with Windows-only paths scanned from another operating system.
handoff
Create, validate, list, and load local Portable Handoff capsules for context transfer, continuing work in a new chat, compacting current work, or loading prior work. Use whenever the user asks for a handoff, context transfer, continuation briefing, or portable work-state summary.
session-review
End-of-session adversarial review loop. Assemble the session's work into a role-assigned, self-contained brief, then run independent reviewers in parallel — an isolated code-reader (the idea-validator agent) that reads the ACTUAL files and web-checks technology currency, plus an external-family model if you have one …
second-opinion
Cross-check the agent's own answer with independent reviewers before bringing it to the user. Use when the user says 'second opinion', 'sanity check', 'cross-check', 'am I missing something', 'stress-test', 'devil's advocate', 'run a full review', 'this is important', 'high-stakes', 'help me choose between', 'critique…