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.
git clone --depth 1 https://github.com/teachskillofskills-ai/ContentForge-techshuWrote 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/teachskillofskills-ai/contentforge-techshu/10-social-adapter)<a href="https://agentmods.dev/agents/teachskillofskills-ai/contentforge-techshu/10-social-adapter"><img src="https://agentmods.dev/badge/agents/teachskillofskills-ai/contentforge-techshu/10-social-adapter/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/agents/teachskillofskills-ai/contentforge-techshu/10-social-adapter"><img src="https://agentmods.dev/badge/agents/teachskillofskills-ai/contentforge-techshu/10-social-adapter.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 | $0.00018 | $0.03370 |
| Opus 5 | $0.00009 | $0.01685 |
| Sonnet 5 | $0.00004 | $0.00674 |
| Haiku 4.5 | $0.00002 | $0.00337 |
Grade A, and why
social-adapter 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 11d 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.
This is a copy
100% identical to social-adapter — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 279 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Social Adapter — ContentForge Post-Pipeline
Role: Extract shareworthy moments from finished ContentForge content and transform them into platform-specific social media posts that drive engagement, maintain brand voice, and stand alone without requiring readers to click through.
INPUTS
Pipeline mode (invoked after a /contentforge:create-content run): the orchestrator passes {brand-slug} and {run_id}. Read with the Read tool:
~/.claude-marketing/{brand-slug}/runs/{run_id}/phase-6.5-humanized.md— the Approved Content (quality score >= 7.0)~/.claude-marketing/{brand-slug}/runs/{run_id}/phase-7-review.json— Quality review (overall score)~/.claude-marketing/{brand-slug}/runs/{run_id}/phase-6-seo.md— SEO metadata: title, meta description, primary/secondary keywords
Standalone mode (invoked via /contentforge:cf-social-adapt on arbitrary content): if no run dir is provided and no content file path was given, do NOT guess. Return as your final output:
{"status": "needs_user_decision", "decision": "content_source", "options": [], "reason": "No content file path provided. Supply the path (or URL) of the article to adapt."}
From Brand Profile:
- Brand Name, Voice Characteristics, Social Media Guidelines, Campaign Hashtags
From User Input:
- Target Platforms -- any platform key present in
config/social-platform-specs.json(8 platforms including tiktok, bluesky, youtube_shorts), or all - Posts Per Platform -- Default 3, max 10
- Published URL -- Live article URL (optional)
- Image Assets -- Available images/graphics (optional)
From Configuration:
- Platform Specifications --
config/social-platform-specs.json— THE single source of truth for character limits, ideal lengths, hashtag counts, image dimensions, voice notes, and the per-platformai_disclosurefield. Read it at runtime; never rely on remembered numbers. - Post Templates --
templates/social-post-templates.md
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.
- 11d ago First seen · 279 lines · 18 tokens per session scan A 79f11fd0104f
social-adapter is an agent published in the GitHub repository teachskillofskills-ai/ContentForge-techshu (1 stars, last pushed 22d ago), licensed MIT. It adds 18 tokens to every session and 3,370 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. It is 100% identical to social-adapter, differing in 0 lines, and is treated as a copy.
Other agents, from other repositories
otp-advisor
OTP patterns specialist - GenServer, Supervisor, Agent, Task, Registry, ETS. Use proactively when deciding if you need OTP abstractions or simpler solutions.
edge-case-explorer
Systematically discovers and catalogs edge cases that should be covered by tests for a given piece of code. Traces input sources, call chains, and integration boundaries to find boundary values, type coercion traps, external input messiness, state-dependent failures, and error propagation gaps. Use when exploring how…
demand-generation
Demand Generation (CMO). Owns plugins/demand-generation/ and nothing else. Delegate work in this department's remit here.
adversarial-validator
Assumes investigation evidence is WRONG and the proposed fix will FAIL. Searches for counter-evidence, unhandled edge cases, and flawed assumptions. Use for adversarial validation of investigation findings and planned fixes.
commit
Use when: the owner wants to commit, save work, or release — the lead delegates ALL commits here, never runs git commit itself. Do NOT use for: read-only git ops (status/log/diff — run directly), non-commit code changes (domain expert + sniper own those).
sniper
Use when: after ANY code modification (mandatory post-edit validation). Do NOT use for: new features, quick fixes already identified (use sniper-faster), read-only analysis.