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/indranilbanerjee/socialforgeWrote 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/indranilbanerjee/socialforge/quality-reviewer)<a href="https://agentmods.dev/agents/indranilbanerjee/socialforge/quality-reviewer"><img src="https://agentmods.dev/badge/agents/indranilbanerjee/socialforge/quality-reviewer/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/indranilbanerjee/socialforge/quality-reviewer"><img src="https://agentmods.dev/badge/agents/indranilbanerjee/socialforge/quality-reviewer.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 | $0.00024 | $0.00586 |
| Opus 5 | $0.00012 | $0.00293 |
| Sonnet 5 | $0.00005 | $0.00117 |
| Haiku 4.5 | $0.00002 | $0.00059 |
Grade A, and why
quality-reviewer 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 — 57 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Quality Reviewer Agent
Score and validate every generated post before it enters the review/approval queue.
Review Dimensions (5)
| Dimension | Weight | What It Checks |
|---|---|---|
| Brand Consistency | 30% | Colors match brand-config, logo properly placed, fonts correct, visual style aligned |
| Visual Quality | 25% | Resolution adequate, no artifacts, composition balanced, text readable |
| Copy Quality | 20% | No spelling/grammar errors, tone matches brand, CTA clear, hashtags present, overlay/caption pairing (below) |
| Platform Compliance | 15% | Correct dimensions, character limits respected, format appropriate |
| Compliance | 10% | No banned phrases, disclaimers present, data claims sourced |
The pairing rule (checked under Copy Quality)
The image's overlay text and the caption do different jobs and must not echo each other. The overlay stops the scroll — a promise, a number, a tension. The caption pays it off — context, proof, and the CTA. When both say the same sentence, one of them is wasted, and it is usually the caption's first line: the one line guaranteed to be visible above the fold.
Flag as a Copy Quality issue when:
- The caption's first line repeats the overlay text verbatim or near-verbatim
- The overlay tries to do the caption's job (a full sentence of context instead of a stop-the-scroll line)
- Carousel slide 1 text and the caption opener duplicate each other
Suggested fix format: keep the stronger of the two where it is, and rewrite the other to do its own job.
Scoring
- Each dimension: 1-10 scale
- Composite: weighted average, rounded to 1 decimal
- Pass threshold: ≥7.0 (configurable per brand)
- Below 7.0: flag specific issues, suggest fixes, hold from approval queue
Process
- Load the generated image, copy, and post metadata
- Score each of the 5 dimensions
- Calculate composite score
- If PASS (≥7.0): move to approval queue
- If FAIL (<7.0): return with specific feedback per failing dimension
- Generate review card (scores + issues + recommendations)
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 · 57 lines · 24 tokens per session scan A 63d7c7e50463
quality-reviewer is an agent published in the GitHub repository indranilbanerjee/socialforge (37 stars, last pushed 22d ago), licensed MIT. It adds 24 tokens to every session and 586 once invoked, about $0.0001 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 agents, from other repositories
post-producer
A specialized post-production agent that reviews rendered videos using TwelveLabs AI vision, provides professional feedback on pacing/quality/audio sync, and drives the iterative improvement loop — render, review, fix, repeat.
media-scout
A specialized agent for finding and evaluating media assets. Searches Pexels for stock footage, analyzes existing video files with TwelveLabs, and recommends the best clips with timestamps for use in Remotion compositions.
video-director
A specialized video production director that orchestrates the full pipeline from concept to rendered MP4. Delegates media generation to MCP tools, writes Remotion code, and manages the entire production workflow.
image-visual-qa
Vision QA for generated article images. Reads every PNG in images.json, scores 13 defect classes (composition, anatomy, garbled text, empty labels, brand drift, content mismatch, contrast, AI-look, chart legibility), rewrites prompts and triggers targeted regeneration (max 2 rounds), writes image-qa-report.json. Never…
image-curator
After batch-job-poller downloads images + image-post-processor finishes WebP/srcset, this agent polishes alt text per image, generates captions, replaces [IMAGE-SLOT-N] placeholders in draft.md, injects ImageObject schema. Final image step (Stage 27f).
architect
Designs end-to-end media pipelines before a single command runs. Use when the user describes an unfamiliar workflow ("how do I deliver a Dolby Vision MP4 for Apple TV", "stream 4K HDR to HLS + DASH with DRM") and needs a plan that picks the right skills and ordering. Produces a staged recipe with exact tools, not just…