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 filestack/filestack-claude-plugin --skill filestack-intelligencegit clone --depth 1 https://github.com/filestack/filestack-claude-pluginWrote 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/filestack/filestack-claude-plugin/filestack-intelligence)<a href="https://agentmods.dev/skills/filestack/filestack-claude-plugin/filestack-intelligence"><img src="https://agentmods.dev/badge/skills/filestack/filestack-claude-plugin/filestack-intelligence/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/filestack/filestack-claude-plugin/filestack-intelligence"><img src="https://agentmods.dev/badge/skills/filestack/filestack-claude-plugin/filestack-intelligence.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 | $0.00133 | $0.01522 |
| Opus 5 | $0.00067 | $0.00761 |
| Sonnet 5 | $0.00027 | $0.00304 |
| Haiku 4.5 | $0.00013 | $0.00152 |
Grade A, and why
filestack-intelligence 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 — 116 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Filestack Intelligence
Filestack exposes AI/ML capabilities as CDN transformation tasks that take a file handle and return JSON. They are backed by AWS Rekognition, Google Cloud Vision, AWS Comprehend/Transcribe, PicScout (copyright), and proprietary models.
Use filestack_analyze to invoke them — one tool, one task param.
Tasks
| Task | Input | Output | Backed by | Use case |
|---|---|---|---|---|
tags |
image handle | { tags: { auto: { keyword: confidence } } } |
AWS Rekognition + Google Vision (best-of-both) | Auto-tagging for search/discovery |
sfw |
image handle | { sfw: boolean } (true = safe) |
AWS Rekognition moderation labels | User-generated content moderation |
caption |
image handle | { caption: "a photo of a..." } |
Vision-language model | Auto alt-text, accessibility, content description |
ocr |
image / PDF handle | { text: "...", confidence, blocks: [...] } |
Google Cloud Vision OCR | Receipts, invoices, signage, document digitization |
copyright |
image handle | { copyright: boolean, matches: [...] } |
PicScout / Getty Images | Detect stock photos / IP violation before publishing |
doc_detection |
photo of a document | { detected: boolean, corners?: [[x,y]...] } |
Proprietary model | Mobile scanning UX — detect doc edges in a phone photo |
image_sentiment |
image handle (with faces) | { sentiment: "positive|neutral|negative", confidence } |
AWS Rekognition emotions | Detect mood / engagement in user photos |
text_sentiment |
text string (no handle) | { sentiment, confidence, language } |
AWS Comprehend | Analyze captions, comments, reviews |
Choosing the right task
- Moderation pipeline (UGC platforms): chain
sfwthentags. Ifsfw=false, reject; ifsfw=truebut tags contain words like "weapon" / "violence", flag for review. - Alt-text / accessibility:
caption— single natural-language sentence. - Search/categorization:
tags— gives you 20-50 keywords with confidence scores. - Compliance (stock photo enforcement, DMCA risk):
copyrightbefore allowing user uploads to be displayed publicly. - Mobile doc scanner:
doc_detectionreturns corners; combine withpartial_pixelateon sensitive regions. - Reviews / comments analysis:
text_sentiment— no file needed, pass the text directly.
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 · 116 lines · 133 tokens per session scan A ae971aedb350
filestack-intelligence is a skill published in the GitHub repository filestack/filestack-claude-plugin (3 stars, last pushed 2d ago), licensed MIT. It adds 133 tokens to every session and 1,522 once invoked, about $0.0007 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 2026-08-31.
Other skills, from other repositories
instrument-data-to-allotrope
Convert laboratory instrument output files (PDF, CSV, Excel, TXT) to Allotrope Simple Model (ASM) JSON format or flattened 2D CSV. Use this skill when scientists need to standardize instrument data for LIMS systems, data lakes, or downstream analysis. Supports auto-detection of instrument types. Outputs include full…
exploratory-data-analysis
Perform bounded, local exploratory analysis of explicitly supported scientific files. Use for redacted CSV/TSV/JSON profiles; optional NumPy, HDF5, FASTA/FASTQ, and basic image metadata inspection; missingness/leakage audits; outlier and transformation sensitivity; and rigorous EDA report scaffolds. Other domain…
matlab
Build, review, migrate, and safely plan MATLAB or GNU Octave numerical workflows, including arrays, tabular/time data, tests, projects, graphics, MAT files, and explicit Python interoperability.
phylogenetics
Build and analyze phylogenetic trees using MAFFT (multiple alignment), IQ-TREE 2 (maximum likelihood), and FastTree (fast NJ/ML). Visualize with ETE3 or FigTree. For evolutionary analysis, microbial genomics, viral phylodynamics, protein family analysis, and molecular clock studies.
research-engineer
An uncompromising Academic Research Engineer. Operates with absolute scientific rigor, objective criticism, and zero flair. Focuses on theoretical correctness, formal verification, and optimal implementation across any required technology.
mapping-to-snomed
Maps clinical concept spans extracted by OpenMed to SNOMED CT concepts through a USER-SUPPLIED terminology server (the user's own Ontoserver, Snowstorm, or UMLS/UTS), never a bundled vocabulary. Use when the user wants to code findings, disorders, procedures, body structures, or substances to SNOMED CT, run an ECL…