classify

A skill for assigning one or more labels to an item using a defined set of categories, called a taxonomy. It can use evidence, confidence, and ambiguity when deciding labels.

In plain words
What is it for?
Use it to categorize content, tag entities, identify types, or apply single- or multi-label classifications.
Why use it?
It provides a consistent way to sort documents, code, data, or other items instead of labeling them ad hoc.

Skill for Claude CodeCodex

Install

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.

agentmods
npx agentmods add skills/synaptiai/agent-capability-standard/classify
Any agent
npx skills add synaptiai/agent-capability-standard --skill classify
Clone the repo
git clone --depth 1 https://github.com/synaptiai/agent-capability-standard

Made for: Claude Code, Codex.

Per session 33 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,452 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00033 $0.01452
Opus 5 $0.00016 $0.00726
Sonnet 5 $0.00007 $0.00290
Haiku 4.5 $0.00003 $0.00145

Measured 2d ago against content hash c6280111dc67, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

classify 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 2d 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.

skills/classify/SKILL.md · 204 lines

How it starts

The opening of the file, as written. The whole thing — 204 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Intent

Assign one or more labels from a defined taxonomy to items based on their observed characteristics. This capability bridges detection and reasoning by providing semantic categorization.

Success criteria:

  • Item assigned at least one label from taxonomy
  • Label assignment supported by evidence
  • Confidence scores reflect classification certainty
  • Ambiguous cases explicitly flagged

Compatible schemas:

  • schemas/output_schema.yaml

Inputs

Parameter Required Type Description
item Yes any The item to classify (entity, document, code, data)
taxonomy No string|array Classification scheme or list of valid labels
multi_label No boolean Whether multiple labels can be assigned (default: false)
context No object Additional context to inform classification

Procedure

  1. Examine the item: Gather characteristics relevant to classification

    • Identify distinguishing features
    • Note structural patterns, content type, metadata
    • Collect evidence for each observed characteristic
  2. Understand the taxonomy: Clarify the classification scheme

    • If taxonomy provided, use those labels exclusively
    • If no taxonomy, infer appropriate categories from context
    • Define clear boundaries between categories
  3. Match characteristics to labels: Evaluate fit for each potential label

    • Score how well item characteristics match each category
    • Consider edge cases and borderline classifications
    • Note which features drive each potential classification
  4. Assign labels: Select the most appropriate label(s)

    • For single-label: choose highest confidence match
    • For multi-label: include all labels above confidence threshold
    • Flag if no label is a strong match
  5. Ground classification: Document evidence supporting each label

    • Reference specific characteristics that drove classification
    • Note any characteristics that contradict the assignment

Read the full file on GitHub · 204 lines

Files

What ships with it

5 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.

Changes

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.

  1. 2d ago First seen · 204 lines · 33 tokens per session scan A c6280111dc67

Subscribe to this mod's changes

classify is a skill published in the GitHub repository synaptiai/agent-capability-standard (4 stars, last pushed 2d ago), licensed Apache-2.0. It adds 33 tokens to every session and 1,452 once invoked, about $0.0002 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.

Related

Other skills, from other repositories

write-unit-tests

Writing unit and integration tests for the tldraw SDK. Use when creating new tests, adding test coverage, or fixing failing tests in packages/editor or packages/tldraw. Covers Vitest patterns, TestEditor usage, and test file organization.

aisa-group/skill-inject · 53 tokens

hugging-face-dataset-creator

Create and manage datasets on Hugging Face Hub. Supports initializing repos, defining configs/system prompts, and streaming row updates. Designed to work alongside HF MCP server for comprehensive dataset workflows.

aisa-group/skill-inject · 44 tokens

design-taste

Stops AI from generating boring, generic UI. Use when building new interfaces, reviewing generated UI, or fixing the flat / generic look that AI tools default to. Anti-slop design principles for premium frontends.

KeyArgo/custodian-kernel · 46 tokens

false-green-audit

Hunt for the failure this project exists to prevent — code that compiles, types, tests green, and quietly reports "all clear" about something it never examined. Use when reviewing a release, auditing a subsystem, or before tagging.

guardana/guardana · 53 tokens

scope-discipline

Keep one task closed-looped before starting the next. Triggered when a new problem surfaces mid-task (a bug, a security finding, a missing env var), when you're about to branch into unrelated work, or when you notice the session has sprawled across many half-finished threads. Prevents the "nothing ever lands" failure…

IgorGanapolsky/ThumbGate · 82 tokens

agentfootprint

Use when building AI agents with agentfootprint — LLMCall, Agent, skills, RAG, memory, control flow, Swarm concepts, mock/anthropic/openai/ollama providers, tools, recorders, resilience, and streaming. Also use when someone asks how agentfootprint works or wants to understand the framework.

footprintjs/agentfootprint · 72 tokens