transform

A method for converting data between formats or schemas, such as JSON, YAML, XML, or CSV. It records which information is preserved, changed, or lost.

In plain words
What is it for?
Use it to reformat data, map fields between schemas, normalize inputs, preserve unknown fields when needed, and validate the result.
Why use it?
It reduces errors when data from one structure must fit another and exposes unclear or missing field mappings.

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

Made for: Claude Code, Codex.

Per session 37 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,344 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 $0.00037 $0.02344
Opus 5 $0.00018 $0.01172
Sonnet 5 $0.00007 $0.00469
Haiku 4.5 $0.00004 $0.00234

Measured 2d ago against content hash 6d3df009b969, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

transform 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/transform/SKILL.md · 325 lines

How it starts

The opening of the file, as written. The whole thing — 325 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Intent

Transform data from one format or schema to another while tracking what information is preserved, modified, or lost during conversion. Ensure output conforms to target schema with full provenance.

Success criteria:

  • Output conforms to target schema
  • All fields mapped correctly or explicitly marked as lost
  • Transformation is deterministic and reproducible
  • Loss/distortion explicitly documented
  • Evidence anchors trace source to output

Compatible schemas:

  • schemas/output_schema.yaml

Inputs

Parameter Required Type Description
source Yes string or object Input data to transform
target_schema Yes string or object Schema or format specification for output
mapping No object Explicit field mappings (source -> target)
preserve_unknown No boolean Keep fields not in mapping (default: false)
strict No boolean Fail on any mapping ambiguity (default: false)
default_values No object Defaults for missing required fields

Procedure

  1. Parse source data: Load and validate input

    • Identify source format (JSON, YAML, XML, CSV, etc.)
    • Parse into internal representation
    • Detect encoding and special characters
    • Record source structure for provenance
  2. Analyze target schema: Understand destination requirements

    • Load target schema specification
    • Identify required vs optional fields
    • Note type constraints and validations
    • Map nested structures
  3. Build transformation map: Match source to target

    • Apply explicit mappings if provided
    • Infer mappings for matching field names
    • Identify fields requiring type conversion
    • Flag unmappable source fields
  4. Execute transformation: Apply mappings

    • Transform each field according to mapping
    • Apply type conversions (string to number, etc.)
    • Handle nested objects recursively
    • Apply default values for missing required fields

Read the full file on GitHub · 325 lines

Files

What ships with it

2 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 · 325 lines · 37 tokens per session scan A 6d3df009b969

Subscribe to this mod's changes

transform is a skill published in the GitHub repository synaptiai/agent-capability-standard (4 stars, last pushed 3d ago), licensed Apache-2.0. It adds 37 tokens to every session and 2,344 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.