answer-format

A final formatting tool for answers that must follow an exact form, such as a number, short string, or comma-separated list. It applies fixed cleanup rules without changing the intended meaning.

In plain words
What is it for?
Use it to normalize written quantities into digits, clean quoted strings and whitespace, or format lists consistently.
Why use it?
It removes small formatting differences that can cause automated checks or downstream systems to reject an otherwise correct answer.

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/sonichi/sutando/answer-format
Any agent
npx skills add sonichi/sutando --skill answer-format
Clone the repo
git clone --depth 1 https://github.com/sonichi/sutando

Made for: Claude Code, Codex.

Per session 0 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 520 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 $0.00000 $0.00520
Opus 5 $0.00000 $0.00260
Sonnet 5 $0.00000 $0.00104
Haiku 4.5 $0.00000 $0.00052

Measured 3d ago against content hash 1cf49eeaa03e, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

answer-format 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 3d ago.

The scan reads SKILL.md. This mod also ships 1 executable file (scripts/normalize.py), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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/answer-format/SKILL.md · 33 lines

How it starts

The opening of the file, as written. The whole thing — 33 lines — stays where its author put it; the contents beside it link to each section on GitHub.

answer-format

Deterministic final-answer normalizer — a last-step pass for any task that ends in a precise answer (a number, a short string, a comma-list). Applies the formatting conventions graders and downstream consumers expect without changing meaning.

Usage:

python3 skills/answer-format/scripts/normalize.py --kind number -- "100 million"   # -> 100000000
python3 skills/answer-format/scripts/normalize.py --kind list --sort -- "b, a, c"   # -> a, b, c
echo "  \"Paris\"  " | python3 skills/answer-format/scripts/normalize.py --kind string  # -> Paris

Or import it:

from normalize import normalize_answer
normalize_answer("100 million", kind="number")   # "100000000"

What it does

kind transforms (all lossless or pattern-gated)
number worded magnitude → digits (3.5 billion3500000000); strip thousands separators (1,2341234); strip a single leading currency ($//£/¥) or trailing % when the rest is numeric
string trim whitespace; strip one layer of surrounding quotes; collapse internal whitespace; optionally drop a leading the/a/an (--drop-article) — interior words and capitalization untouched
list comma-separated, one space after each comma; per-element trim; optional case-insensitive sort (--sort) and per-element numeric normalization (--number-items)
auto (default) infer kind from shape, then apply the above

Design principle

Conservative. A normalizer that mangles a correct answer is worse than none, so every transform is either lossless or gated on a confident pattern; ambiguous input passes through unchanged. Sorting and article-dropping are opt-in because graders rarely want them.

Why

Precise answers routinely fail grading or downstream matching on format alone — "100 million" vs "100000000", "1,234" vs "1234", '"Paris"' vs Paris. This is a general capability (any task ending in an exact answer benefits); it also implements the final-format step of the agent-eval solver contract, where a single format miss cost a correct L3 answer.

Read the full file on GitHub · 33 lines

Files

What ships with it

1 file 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. 3d ago First seen · 33 lines · 0 tokens per session scan A 1cf49eeaa03e

Subscribe to this mod's changes

answer-format is a skill published in the GitHub repository sonichi/sutando (389 stars, last pushed 3d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 520 tokens. 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.