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 agentmods add skills/sonichi/sutando/answer-formatnpx skills add sonichi/sutando --skill answer-formatgit clone --depth 1 https://github.com/sonichi/sutandoWhat 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 | $0.00000 | $0.00520 |
| Opus 5 | $0.00000 | $0.00260 |
| Sonnet 5 | $0.00000 | $0.00104 |
| Haiku 4.5 | $0.00000 | $0.00052 |
Grade A, and why
answer-format scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 3d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 33 lines — stays where its author put it; the contents beside it link to each section on GitHub.
answer-format
Deterministic final-answer normalizer — a last-step pass for any task that ends in a precise answer (a number, a short string, a comma-list). Applies the formatting conventions graders and downstream consumers expect without changing meaning.
Usage:
python3 skills/answer-format/scripts/normalize.py --kind number -- "100 million" # -> 100000000
python3 skills/answer-format/scripts/normalize.py --kind list --sort -- "b, a, c" # -> a, b, c
echo " \"Paris\" " | python3 skills/answer-format/scripts/normalize.py --kind string # -> Paris
Or import it:
from normalize import normalize_answer
normalize_answer("100 million", kind="number") # "100000000"
What it does
| kind | transforms (all lossless or pattern-gated) |
|---|---|
number |
worded magnitude → digits (3.5 billion→3500000000); strip thousands separators (1,234→1234); strip a single leading currency ($/€/£/¥) 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.
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.
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.
- 3d ago First seen · 33 lines · 0 tokens per session scan A 1cf49eeaa03e
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.
Other skills, from other repositories
contacts
Manage contacts, communication channels, access control, and invite links.
gmail
Manage Gmail email — drafting, sending, organizing, filters, vacation replies, and inbox analysis.
app-builder
Build and edit small, personal visual tools and artifacts — dashboards, trackers, calculators, data visualizations, charts, simple landing pages, and slide decks the user wants for THEMSELVES. This is the right skill whenever the user asks to "visualize this," "make a chart," or "build an artifact" for their own use…
assistant-migration
Migrate from ChatGPT, Claude, OpenClaw, Hermes, Manus, and other AI assistants into Vellum by inspecting their data exports, conversation archives, files, prompts, custom instructions, memory, saved memories, tools, GPTs, workflows, integrations, and relationships, then mapping as much as safely possible into Vellum…
guardian-verify-setup
Set up channel verification for phone, Telegram, Slack, Discord, or email channels via outbound verification flow.
media-processing
Ingest and process media files (video, audio, image).