noodle: Skill for Claude Code

.agents/skills/noodle-use/SKILL.md

noodle-use is a skill for Claude Code, Codex from wilfredinni/noodle. It costs 36 tokens per session (7,980 once invoked), scanned A, original, Apache-2.0.

A set of instructions for using Noodle, a terminal-based client for working with REST APIs. It stores API request collections, environments, and related settings in YAML and dotenv files.

In plain words
What is it for?
Use it to create or edit requests, folders, collections, and environments; run or validate collections; organize them; audit REST practices and security; import OpenAPI, Swagger, Postman, or Insomnia files; and convert cURL commands.
Why use it?
It helps automate API collections without manually editing every request or relying on unsupported commands. It also provides guidance for organizing, checking, importing, exporting, and converting collections.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: installed under .agents/ (shared by several agents).

This is wilfredinni/noodle's own configuration. It tells Claude Code and Codex how to work on noodle itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything noodle configures →

Needs its repository: it runs a file that does not travel with it, so clone the repository first. The line is noodle collection run ./my-api --data ./data/users.csv.

Reuse

Borrowing it

Nothing to install: this file belongs to wilfredinni/noodle. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/wilfredinni/noodle/main/.agents/skills/noodle-use/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/wilfredinni/noodle

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for noodle-use

README.md
[![agentmods](https://agentmods.dev/badge/skills/wilfredinni/noodle/noodle-use/github.svg)](https://agentmods.dev/skills/wilfredinni/noodle/noodle-use)
Your own site
<a href="https://agentmods.dev/skills/wilfredinni/noodle/noodle-use"><img src="https://agentmods.dev/badge/skills/wilfredinni/noodle/noodle-use/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.

agentmods 80×15 button for noodle-use

Your own site · 80×15
<a href="https://agentmods.dev/skills/wilfredinni/noodle/noodle-use"><img src="https://agentmods.dev/badge/skills/wilfredinni/noodle/noodle-use.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 36 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 7,980 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector warn 7 Sept 2026
SkillSpector: 2 findings, up to high

These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →

  • high Privilege Escalation · line 92
    Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.
    Fix: Remove references to credential paths. Use environment variables or secrets managers. For docs, use placeholder paths (e.g., /path/to/config). Never load .env or token files in production code paths.
  • medium Rogue Agent · line 23
    Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.
    Fix: Remove any persistence mechanisms (cron jobs, startup scripts, state files). Skills should not maintain state across sessions without explicit user consent.
How audits are shown
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 5.1 $0.00036 $0.07980
Opus 5.5 $0.00014 $0.03192
Sonnet 5.5 $0.00007 $0.01596
Haiku 4.5 $0.00004 $0.00798

Measured today against content hash e405ec57e09b, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

noodle-use 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 today.

The scan reads SKILL.md. This mod also ships 1 executable file (noodle-script.d.ts), 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.

.agents/skills/noodle-use/SKILL.md · 430 lines

How it starts

The opening of the file, as written. The whole thing — 430 lines — stays where its author put it; the contents beside it link to each section on GitHub.

noodle-use

Terminal REST client. YAML files on disk. Dotenv environments. Prefer supported non-interactive automation commands; use file-level operations for richer collection edits. No Bun dependency.

Collection setup and teardown

Collection settings.yml can reference one saved setup request and one saved teardown request:

hooks:
  setup: auth/login
  teardown: auth/logout

Either field is optional. IDs are collection-relative request paths without .yml; they must exist and must be different. Configure them in Collection Settings > General, or edit settings.yml. CLI collection run and the TUI Runner use the same settings. Manual sends and request run do not automatically run hooks.

The runner resolves references and preflights applicable script/test sources before HTTP, then runs setup, selected main requests in collection order, and teardown. Each stage uses the normal request lifecycle, including inherited collection/folder/request scripts and tests. Targets and tags select only main requests; hook requests are excluded from that selection and run once in their assigned stage. When no main requests remain, no stage sends HTTP.

A failed setup skips main requests with reason setup-failed and still attempts teardown. Ordinary failures and fail-fast also attempt teardown for the current row. Teardown records its own outcome without replacing earlier failures. Fail-fast prevents later dataset rows from starting. Explicit cancellation aborts active work and does not start teardown or other requests; HTTP effects already sent cannot be undone.

With CSV/JSON data, the sequence runs once per row. Setup, main requests, and teardown share that row's RunScope and cookie jar; the next row gets a fresh scope and a transient copy of the initial cookie jar. Runner persistence remains suppressed. Configured delays apply between executed stages. Hooks count toward execution limits and progress totals. Results, skips, progress events, summaries, and TUI details identify setup, main, or teardown; collections without hooks retain their existing result shapes.

Read the full file on GitHub · 430 lines

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. today Changed · +2 lines e405ec57e09b
  2. 3d ago Changed · +20 lines b5ba16fec9cd
  3. 13d ago Changed 7fe869b5b8be
  4. 19d ago Changed 8e0aeff21752
  5. 24d ago Changed 9aeb8d3ef828
  6. 1mo ago Changed · +2 lines cba352f2a018
  7. 1mo ago Changed · +1 lines b23e5c85936c
  8. 1mo ago Changed · +19 lines 4e40ab713c57
  9. 1mo ago Changed 1f1c614c2429
  10. 1mo ago First seen · 386 lines · 36 tokens per session scan A 9c573eda8b00

Subscribe to this mod's changes

noodle-use is a skill published in the GitHub repository wilfredinni/noodle (401 stars, last pushed today), licensed Apache-2.0. It adds 36 tokens to every session and 7,980 once invoked, about $0.0001 per session on Opus 5.5. 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 2026-08-30.

Related

noodle-use compared with skills from other repositories

noodle-use next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
noodle-usewilfredinni/noodleSkill401todayApache-2.0A36Claude Code, Codex
api-designericrisco/rsc-harnessSkill5032d agoMITA105Claude Code, Codex
update-api-documentationtarlepp/symfony-flex-backendSkill288yesterdayMITA36Claude Code, Codex
update-api-response-contracttarlepp/symfony-flex-backendSkill288yesterdayMITA31Claude Code, Codex
update-symfony-recipestarlepp/symfony-flex-backendSkill288yesterdayMITA32Claude Code, Codex
add-api-dto-mappingtarlepp/symfony-flex-backendSkill288yesterdayMITA38Claude Code, Codex
add-doctrine-querytarlepp/symfony-flex-backendSkill288yesterdayMITA31Claude Code, Codex