wings: Skill for Claude Code

.claude/skills/sec-fuzzing/SKILL.md

sec-fuzzing is a skill for Claude Code from luisfurquim/wings. It costs 67 tokens per session (906 once invoked), scanned A, original, MPL-2.0.

A guide to continuous fuzzing in Go, where automatically generated and often malformed inputs are repeatedly sent to parsers and decoders to find bugs.

In plain words
What is it for?
It is for fuzzing expression parsers, internationalization catalog tools, serializers and deserializers, signature verification, and locale or currency parsing, with corpus and CI-budget guidance.
Why use it?
It helps expose crashes, unsafe input handling, and data-corruption problems that ordinary example-based tests may miss.

Skill for Claude Code

Written for Claude Code: installed under .claude/.

This is luisfurquim/wings's own configuration. It tells Claude Code how to work on wings 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 wings configures →

Reuse

Borrowing it

Nothing to install: this file belongs to luisfurquim/wings. 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/luisfurquim/wings/main/.claude/skills/sec-fuzzing/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/luisfurquim/wings

Made for: Claude Code.

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 sec-fuzzing

README.md
[![agentmods](https://agentmods.dev/badge/skills/luisfurquim/wings/sec-fuzzing.svg)](https://agentmods.dev/skills/luisfurquim/wings/sec-fuzzing)
Your own site
<a href="https://agentmods.dev/skills/luisfurquim/wings/sec-fuzzing"><img src="https://agentmods.dev/badge/skills/luisfurquim/wings/sec-fuzzing.svg" alt="Measured on agentmods" height="20"></a>
Per session 67 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 906 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 pass 7 Sept 2026
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 $0.00067 $0.00906
Opus 5 $0.00034 $0.00453
Sonnet 5 $0.00013 $0.00181
Haiku 4.5 $0.00007 $0.00091

Measured 8d ago against content hash 427aca2e84f8, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

sec-fuzzing 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 8d 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.

.claude/skills/sec-fuzzing/SKILL.md · 71 lines

How it starts

The opening of the file, as written. The whole thing — 71 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Continuous Fuzzing (Go native)

djb minimized parsers because parsers are where bugs live; Apollo verified exhaustively because there was no patching after launch. Fuzzing is the modern tool that serves both: machine-generated hostile input, continuously, against every parser that survived minimization.

Where the parsers are (priority order)

Target Why Harness note
expr.ParseFlexBlock, expr.TokenizeFlexContent, expr.ParseReference, splitSymbols hand-written string parsers; webdev-authored input; the leniency/passthrough contract must hold for ALL inputs pure Go, fuzz natively
cmd/gen_i18n catalog align/remap (align.go: exact map + anchored Levenshtein) merges old+new catalogs; corruption here silently destroys translations fuzz the pure functions; fixture HTML via f.Add seeds
codec de/serialization classic round-trip target
wi18n catalog load + verify.go runtime-fetched JSON + ed25519 .sig; must refuse, never panic, on garbage structure as portable funcs if needed
wi18n/fmt*, currency parsing locale data → formatting

Go fuzzing runs on native targets only — another reason parsing logic stays in portable packages (expr/ already is; see sec-wasm-go).

Writing targets

func FuzzParseFlexBlock(f *testing.F) {
    f.Add("{{@gender %qt #0}}")            // seeds: real syntax from docs/demo
    f.Add("{{%qt *flexer ~$produto}}")
    f.Add("{{=cesta @gender %n}}")
    f.Fuzz(func(t *testing.T, s string) {
        blk, err := expr.ParseFlexBlock(s)  // property 1: never panics
        if err != nil { return }
        _ = blk.Render(...)                 // property 2: accepted input renders
    })
}

Properties worth asserting beyond "no panic":

  • Round-trip: tokenize → reassemble ≍ input (modulo documented space collapse in TokenizeFlexContent).
  • Fail-closed: for verify.go, a mutated body or sig NEVER verifies; flipping any byte of a known-good pair must yield an error.
  • Idempotence: running align/remap twice equals running it once (the restart-protection property from sec-fail-operational, made testable).
  • No index out of range: any catalog index arriving from fuzzed JSON is bounds-checked, returns error.

Read the full file on GitHub · 71 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. 8d ago First seen · 71 lines · 67 tokens per session scan A 427aca2e84f8

Subscribe to this mod's changes

sec-fuzzing is a skill published in the GitHub repository luisfurquim/wings (29 stars, last pushed 1mo ago), licensed MPL-2.0. It adds 67 tokens to every session and 906 once invoked, about $0.0003 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 2026-08-30.

Related

Other skills, from other repositories

research-engineer

An uncompromising Academic Research Engineer. Operates with absolute scientific rigor, objective criticism, and zero flair. Focuses on theoretical correctness, formal verification, and optimal implementation across any required technology.

davila7/claude-code-templates · 43 tokens

tika-eval-compare

Compare extracts from two Tika builds over a corpus to detect regressions in content, encoding, exceptions, and embedded-document handling. Use for "compare before/after extracts", "eval this change against the corpus".

apache/tika · 50 tokens

neuron-evaluation-engineer

Create and run AI evaluations with datasets, assertions, and output drivers in Neuron AI. Use this skill whenever the user mentions evaluation, testing AI systems, creating evaluators, dataset-driven testing, assertion-based validation, or wants to measure AI system performance. Also trigger for tasks involving…

neuron-core/neuron-ai · 77 tokens

jetson-validate-image

Use after jetson-flash-image to run static BSP checks, on-target smoke/regression tests on a flashed DUT, or both. Not for build or flash steps. Triggers: validate bsp, on-target validation.

NVIDIA/skills · 50 tokens

atmos-validation

Validate Atmos projects, components, arbitrary JSON Schema inputs, EditorConfig, and GitHub Actions; use affected-file selection and native CI annotations.

cloudposse/atmos · 31 tokens

skill-benchmark

Benchmark AI skill effectiveness by measuring implementation quality against legacy constraints.

HoangNguyen0403/agent-skills-standard · 16 tokens