Borrowing it
Nothing to install: this file belongs to bex-co/bex. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/bex-co/bex/main/.claude/skills/routine-crash-fuzzer/SKILL.mdgit clone --depth 1 https://github.com/bex-co/bexWrote 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.
[](https://agentmods.dev/skills/bex-co/bex/routine-crash-fuzzer)<a href="https://agentmods.dev/skills/bex-co/bex/routine-crash-fuzzer"><img src="https://agentmods.dev/badge/skills/bex-co/bex/routine-crash-fuzzer/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.
<a href="https://agentmods.dev/skills/bex-co/bex/routine-crash-fuzzer"><img src="https://agentmods.dev/badge/skills/bex-co/bex/routine-crash-fuzzer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 5 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 34 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.
- high Privilege Escalation · line 35 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.
- high Privilege Escalation · line 36 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.
- high Privilege Escalation · line 35 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 Excessive Agency · line 15 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00087 | $0.01537 |
| Opus 5 | $0.00044 | $0.00768 |
| Sonnet 5 | $0.00017 | $0.00307 |
| Haiku 4.5 | $0.00009 | $0.00154 |
Grade A, and why
routine-crash-fuzzer 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 4d 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 — 66 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Routine: Crash Fuzzer
Find crashes from two evidence sources — live platform service logs first (real crashes beat hypothetical ones), then Go native fuzzing of untrusted-input parsers — and fix each at its root cause.
Routine ground rules
- A user request to run this routine authorizes the full cycle: plan, fix, verify, then invoke
$ship(Codex) or/ship(Claude) directly in the same run. Honor explicit user limits such as audit-only or no-ship. - Keep a concise execution plan in the conversation and update it as findings are confirmed. Continue into implementation without a planning approval pause. Do not create or file a
.pmmilestone/task as a prerequisite or substitute for fixing; use the board only if the user requests it. - After the verification phase, follow the shipping phase below without asking the user to invoke ship separately. Preserve the ship skill's branch, conflict-resolution, and safety rules.
- Fix everything you find directly in the working tree. If a fix can't be finished safely in this run, revert only your partial work for that fix and list it under Deferred in the report — never leave the tree half-refactored.
- Scope: parse
$ARGUMENTSper Phase 1 — an optional path/module scope or skill-specific target. No argument = the skill's stated default (usually the whole repo via parallel agents per module: lego/types, lego/operator, lego/backend, lego/cli, dashboard). - False-positive discipline: if a finding is intentional, load-bearing, or ambiguous, skip it with a one-line reason — don't argue it into a change.
- Every change must pass the verification gates for the modules it touched before being reported as done: operator
make test+make lint(fromlego/operator/),cd lego/backend && go test ./...,cd lego/cli && go test ./..., dashboardyarn test+ typecheck. - Run
npx [email protected] --writeon any markdown touched. - Before shipping, summarize results in commentary using: Fixed (file:line + one-line rationale) / Deferred (item + why) / Skipped (finding + reason) / Gates (commands run + outcomes).
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.
- 4d ago First seen · 66 lines · 87 tokens per session scan A 55d04fa24bb1
routine-crash-fuzzer is a skill published in the GitHub repository bex-co/bex (555 stars, last pushed today), licensed Apache-2.0. It adds 87 tokens to every session and 1,537 once invoked, about $0.0004 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 2026-09-05.
Other skills, from other repositories
network-rca
Kubernetes network root cause analysis skill powered by Kubeshark MCP. Use this skill whenever the user wants to investigate past incidents, perform retrospective traffic analysis, take or manage traffic snapshots, extract PCAPs, dissect L7 API calls from historical captures, compare traffic patterns over time, detect…
pinchtab-dev
Develop and contribute to the PinchTab project. Use when working on PinchTab source code, adding features, fixing bugs, running tests, or preparing PRs. Triggers on "work on pinchtab", "pinchtab development", "contribute to pinchtab", "fix pinchtab bug", "add pinchtab feature".
debugging-failures
Diagnose a failing Ginkgo suite as an agent — always run with --json-report into a predictable temp/gitignored location, read the terminal verdict line, then use jq to extract structured failure details (name, message, file:line, panic value, captured logs). Covers the panicked-vs-failed trap, panic locations pointing…
routing-calibration
Use when calibrating or validating a maintained routing recipe against live model backends, including probe manifests and evidence reports.
config-loader-helper
Diagnose configuration-related failures, enumerate required env vars, and guide safe local test setup (no secrets).
fix-suggester
Diagnose failures and propose minimal, test-backed fixes with verification and rollback instructions.