CS2_VibeSignatures: Skill for Claude Code

.claude/skills/run-validation-until-no-failure/SKILL.md

run-validation-until-no-failure is a skill for Claude Code, Codex from HLND2T/CS2_VibeSignatures. It costs 176 tokens per session (3,864 once invoked), scanned A, original, MIT.

A validation skill that repeatedly runs a program-analysis pipeline until it has no reported failures. It also investigates each failing analysis skill and waits for the user to choose how to handle it.

In plain words
What is it for?
It helps run IDA validation, explain the first failure, offer repair or temporary-disable options, and resume the checks after a decision.
Why use it?
It gives a structured way to deal with failing checks without silently disabling them or changing requirements. Infrastructure problems are surfaced separately from analysis problems.

Skill for Claude CodeCodex

Written for Claude Code and Codex: disable-model-invocation in frontmatter, but also agents/openai.yaml present.

This is HLND2T/CS2_VibeSignatures's own configuration. It tells Claude Code and Codex how to work on CS2_VibeSignatures 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 CS2_VibeSignatures configures →

Needs its repository: it runs a file that does not travel with it, so clone the repository first. The line is uv run python tests/run_test_suite.py unit -b --durations 30.

Reuse

Borrowing it

Nothing to install: this file belongs to HLND2T/CS2_VibeSignatures. 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/HLND2T/CS2_VibeSignatures/main/.claude/skills/run-validation-until-no-failure/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/HLND2T/CS2_VibeSignatures

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 run-validation-until-no-failure

README.md
[![agentmods](https://agentmods.dev/badge/skills/hlnd2t/cs2_vibesignatures/run-validation-until-no-failure/github.svg)](https://agentmods.dev/skills/hlnd2t/cs2_vibesignatures/run-validation-until-no-failure)
Your own site
<a href="https://agentmods.dev/skills/hlnd2t/cs2_vibesignatures/run-validation-until-no-failure"><img src="https://agentmods.dev/badge/skills/hlnd2t/cs2_vibesignatures/run-validation-until-no-failure/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 run-validation-until-no-failure

Your own site · 80×15
<a href="https://agentmods.dev/skills/hlnd2t/cs2_vibesignatures/run-validation-until-no-failure"><img src="https://agentmods.dev/badge/skills/hlnd2t/cs2_vibesignatures/run-validation-until-no-failure.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 176 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,864 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: 1 finding, up to medium

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 →

  • medium Excessive Agency · line 56
    Skill allows unbounded resource consumption (API calls, storage, compute). Without rate limits or quotas, a compromised or misbehaving agent can cause denial-of-service or cost overruns.
    Fix: Set explicit rate limits, timeouts, and resource quotas for API calls, file operations, and compute. Implement circuit breakers for runaway loops.
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 $0.00176 $0.03864
Opus 5 $0.00088 $0.01932
Sonnet 5 $0.00035 $0.00773
Haiku 4.5 $0.00018 $0.00386

Measured 10d ago against content hash 3dc5d9e8e108, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

run-validation-until-no-failure 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 10d 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/run-validation-until-no-failure/SKILL.md · 298 lines

How it starts

The opening of the file, as written. The whole thing — 298 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Run Validation Until No Failure

Loop the analysis/validation pipeline until it reports Failed: 0. Each iteration: run ida_analyze_bin.py -debug; if a skill failed (the pipeline is fail-fast, so it's exactly one), diagnose why, present several concrete resolution options, and ask the user which option to take. Do not disable or record the skill before the user answers. If the user explicitly answers that it cannot be solved now and asks to temporarily disable the skill, append the failure to docs/ida_validation_failure-<GAMEVER>.md, comment that skill out of configs/<GAMEVER>.yaml, and run the unit and repository-contract unittest suites before resuming validation. If the config dependency test reports consumers whose expected_input can no longer be produced, apply the same ask-before-action rule to each dependent skill. Environment / infrastructure failures are not skill bugs — STOP and surface those instead of quarantining a skill.

Resolve GAMEVER from the user's explicit request or CS2VIBE_GAMEVER; use only configs/$GAMEVER.yaml for the validation run and all quarantine edits.

When to Use

  • The user asks to "run validation until it passes / until no failures", "get validation green", or "disable the failing skills and keep going".
  • After bumping to a new game version or landing many new skills, to triage a wave of failures — each gets quarantined with its reason for later fixing.

Why the loop works (pipeline facts)

  • uv run ida_analyze_bin.py -debug ends with a summary and exits non-zero when Failed > 0:
    ============================================================
    Summary
    ============================================================
      Successful: N
      Failed: N
      Skipped: N
    
  • It is fully fail-fast: the first failing skill aborts the remaining skills, the remaining platforms, and the remaining modules. So each run surfaces exactly one actionable failing skill — handle at most one validation-failing skill per iteration.
  • Skills whose expected_output YAML already exist on disk are skipped on re-runs, so each iteration advances quickly to the next unresolved skill.

Read the full file on GitHub · 298 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. 10d ago First seen · 298 lines · 176 tokens per session scan A 3dc5d9e8e108

Subscribe to this mod's changes

run-validation-until-no-failure is a skill published in the GitHub repository HLND2T/CS2_VibeSignatures (65 stars, last pushed yesterday), licensed MIT. It adds 176 tokens to every session and 3,864 once invoked, about $0.0009 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

systematic-debugging

4-phase root cause debugging: understand bugs before fixing.

NousResearch/hermes-agent · 16 tokens

langsmith-observability

LLM observability platform for tracing, evaluation, and monitoring. Use when debugging LLM applications, evaluating model outputs against datasets, monitoring production systems, or building systematic testing pipelines for AI applications.

davila7/claude-code-templates · 45 tokens

experimental-code-coverage-local-debugger

Runs code coverage locally via Universal Test Runner (UTR) or helper scripts, mimicking LUCI trybots. Activate when CQ tryjobs fail or underreport coverage, to test local GN/recipe repairs before uploading, or to debug hermetic crashes.

chromium/chromium · 59 tokens

adversarial-reviewer

Adversarial code review that assumes bugs exist and hunts for them. Use when asked to review code, find bugs, audit for correctness, stress-test a PR, or when someone says "tear this apart" or "what's wrong with this". Give no benefit of the doubt — every line is guilty until proven innocent.

emdash-cms/emdash · 71 tokens

cli-e2e

Write, modify, or debug Docker-based Composio CLI end-to-end tests under ts/e2e-tests/cli, including binary invocation, fixture isolation, output assertions, and package manifests. Use for CLI E2E test suites only; use cli-command for CLI source implementation.

ComposioHQ/composio · 62 tokens

ios-simulator

Verify and debug native, React Native, Expo, or Flutter apps on an iOS Simulator with agent-device. Use when an agent needs to launch an app, inspect its live UI, tap, type, scroll, validate a code change, collect failure evidence, or reproduce a workflow on an iPhone or iPad Simulator.

callstack/agent-device · 69 tokens