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 skills add HLND2T/CS2_VibeSignatures --skill create-agent-skill-fallbackgit clone --depth 1 https://github.com/HLND2T/CS2_VibeSignaturesWrote 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/hlnd2t/cs2_vibesignatures/create-agent-skill-fallback)<a href="https://agentmods.dev/skills/hlnd2t/cs2_vibesignatures/create-agent-skill-fallback"><img src="https://agentmods.dev/badge/skills/hlnd2t/cs2_vibesignatures/create-agent-skill-fallback/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/hlnd2t/cs2_vibesignatures/create-agent-skill-fallback"><img src="https://agentmods.dev/badge/skills/hlnd2t/cs2_vibesignatures/create-agent-skill-fallback.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 4 findings, 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 Agent Snooping · line 18 Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.Fix: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.
- medium Agent Snooping · line 114 Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.Fix: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.
- medium Agent Snooping · line 170 Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.Fix: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.
- medium Agent Snooping · line 340 Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.Fix: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.
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 | $0.00185 | $0.05401 |
| Opus 5.5 | $0.00074 | $0.02160 |
| Sonnet 5.5 | $0.00037 | $0.01080 |
| Haiku 4.5 | $0.00018 | $0.00540 |
Grade A, and why
create-agent-skill-fallback 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 2mo 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 — 357 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Create an Agent SKILL.md Fallback for a Finder
Given a target find-XXXX finder whose preprocessor uses a fragile foundation (most often LLM_DECOMPILE),
author .claude/skills/find-XXXX/SKILL.md — the Agent fallback that ida_analyze_bin.py runs only when the
preprocessor returns failure. The preprocessor stays as-is; this skill adds a durable backstop beside it.
This is the robustness-oriented sibling of /convert-finder-skill-to-preprocessor-scripts (that skill turns a
SKILL.md into a preprocessor; this one gives a preprocessor a SKILL.md fallback).
When to Use
- A
find-XXXXfinder failed on a new game version because a member/vfunc/function was inlined or de-inlined relative to what its LLM_DECOMPILE reference expects (classic symptom: one target in a multi-target-decompilesskill can no longer be found, aborting the module). - You want to pre-emptively backstop an LLM_DECOMPILE-based finder (patterns C/D/E) whose correctness hinges on a predecessor keeping a fixed decompiled shape.
- The recipe also applies to xref-string / found_call / index-based finders — the foundation differs, but the same "self-contained, skip-existing, anchor semantically, follow the callee" method holds.
Do not use this to replace a working preprocessor. The fallback is a safety net; the preprocessor remains the fast path.
The one constraint that drives the whole design
When the preprocessor fails, agent_runner.run_skill launches the agent with a prompt of only
/{skill_name} (see _build_claude_command, profile sig-finder). The skill's expected_yaml_paths is used
only for post-run missing-file verification (_missing_expected_outputs / _result_failure_reason) — it is
never injected into the prompt, and the missing list is not fed back to the agent on retry.
Consequence: the fallback SKILL.md you generate MUST be fully self-contained. It must enumerate every output, gate each by platform, and tell the agent to skip outputs whose YAML already exists (the preprocessor may have written most of them before failing; earlier fallback skills may have written others).
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.
- 2mo ago Changed · -2 lines 75ce7153f74e
- 2mo ago First seen · 359 lines · 185 tokens per session scan A 5f8a8cd18b43
create-agent-skill-fallback is a skill published in the GitHub repository HLND2T/CS2_VibeSignatures (67 stars, last pushed today), licensed MIT. It adds 185 tokens to every session and 5,401 once invoked, about $0.0007 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.
create-agent-skill-fallback compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| create-agent-skill-fallbackHLND2T/CS2_VibeSignatures | Skill | 67 | today | MIT | A | 185 | Claude Code, Codex |
| systematic-debuggingopen-metadata/OpenMetadata | Skill | 16k | yesterday | Apache-2.0 | A | 37 | Claude Code |
| log-error-digestzebbern/claude-code-guide | Skill | 4.7k | 3d ago | MIT | A | 71 | Claude Code, Codex |
| cwv-optimizeradobe/skills | Skill | 319 | yesterday | Apache-2.0 | A | 112 | Claude Code |
| ci-fixersipyourdrink-ltd/bernstein | Skill | 1.2k | yesterday | Apache-2.0 | A | 15 | Claude Code, Codex |
| incident-response-incident-responsermyndharis/antigravity-skills | Skill | 1.9k | 23d ago | MIT | A | 36 | Claude Code |
| triaging-web-analytics-supportPostHog/posthog | Skill | 41k | yesterday | none | A | 151 | Claude Code, Codex |