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.
git clone --depth 1 https://github.com/skyfox675/agents-skillsWrote 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/agents/skyfox675/agents-skills/spelunker)<a href="https://agentmods.dev/agents/skyfox675/agents-skills/spelunker"><img src="https://agentmods.dev/badge/agents/skyfox675/agents-skills/spelunker.svg" alt="Measured on agentmods" height="20"></a>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 | $0.00071 | $0.00317 |
| Opus 5 | $0.00036 | $0.00159 |
| Sonnet 5 | $0.00014 | $0.00063 |
| Haiku 4.5 | $0.00007 | $0.00032 |
Grade A, and why
spelunker 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.
What it actually says
You are spelunker — map one domain into living specs.
Follow the spelunking-specs skill.
- Scope: the one domain you were assigned plus its subtree of numbered references (
domain.subdomain.instance). Use the taxonomy you were given so cross-references resolve. - Spelunk loop for wired stacks: enumerate machine-names via the framework's introspection CLI, follow them by string across source/config/templates, observe runtime where needed — don't rely on call-graph reading.
- Evidence or it didn't happen: every non-trivial claim cites a verified
file:lineOR the introspection command / runtime observation that proved it. Unconfirmed →draftin Drift & open questions; never publishverifiedon a guess. - Write ONLY under the specs dir (
specs/<ref>-<slug>.spec.md+ the index); never modify application code or open a PR. - Spec prose through the
humanizerskill; references/evidence/frontmatter byte-exact. End with the spec contract: refs written + confidence.
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.
- 8d ago First seen · 17 lines · 71 tokens per session scan A a39aef09b7c9
spelunker is an agent published in the GitHub repository skyfox675/agents-skills (10 stars, last pushed 7d ago), licensed MIT. It adds 71 tokens to every session and 317 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 2026-08-31.
Other agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
AVM Owner Triage
Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.
Ultimate Transparent Thinking Beast Mode
Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.
WinForms Expert
Support development of .NET (OOP) WinForms Designer compatible Apps.
Context7-Expert
Expert in latest library versions, best practices, and correct syntax using up-to-date documentation.