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 takeaseatventure/devops-skills --skill env-drift-huntergit clone --depth 1 https://github.com/takeaseatventure/devops-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/skills/takeaseatventure/devops-skills/env-drift-hunter)<a href="https://agentmods.dev/skills/takeaseatventure/devops-skills/env-drift-hunter"><img src="https://agentmods.dev/badge/skills/takeaseatventure/devops-skills/env-drift-hunter/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/takeaseatventure/devops-skills/env-drift-hunter"><img src="https://agentmods.dev/badge/skills/takeaseatventure/devops-skills/env-drift-hunter.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00113 | $0.02050 |
| Opus 5.5 | $0.00045 | $0.00820 |
| Sonnet 5.5 | $0.00023 | $0.00410 |
| Haiku 4.5 | $0.00011 | $0.00205 |
Grade C, and why
env-drift-hunter scanned grade C with 1 finding 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.
Enumerates the file system for secretshighData exfiltration
Searching home directories for .env, .ssh, .aws or credential files is reconnaissance for credential theft.
### Step 1: Find all .env files The source is not reproduced here
A licence we could not identify
The repository carries a LICENSE file, but it is custom or dual enough that GitHub cannot name it and neither can this catalogue. Unknown terms are not permission, so the body is not copied here. Read the licence at the source and decide for yourself.
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 First seen · 154 lines · 113 tokens per session scan C b0899ae3c84a
env-drift-hunter is a skill published in the GitHub repository takeaseatventure/devops-skills (2 stars, last pushed 3mo ago), with no licence file. It adds 113 tokens to every session and 2,050 once invoked, about $0.0005 per session on Opus 5.5. A static security scan graded it C with 1 finding (enumerates the file system for secrets). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
stage-refactor-checklist
Comprehensive checklist for refactoring a schemacompiler stage folder. Use EVERY TIME you refactor a compiler stage (resolve, unify, codegen, etc.). Read this before writing any code.
bugs
CTF-style security and correctness audit. Dispatches parallel Opus subagents to hunt for day-0 bugs in security-critical files. Each agent must find a real bug or honestly admit failure. Use when you want a thorough adversarial review of a codebase area.
invariant-first-coding
Reason from proven invariants before coding. Use when reviewing fallback logic, narrowing types, handling conversions, deciding whether an error path is real or impossible, removing overdefensive code, or when the user questions whether code is being too theatrical, too hedged, or not fail-closed enough.
postmortem
Run a blameless postmortem for a production incident. Investigate with data, write a structured report, build verification queries, and track remediation. Use when something broke in production, money was lost, users were affected, or a security issue was exploited.
simple
Frame any technical answer as a reproducible five-part diagnosis. Use when the user asks for a root-cause explanation, a fix proposal, a debugging write-up, or says "explain why", "what's the problem", "propose a fix", or invokes /simple. Forces the answer into: problem, evidence, proposal, mechanism, test methodology.
state-machine-dfa
Document state machines with mermaid diagrams and DFA transition files. Use when writing, reviewing, or adding state-driven logic to modules that have sequential phase transitions, lifecycle management, or protocol handshakes.