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 Benja-Pauls/SerpentStack --skill generate-skillsgit clone --depth 1 https://github.com/Benja-Pauls/SerpentStackWrote 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/benja-pauls/serpentstack/generate-skills)<a href="https://agentmods.dev/skills/benja-pauls/serpentstack/generate-skills"><img src="https://agentmods.dev/badge/skills/benja-pauls/serpentstack/generate-skills/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/benja-pauls/serpentstack/generate-skills"><img src="https://agentmods.dev/badge/skills/benja-pauls/serpentstack/generate-skills.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 | $0.00066 | $0.01693 |
| Opus 5.5 | $0.00026 | $0.00677 |
| Sonnet 5.5 | $0.00013 | $0.00339 |
| Haiku 4.5 | $0.00007 | $0.00169 |
Grade A, and why
generate-skills 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 1mo 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 — 189 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Generate Project-Specific Skills
Analyze an existing codebase and interview the developer to produce project-specific Agent Skills (SKILL.md files) that teach IDE agents how to write code matching the project's conventions.
This skill works for ANY codebase — not just SerpentStack. The output is a .skills/ directory following the Agent Skills open standard (agentskills.io).
When to Use
- The user has an existing project and wants agents to understand their conventions
- The user says "generate skills," "create skills for my project," or "make my agent understand my codebase"
- The user wants a
.skills/directory for a project that doesn't have one
Phase 1: Codebase Discovery
Before asking questions, read the codebase to come prepared. Reduce burden on the developer by finding answers yourself first.
- Read project structure:
ls -Rorfind . -type f -name "*.py" -o -name "*.ts" -o -name "*.js" | head -50 - Read config files:
package.json,pyproject.toml,Cargo.toml,go.mod,Makefile,docker-compose.yml - Read existing context files:
.cursorrules,CLAUDE.md,.github/copilot-instructions.md,CONTRIBUTING.md - Read 2-3 representative source files: a model/entity, a service/controller, a test file, a route/handler
- Read the test setup:
conftest.py,jest.config,vitest.config, test fixtures
From this, form hypotheses about:
- Language, framework, and major dependencies
- Project structure (where models, services, routes, tests live)
- Transaction/database patterns
- Auth approach
- Test infrastructure
- API patterns (REST, GraphQL, RPC)
- Frontend patterns (if applicable)
Phase 2: Developer Interview
Use AskUserQuestion to confirm hypotheses and uncover conventions that aren't visible in code. Ask 5-8 rounds of questions. Do not ask obvious questions — you already read the code. Ask about the WHY and the EDGE CASES.
Round 1: Confirm Architecture
Present what you found and ask for corrections:
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.
- 1mo ago First seen · 189 lines · 66 tokens per session scan A 24251a5b17e2
generate-skills is a skill published in the GitHub repository Benja-Pauls/SerpentStack (2 stars, last pushed 6mo ago), licensed MIT. It adds 66 tokens to every session and 1,693 once invoked, about $0.0003 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 2026-08-31.
Other skills, from other repositories
feishu
Work with Feishu or Lark bots, docs, sheets, bitables, approval flows, and OpenAPI/MCP setup without hardcoding credentials.
interview
Ask one useful structured question at a time only when material product/implementation choices are genuinely missing; remember answers and produce a brief/spec. Discoverable facts should be investigated instead of asked.
recipe-create-meet-space
Create a Google Meet meeting space and share the join link.
refocusing
Use when a long-running agent may have lost the product outcome, when context was compacted, when work has crossed a major boundary, or when a fresh path-based trace is needed before the next consequential action. Not for fresh-session orientation, waking an idle seat, or checkpoints.
printing-press-import
Bring a published CLI from the public library into the internal library so it's identical to a freshly-generated copy — module path reverted, manuscripts placed alongside, ready for /printing-press-polish or /printing-press-emboss. Use when the public library has a CLI you don't have locally, or to recover from a…
atmos-validation
Validate Atmos projects, components, arbitrary JSON Schema inputs, EditorConfig, and GitHub Actions; use affected-file selection and native CI annotations.