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 dev-servergit 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/dev-server)<a href="https://agentmods.dev/skills/benja-pauls/serpentstack/dev-server"><img src="https://agentmods.dev/badge/skills/benja-pauls/serpentstack/dev-server/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/dev-server"><img src="https://agentmods.dev/badge/skills/benja-pauls/serpentstack/dev-server.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 | $0.00033 | $0.00612 |
| Opus 5.5 | $0.00013 | $0.00245 |
| Sonnet 5.5 | $0.00007 | $0.00122 |
| Haiku 4.5 | $0.00003 | $0.00061 |
Grade A, and why
dev-server 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 — 59 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Dev Server
Starting the Dev Environment
make dev # Starts Postgres, Redis, runs migrations, launches backend + frontend
make dev-docker # Alternative: run everything in Docker
Backend: http://localhost:8000 · API docs: http://localhost:8000/api/docs Frontend: http://localhost:5173
If make dev fails, check docker compose ps to verify Postgres is healthy.
Error Detection Patterns
Backend (FastAPI) — Structured JSON Logs
| Pattern | Meaning | Fix |
|---|---|---|
"level": "ERROR" |
Application error | Read traceback, module, lineno fields |
ModuleNotFoundError |
Missing dependency | cd backend && uv add <package> |
sqlalchemy.exc.OperationalError |
Database connection failed | Check Postgres is running, migrations are current |
sqlalchemy.exc.ProgrammingError: relation "X" does not exist |
Missing migration | cd backend && uv run alembic upgrade head |
pydantic.ValidationError |
Schema field mismatch | Compare request payload against Pydantic model |
ImportError: cannot import name 'X' from 'app.models' |
Model not exported | Add import to backend/app/models/__init__.py |
Frontend (Vite/React)
| Pattern | Meaning | Fix |
|---|---|---|
TS\d{4}: (e.g., TS2345) |
TypeScript error | Read file path + line number from message |
[vite] Internal server error |
Build failure | Read full error below the message |
Module not found: Can't resolve |
Missing package | cd frontend && npm install or add the dependency |
Uncaught Error: |
React runtime error | Read component stack trace |
[hmr] Failed to reload |
HMR failure (usually syntax) | File path is in the message |
Auto-Fix Workflow
When an error is detected:
- Classify: syntax, type, import, runtime, or database error
- Locate: extract file path and line number from the error output
- Check recent changes:
git diff HEAD~1 -- <file> - Read the file: open at the relevant line, read 20 lines of surrounding context
- Fix: apply the minimal change to resolve the error
- Verify: wait for hot-reload, confirm the error is gone
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 · 59 lines · 33 tokens per session scan A 41be0fc57345
dev-server is a skill published in the GitHub repository Benja-Pauls/SerpentStack (2 stars, last pushed 6mo ago), licensed MIT. It adds 33 tokens to every session and 612 once invoked, about $0.0001 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
code_explorer
Explores the repository to locate primary source files, coupled UI components, and test files for bug reports or feature requests.
test-failure-explorer
Import and query an existing Vitest 3.2 JSON report to explore test failures, file-level errors and original diagnostic evidence.
session-investigator
Investigate fast-agent session and history files to diagnose issues. Use when a session ended unexpectedly, when debugging tool loops, when correlating sub-agent traces with main sessions, or when analyzing conversation flow and timing. Covers session.json metadata, history JSON format, message structure, tool…
feedback
Skill "feedback" from Hmbown/Codewhale, covering feedback, when to use, setup, workflow and non-goals.
smiles-validation
Strict SMILES validation, structural comparison, and modification verification. Catches invalid LLM-generated molecules.
oversight-team
Use when you are a seat on the oversight pod (a standing monitor-mode rig that keeps OTHER rigs healthy), configuring or running the drift detectors, or choosing whether to intervene vs escalate. Covers the pull-not-poll posture, the v0 detectors (premature-park, process-drift, off-task, token-burn), the intervention…