Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/OrcaQubits/agentic-commerce-skills-pluginsnpx agentmods add skills/orcaqubits/agentic-commerce-skills-plugins/nlweb-dev-patternsWrote 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/orcaqubits/agentic-commerce-skills-plugins/nlweb-dev-patterns)<a href="https://agentmods.dev/skills/orcaqubits/agentic-commerce-skills-plugins/nlweb-dev-patterns"><img src="https://agentmods.dev/badge/skills/orcaqubits/agentic-commerce-skills-plugins/nlweb-dev-patterns/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/orcaqubits/agentic-commerce-skills-plugins/nlweb-dev-patterns"><img src="https://agentmods.dev/badge/skills/orcaqubits/agentic-commerce-skills-plugins/nlweb-dev-patterns.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 | $0.00110 | $0.02513 |
| Opus 5 | $0.00055 | $0.01256 |
| Sonnet 5 | $0.00022 | $0.00503 |
| Haiku 4.5 | $0.00011 | $0.00251 |
Grade A, and why
nlweb-dev-patterns 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 3d 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 — 208 lines — stays where its author put it; the contents beside it link to each section on GitHub.
NLWeb Development Patterns
Config layout changed upstream. NLWeb replaced the single
site_types.xmlwith two files inconfig/:sites.xml(site name →itemTypelist + description) andtools.xml(per-site / per-type tool definitions, prompts and examples, scoped by<Site id="…">/<Item>blocks). Older guidance — including anysite_type/extendsinheritance syntax — describes the retired file. Fetchconfig/sites.xmlandconfig/tools.xmlfrom the live repo before editing anything.
Before writing code
Fetch live docs:
- Fetch https://github.com/nlweb-ai/NLWeb/blob/main/docs/nlweb-systemmap.md for module layout.
- Fetch https://github.com/nlweb-ai/NLWeb/blob/main/docs/nlweb-control-flow.md for the request lifecycle.
- Fetch https://github.com/nlweb-ai/NLWeb/blob/main/docs/life-of-a-chat-query.md for an end-to-end trace.
- Fetch https://github.com/nlweb-ai/NLWeb/blob/main/docs/nlweb-configs-files.md for the config precedence rules.
- Inspect
core/baseHandler.py,core/router.py,core/retriever.py,core/ranking.pyfor current code paths.
Pattern: Mixed-Mode Programming
NLWeb's defining design choice. Rather than one big LLM call per query, NLWeb makes many small calls, each with a strict JSON output schema (<returnStruc>), feeding Python control flow.
Implications:
- Cost and latency scale with the number of call sites, not the size of any one call.
- Failures are localized — one bad call doesn't poison the response.
- Steerability is high — you can tune any single prompt without touching the rest.
- Debugging is harder — you must trace which of N calls misbehaved.
When designing extensions, follow the same pattern: small, schema-constrained LLM calls, deterministic Python glue.
Pattern: FastTrack vs Analysis (Parallel Paths)
NLWebHandler runs two paths in parallel:
| Path | What it does | When it wins |
|---|---|---|
| FastTrack | Immediate vector search → stream early results | Common queries with obvious retrieval matches |
| Analysis | Decontextualize → detect type → route via ToolSelector to a specific handler |
Ambiguous queries, complex flows (compare, recipe substitution) |
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.
- 3d ago First seen · 208 lines · 0 tokens per session scan A 844bb7289a7c
nlweb-dev-patterns is a skill published in the GitHub repository OrcaQubits/agentic-commerce-skills-plugins (39 stars, last pushed 3d ago), licensed MIT. It adds 110 tokens to every session and 2,513 once invoked, about $0.0006 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 2026-09-15.
Other skills, from other repositories
pi-loop-forensics
Diagnose pi-go agent loops and degenerate turns — "agent loop aborted", runaway thinking with no tool calls, repeated phrases. Discriminates genuine model repetition collapse from a race, a tool-parse failure, or a too-low guard, and A/B replays a seed session across providers.
nightly-session-watch
Nightly sweep of the last 24h of pi-go sessions — anomalous runs, loop aborts, tool error rates, token waste, real prompt-token spend, and whether the observation and palace pipelines are still recording. Triages each finding to the specialist skill that diagnoses it. Use for an unattended daily health check, or on…
archestra-dev-llm-providers
Use when adding an LLM provider, changing proxy adapters or provider routes, fixing streaming/tool-call translation bugs, editing model fetchers or model handling, or touching provider credentials/enums and model constants.
archestra-dev-investigate
Use when investigating Archestra bugs or incidents — staging issues, backend 50x errors, Drizzle failed queries, DB connection pressure, deploy regressions, or Kubernetes/runtime symptoms. Orientation only; defers the process to /investigate.
chaingpt
Build with the ChainGPT Web3 AI developer platform. Full API/SDK reference and project scaffolding for: Web3 AI Chatbot & LLM, AI NFT Generator, Smart Contract Generator, Smart Contract Auditor, AI Crypto News, AgenticOS Twitter agents, and Solidity LLM. Use when building blockchain apps, Web3 chatbots, NFT tools…
ironmesh-peers
Drill into per-peer IronMesh metrics — retry reasons, session rekeys, offline-since, transport type. Use when ironmesh-status shows a problem on a specific peer and you need detail.