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 agentmods add skills/promptpartner/agentsmith/new-researchnpx skills add PromptPartner/agentsmith --skill new-researchgit clone --depth 1 https://github.com/PromptPartner/agentsmithWrote 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/promptpartner/agentsmith/new-research)<a href="https://agentmods.dev/skills/promptpartner/agentsmith/new-research"><img src="https://agentmods.dev/badge/skills/promptpartner/agentsmith/new-research.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 | $0.00074 | $0.00436 |
| Opus 5 | $0.00037 | $0.00218 |
| Sonnet 5 | $0.00015 | $0.00087 |
| Haiku 4.5 | $0.00007 | $0.00044 |
Grade A, and why
new-research 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 5d 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
New research note
Research belongs in the repo, traceable to sources, and is never silently deleted (R9). This scaffolds one note per topic.
When this fires
"start a research note" / "capture these sources" / beginning any multi-source investigation whose findings should outlive the session.
Fast path — if the Agentsmith CLI is available
Run agentsmith new-research "topic name" — use .agentsmith/agentsmith on macOS/Linux or
.agentsmith\\agentsmith.cmd on Windows when the command is not on PATH. It slugifies the title and writes
docs/research/<slug>.md from the template (it won't overwrite an existing file).
Fallback — no CLI
- slug = the topic lowercased, every run of non-alphanumeric characters →
-, ends trimmed. - If
docs/research/<slug>.mdalready exists, STOP — append to it, never overwrite. - Otherwise create it with a no-delete banner (obsolete → move to
docs/research/_archive/, R9) and these sections:- Question / scope
- Sources consulted — url or citation; what you actually opened, dated.
- Findings — each traceable to a source above; mark single-sourced / uncertain items.
- Open questions / what was NOT checked.
Report
Name the file created and remind the operator to commit it (R9 — research lives in git, not memory). Every finding you add later must cite a source already in the note.
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.
- 5d ago First seen · 34 lines · 74 tokens per session scan A b09c9685be13
new-research is a skill published in the GitHub repository PromptPartner/agentsmith (185 stars, last pushed yesterday), licensed MIT. It adds 74 tokens to every session and 436 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 2026-08-30.
Other skills, from other repositories
meta-config-stack-detect
Inspect a codebase, a stack the user describes, or a description of what they want to build; map what is there to agents-inc catalog skills — or intent to candidate built-in stacks the user picks from — and emit a SeedPayload plus a human-readable proposal report. Use when seeding a configuration for a project that…
meta-design-composable-components
Composable component APIs — parts, state, polymorphism.
web-meta-framework-nextjs
Next.js App Router patterns (15-16) - file-based routing, Server/Client Components, streaming, Suspense, metadata API, parallel routes, Server Actions, mutations, revalidation, Cache Components.
ai-provider-anthropic-sdk
Official Anthropic SDK patterns for TypeScript/Node.js — client setup, Messages API, streaming, tool use, vision, extended thinking, structured outputs, prompt caching, batch API, and production best practices.
api-baas-firebase
Firebase backend-as-a-service — Firestore, Authentication, Cloud Functions v2, Storage, Hosting, Admin SDK, security rules, emulator suite.
api-database-mongodb
Native MongoDB driver (the mongodb npm package) - MongoClient lifecycle, typed collections, CRUD result shapes, cursors, aggregation pipelines, index design, transactions.