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 maystudios/claude-skills --skill auto-researchgit clone --depth 1 https://github.com/maystudios/claude-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/maystudios/claude-skills/auto-research)<a href="https://agentmods.dev/skills/maystudios/claude-skills/auto-research"><img src="https://agentmods.dev/badge/skills/maystudios/claude-skills/auto-research/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/maystudios/claude-skills/auto-research"><img src="https://agentmods.dev/badge/skills/maystudios/claude-skills/auto-research.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 2 findings, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Rogue Agent · line 3 Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.Fix: Remove any persistence mechanisms (cron jobs, startup scripts, state files). Skills should not maintain state across sessions without explicit user consent.
- medium Excessive Agency · line 164 Skill allows unbounded resource consumption (API calls, storage, compute). Without rate limits or quotas, a compromised or misbehaving agent can cause denial-of-service or cost overruns.Fix: Set explicit rate limits, timeouts, and resource quotas for API calls, file operations, and compute. Implement circuit breakers for runaway loops.
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 | $0.00234 | $0.02692 |
| Opus 5.5 | $0.00094 | $0.01077 |
| Sonnet 5.5 | $0.00047 | $0.00538 |
| Haiku 4.5 | $0.00023 | $0.00269 |
Grade A, and why
auto-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 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.
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 — 183 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Auto-Research
Improve a target prompt artifact (SKILL.md, CLAUDE.md, subagent definition, slash-command, or generic prompt markdown) by:
- Detecting the artifact type and the rules that apply to it
- Researching current authoritative best practices in parallel — every claim cited
- Proposing a rewrite with per-change rationale and source URLs
- Validating the rewrite — for testable artifacts, an autonomous Karpathy-style binary-assertion eval loop with git commit/reset bookkeeping; for non-testable artifacts, deterministic format validation
- Confirming once at the very end with a before/after score table, the diff, and the cited sources — only the user's explicit "yes" causes the final write
Run autonomously between steps 1 and 4. Stop only at step 5.
Phase 0 — Read Inputs and Set Up Workspace
The user will name a target artifact (a path, or a phrase like "my copywriting skill" — resolve it). Resolution rules:
- If a path is given, use it.
- If a skill name is given, search
.claude/skills/<name>/SKILL.md(project) then~/.claude/skills/<name>/SKILL.md(user). - If "this CLAUDE.md" or similar, use the most-specific one in the current working directory tree (project > user).
Then:
- Read the target artifact in full.
- Classify it via references/artifact-types.md: SKILL.md / CLAUDE.md / subagent / slash-command / generic-prompt.
- Set up the workspace — a sibling directory
.auto-research/<target-name>/next to the target. If the target's parent directory is not undergit, rungit initthere so commit/reset bookkeeping works locally. (If the user's project root has its own git repo and the target lives inside it, use the existing repo — do NOT init a sub-repo.) - Capture baseline — copy the original artifact to
.auto-research/<target-name>/iteration-0/baseline.mdand record git rev (git rev-parse HEADif available, else "untracked"). - Create
iterations.tsvwith columns:iter | hypothesis | score_before | score_after | decision | git_rev | timestamp | notes.
What ships with it
5 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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 · 183 lines · 234 tokens per session scan A 033488c373a6
auto-research is a skill published in the GitHub repository maystudios/claude-skills (26 stars, last pushed 2mo ago), licensed MIT. It adds 234 tokens to every session and 2,692 once invoked, about $0.0009 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 2026-08-30.
Other skills, from other repositories
timescaledb-hyperfunctions
Use this skill when writing analytical SQL over time-series data with the TimescaleDB Toolkit (timescaledbtoolkit extension) hyperfunctions: approximate percentiles, statistical summaries, time-weighted averages, counter/gauge rates, uptime/heartbeat tracking, state durations, OHLC candlesticks, approximate distinct…
pgvector-semantic-search
Use this skill for setting up vector similarity search with pgvector for AI/ML embeddings, RAG applications, or semantic search. Trigger when user asks to: Store or search vector embeddings in PostgreSQL Set up semantic search, similarity search, or nearest neighbor search Create HNSW or IVFFlat indexes for vectors…
postgres
Use this skill for any PostgreSQL database work — table design, indexing, data types, constraints, extensions (pgvector, PostGIS, TimescaleDB), search, and migrations. Trigger when user asks to: Explore an existing PostgreSQL database to understand its objects and relationships Design or modify PostgreSQL tables…
cloudflare-development
Cloudflare Workers, Pages, KV, D1, R2, and Durable Objects development best practices for edge computing applications.
grpc-development
Best practices for building high-performance services with gRPC and Protocol Buffers. Use when designing RPC services, defining protobuf schemas, implementing streaming APIs, setting up gRPC interceptors, or building cross-language service communication.
kafka-development
Best practices for Apache Kafka event streaming and distributed messaging. Use when building event-driven architectures, implementing producer/consumer patterns, designing topic partitioning strategies, setting up Kafka Streams, configuring schema registries, or integrating change data capture pipelines.