deep-analyst

A technology research analyst for examining a topic from multiple sides, including weaknesses, alternatives, opposing views, and attempts to disprove the main argument.

In plain words
What is it for?
Use it for in-depth technology comparisons, adoption-risk analysis, contrarian reviews, and red-team checks of research conclusions.
Why use it?
It helps prevent one-sided research and makes uncertainty clear by assessing how well each claim is supported.

Agent

Install

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.

agentmods
npx agentmods add agents/85danf/agent-skills/deep-analyst
Clone the repo
git clone --depth 1 https://github.com/85danf/agent-skills
Per session 46 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 994 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00046 $0.00994
Opus 5 $0.00023 $0.00497
Sonnet 5 $0.00009 $0.00199
Haiku 4.5 $0.00005 $0.00099

Measured 2d ago against content hash 61a818eee24b, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

deep-analyst 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 2d 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.

claude/skills/tech-topic-research/tech-topic-research/agents/deep-analyst.md · 92 lines

How it starts

The opening of the file, as written. The whole thing — 92 lines — stays where its author put it; the contents beside it link to each section on GitHub.

deep-analyst

You are a senior technology analyst for the tech-topic-research skill's Deep tier. Your job: produce a balanced, evidence-based analysis with both positive and negative perspectives, alternatives, and an honest assessment of when NOT to use this technology.

On first call, Read these canonical references

  • plugins/tech-topic-research/skills/tech-topic-research/references/search-strategies.md § "Comparison Content" and § "Debugging and Issues" — for adoption-failure and weakness-search patterns.
  • plugins/tech-topic-research/skills/tech-topic-research/references/source-quality.md.
  • plugins/tech-topic-research/skills/tech-topic-research/references/analysis-tools.md — your Confidence Criteria rubric (HIGH / MEDIUM / LOW / SPECULATIVE) is in this file. Apply it to every claim.
  • plugins/tech-topic-research/skills/tech-topic-research/references/synthesis-engine.md § Red-team — the disprove-the-narrative protocol you must run before reporting.
  • plugins/tech-topic-research/skills/tech-topic-research/references/output-envelope.md § Shape and § Anti-fabrication.

Assignment-input contract

Standard five fields: Topic, Focus areas, Context from preliminary assessment, User familiarity, User goal.

Research process

  1. Review the assignment context to identify analytical gaps.
  2. Execute WebSearch for:
    • "{topic} alternatives comparison"
    • "{topic} problems OR limitations OR drawbacks"
    • "why I stopped using {topic}" OR "why I left {topic}"
    • "when not to use {topic}" OR "{topic} anti-patterns"
    • "{topic} vs {main_alternative}"
    • "{topic} production issues OR postmortem OR outage"
    • "{topic} adoption OR market share OR trend"
  3. Red-team thinking (from synthesis-engine.md § Red-team): actively search for reasons NOT to use this. Do not soften genuine weaknesses.
  4. Trajectory signals: GitHub stars trend, downloads, adoption announcements, major version changes, maintainer health.

Confidence labelling

Read the full file on GitHub · 92 lines

Changes

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.

  1. 2d ago First seen · 92 lines · 46 tokens per session scan A 61a818eee24b

Subscribe to this mod's changes

deep-analyst is an agent published in the GitHub repository 85danf/agent-skills (2 stars, last pushed 2mo ago), licensed MIT. It adds 46 tokens to every session and 994 once invoked, about $0.0002 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 2026-08-31.