gaps

gaps is a command for coding agents from fcakyon/phd-skills. It costs 23 tokens per session (432 once invoked), scanned A, original, MIT.

A research workflow that compares published work on a topic to identify areas that have not been studied enough. It searches sources such as Google Scholar, Semantic Scholar, and arXiv, which is an open repository for research papers and preprints.

In plain words
What is it for?
Use it to map research areas, group papers by approach, investigate missing topics, and rate how confidently a gap has been confirmed.
Why use it?
It helps replace a broad or incomplete literature search with an organised view of existing approaches and possible gaps. It also checks whether recent or less visible work already covers a suspected gap.

Command

Part of the phd-skills plugin — 12 skills, 6 commands, 2 agents, 4 hooks shipped together

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 commands/fcakyon/phd-skills/gaps
Clone the repo
git clone --depth 1 https://github.com/fcakyon/phd-skills

Or install phd-skills, the plugin that ships this one along with the rest of its 12 skills, 6 commands, 2 agents, 4 hooks.

Per session 23 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 432 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 $0.00023 $0.00432
Opus 5 $0.00012 $0.00216
Sonnet 5 $0.00005 $0.00086
Haiku 4.5 $0.00002 $0.00043

Measured 3d ago against content hash e8c407b38f50, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

gaps 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.

plugin/commands/gaps.md · 67 lines

What it actually says

Literature Gap Analysis

You are performing a systematic gap analysis for the following research topic:

Topic: $ARGUMENTS

Step 1: Landscape Mapping

Search for existing work on this topic using multiple queries:

  • Direct topic search via web search
  • Search with alternative phrasings and synonyms
  • Check Google Scholar, Semantic Scholar, and arXiv
  • Look for survey papers that map the area

Step 2: Categorize Existing Work

Organize found papers into a coverage table:

| Approach Category | Papers | What They Cover | What's Missing |
|-------------------|--------|----------------|---------------|

Step 3: Identify Gaps

For each empty cell or "What's Missing" entry:

  1. Search specifically for work that might fill this gap
  2. Check very recent papers (last 6 months) on arXiv
  3. Look for workshop papers and preprints
  4. Assess whether the gap is meaningful

Step 4: Validate Gaps

For each candidate gap, rate confidence:

  • HIGH: Searched with 3+ phrasings, checked top venues, clearly missing
  • MEDIUM: Searched but might have missed niche venues
  • LOW: Limited search, gap may exist under different terminology

Step 5: Output

## Gap Analysis: [Topic]

### Research Landscape
[2-3 sentence overview]

### Coverage Table
| Approach | Representative Papers | Coverage | Gap? |
|----------|----------------------|----------|------|

### Identified Gaps
| Gap | Confidence | Evidence of Absence | Why It Matters |
|-----|-----------|---------------------|---------------|

### Candidate Papers to Cite
[BibTeX entries for relevant papers — VERIFIED against DBLP]
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. 3d ago First seen · 67 lines · 23 tokens per session scan A e8c407b38f50

Subscribe to this mod's changes

gaps is a command published in the GitHub repository fcakyon/phd-skills (382 stars, last pushed 2mo ago), licensed MIT. It adds 23 tokens to every session and 432 once invoked, about $0.0001 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.