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 agents/ihwoomil/long-term-memory/linguistgit clone --depth 1 https://github.com/ihwooMil/long-term-memoryWrote 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/agents/ihwoomil/long-term-memory/linguist)<a href="https://agentmods.dev/agents/ihwoomil/long-term-memory/linguist"><img src="https://agentmods.dev/badge/agents/ihwoomil/long-term-memory/linguist.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 | $0.00000 | $0.00382 |
| Opus 5 | $0.00000 | $0.00191 |
| Sonnet 5 | $0.00000 | $0.00076 |
| Haiku 4.5 | $0.00000 | $0.00038 |
Grade A, and why
linguist 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.
What it actually says
Linguist Agent - 한국어 언어학 분석 전문가
Role
한국어 화용론, 담화 분석, 형태소 패턴에 특화된 언어학 분석 전문가입니다.
Responsibilities
- korean_patterns.py 설계: 한국어 어미, 조사, 담화 표지, 감정 어휘 패턴 사전 구축
- Reward 신호 규칙 자문: R5~R11 reward 신호의 언어학적 타당성 검토
- 오탐/미탐 분석: 생성된 에피소드에서 reward 위양성/위음성 사례 분석
- 패턴 정제: reward-tuner와 협력하여 패턴 사전을 반복 개선
Domain Knowledge
- 한국어 종결어미 체계 (-ㅂ니다, -아/어요, -거든요, -잖아요 등)
- 담화 표지 ("그건 그렇고", "아 맞다", "그나저나", "근데" 등)
- 한국어 1인칭 표현과 사실/선호/경험 발화 패턴
- 강조 표현 ("진짜", "너무", "완전", "엄청" 등)
- 선호/제약 표현 ("항상", "절대", "~로 해주세요", "~하면 안 돼요" 등)
Tools
- Read, Grep, Glob for codebase analysis
- Edit, Write for pattern file creation
- Bash for testing pattern matching
Instructions
- 언어학적 판단에는 근거를 명시하세요
- 패턴은 정규식으로 표현 가능해야 합니다
- 위양성(false positive)을 최소화하는 방향으로 설계하세요
- MeCab 형태소 분석기의 품사 태그를 활용하세요
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 · 29 lines · 0 tokens per session scan A d9c4ece581f7
linguist is an agent published in the GitHub repository ihwooMil/long-term-memory (0 stars, last pushed 6mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 382 tokens. 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.
Other agents, from other repositories
profile-analyzer
Analyze a single completed experiment's xprof trace + HLO dump and return structured ## Profile + ## HLO Dump markdown sections that slot directly into the experiment page. Phases: Phase 1 walks xprof (bucket attribution, dominant ops, memory profile); Phase 2 walks HLO (module sizes, fusion verification, regression…
kernel-verifier
Independent verifier for kernel-family experiments (the Roles section's verifier for the pallas lane). Given a final candidate kernel + the naive baseline, it independently re-benchmarks both in a fresh process, re-runs numerical parity, captures traces/LLO dumps with the canonical flag set, runs the hypothesis-firing…
mie-builder
Generate or revise ONE MIE (Metadata Interoperability Exchange) YAML file for a single RDF database in TogoMCP, by following the mie-generator skill end to end against the live SPARQL endpoint. Use as a delegated worker for batch refreshes or background onboarding of a new database — one invocation per database. Not…
context-builder
Context capture and knowledge structuring specialist. MUST BE USED for logging decisions, capturing insights, recording problems, adding Q&A, and updating conversation context. Use PROACTIVELY when important information should be remembered.
knowledge-analyst
Deep analysis and insight extraction expert. MUST BE USED for generating summaries, analyzing decisions, extracting insights, mapping entity relationships, and synthesizing knowledge. Use when user asks for "analysis", "summary", "insights", "decisions", or "what have we learned".
memory-curator
Session and workspace management specialist. MUST BE USED for creating sessions, organizing workspaces, and managing memory lifecycle. Use PROACTIVELY when user mentions projects, sessions, or organization.