context-compression

context-compression is a skill for Claude Code, Codex from dzhokhov/markdown-agent-vault-ru. It costs 187 tokens per session (3,317 once invoked), scanned A, original, MIT.

A skill for condensing the history of meetings and projects into a short memory file. It records decisions, changes, outdated agreements, open questions, and key meetings.

In plain words
What is it for?
Use it to maintain a compact project history in meetings/README.md and find the meetings relevant to a current question.
Why use it?
It prevents the agent from rereading many old meeting notes while preserving the reasoning behind important decisions.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: mentions AGENTS.md.

Good fit Use it to maintain a compact project history in meetings/README.md and find the meetings relevant to a current question.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/dzhokhov/markdown-agent-vault-ru/context-compression
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.

Any agent
npx skills add dzhokhov/markdown-agent-vault-ru --skill context-compression
Clone the repo
git clone --depth 1 https://github.com/dzhokhov/markdown-agent-vault-ru

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for context-compression

README.md
[![agentmods](https://agentmods.dev/badge/skills/dzhokhov/markdown-agent-vault-ru/context-compression/github.svg)](https://agentmods.dev/skills/dzhokhov/markdown-agent-vault-ru/context-compression)
Your own site
<a href="https://agentmods.dev/skills/dzhokhov/markdown-agent-vault-ru/context-compression"><img src="https://agentmods.dev/badge/skills/dzhokhov/markdown-agent-vault-ru/context-compression/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.

agentmods 80×15 button for context-compression

Your own site · 80×15
<a href="https://agentmods.dev/skills/dzhokhov/markdown-agent-vault-ru/context-compression"><img src="https://agentmods.dev/badge/skills/dzhokhov/markdown-agent-vault-ru/context-compression.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 187 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,317 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00187 $0.03317
Opus 5.5 $0.00075 $0.01327
Sonnet 5.5 $0.00037 $0.00663
Haiku 4.5 $0.00019 $0.00332

Measured 1mo ago against content hash 97d5a563cc09, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

context-compression 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 1mo 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.

skills/context-compression/SKILL.md · 230 lines

How it starts

The opening of the file, as written. The whole thing — 230 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Context Compression — скилл сжатия исторического контекста

Зачем этот скилл

meeting-processing должен разбирать текущую встречу, а не держать всю историю контура в окне контекста. Этот скилл поддерживает отдельный сжатый слой истории, чтобы агент мог восстановить причинную цепочку без чтения десятков старых встреч.

Главный выход скилла — meetings/README.md в головном проекте контура или в папке встреч проекта. Это не пересказ всех встреч, а навигационная память: что решили, что изменили, что устарело, какие вопросы ещё открыты и какие встречи являются якорными.

meetings/README.md не заменяет текущую картину проекта или продукта. Если нужен ответ «что сейчас главное», он живёт в отдельной текущей картине, объявленной в README.md или context.md, по правилу Память vault.

Принципы

  1. Сжатие отдельно от разбора. Скилл не извлекает задачи из новой встречи и не маршрутизирует их в plan.md / tasks.md. Это делает meeting-processing.
  2. Ограниченное чтение. Запрещено читать все старые встречи целиком. Полностью читаются только ближайшие и явно связанные встречи.
  3. Решения важнее пересказа. В сжатой истории хранятся цепочки решений: «было → изменилось → почему → ссылка».
  4. Устаревшее видно явно. Если старое решение отменено или переопределено, оно остаётся в сжатой истории как superseded, чтобы агент не принял его за актуальное.
  5. Каждый пункт со ссылкой. Любой сжатый факт должен ссылаться на исходную встречу или log.md.
  6. Сжатие тоже ограничено. meetings/README.md не должен становиться новым длинным архивом: если он разрастается, старые цепочки сворачиваются в годовой файл истории.
  7. Публичность проверяется до записи. Сжатый слой часто видят больше людей, чем отдельные заметки. Не концентрируй в нём персональные оценки, конфликты, деньги и чувствительные детали без явного основания.
  8. История не равна текущей картине. После обновления meetings/README.md проверь, не нужно ли отдельно обновить текущую картину проекта или продукта. Не подменяй её сжатой историей встреч.
  9. Сводка не равна истине. Сжатая история хранит ссылку на источник, тип утверждения, основание и статус доверия для важных цепочек решений.
  10. Слабое не повышается молча. Пункты с evidence.strength: low, историческими ссылками без источника или устаревшим last_verified не используются как факты текущей картины.
  11. Конфликт сохраняется. Если старое и новое утверждения противоречат друг другу, создать или обновить конфликт, а не сглаживать формулировку.

Read the full file on GitHub · 230 lines

Files

What ships with it

1 file 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.

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. 1mo ago First seen · 230 lines · 187 tokens per session scan A 97d5a563cc09

Subscribe to this mod's changes

context-compression is a skill published in the GitHub repository dzhokhov/markdown-agent-vault-ru (2 stars, last pushed 1mo ago), licensed MIT. It adds 187 tokens to every session and 3,317 once invoked, about $0.0007 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 2026-08-31.

Related

Other skills, from other repositories

log

Use this when a PersonalOS work session, chat outcome, personal reflection, or provided source should be persisted into the modular Daily context and any already-owned canonical files. Do NOT use for single-call processing, single-source knowledge ingestion, Gmail/WhatsApp propagation, or Lexware booking.

vincentmumme/personalos-boilerplate · 59 tokens

analyse-call

Use this when a local call transcript or meeting note should be analyzed into traceable PersonalOS context. Preserves the source, separates evidence from interpretation, updates only proven owner truth, routes confirmed commitments through task-manager, and never sends messages or triggers external actions without…

vincentmumme/personalos-boilerplate · 58 tokens

lint-brain

Run health checks over the brain vault - find orphan notes, broken wikilinks, missing frontmatter, stale projects, and missing cross-links. Use when asked to "lint the brain", "health check", "vault hygiene", or "/lint-brain".

michaeljauk/brain-starter · 56 tokens

ingest-article

Ingest an article from a URL or raw text into the brain vault. Extracts key knowledge, determines placement, creates or updates notes, and links to relevant projects. Use when the user shares a URL or text and wants to absorb it into their knowledge base.

michaeljauk/brain-starter · 58 tokens

wrap-session-up

End-of-session review for a Claude Code conversation. Replays what was discussed, checks for open action items, documents relevant outcomes in the brain vault, and creates Todoist tasks for anything untracked. Use at the end of a work session to ensure nothing falls through the cracks.

michaeljauk/brain-starter · 60 tokens

kickoff

Guided first-run setup for a forked brain-starter vault. Walks through identity, first project, semantic search, integrations, indexes, and the first commit - verifying each phase before moving on. Use when the user has just forked or cloned brain-starter, says "set up my brain", "I just forked brain-starter", or runs…

michaeljauk/brain-starter · 80 tokens