obsidian-tracker-session-log

obsidian-tracker-session-log is a skill for Claude Code from IvanLutsenko/awac-ai-agent-plugins. It costs 25 tokens per session (595 once invoked), scanned A, original, MIT.

A session-log command that saves a summary of coding work to an Obsidian project. It records the goal, actions, results, and next steps, using active tracking data when available.

In plain words
What is it for?
Use it to document what a session achieved, what remains, and which operations were performed for a selected project.
Why use it?
It removes the need to write a session report from scratch or rely on memory after work is finished.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: names the AskUserQuestion tool; mentions Claude Code; runs codex exec.

Part of the obsidian-tracker plugin — 19 skills, 19 commands shipped together

Good fit Use it to document what a session achieved, what remains, and which operations were performed for a selected project.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/ivanlutsenko/awac-ai-agent-plugins/session-log
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 IvanLutsenko/awac-ai-agent-plugins --skill session-log
Clone the repo
git clone --depth 1 https://github.com/IvanLutsenko/awac-ai-agent-plugins

Made for: Claude Code.

Or install obsidian-tracker, the plugin that ships this one along with the rest of its 19 skills, 19 commands.

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 obsidian-tracker-session-log

README.md
[![agentmods](https://agentmods.dev/badge/skills/ivanlutsenko/awac-ai-agent-plugins/session-log/github.svg)](https://agentmods.dev/skills/ivanlutsenko/awac-ai-agent-plugins/session-log)
Your own site
<a href="https://agentmods.dev/skills/ivanlutsenko/awac-ai-agent-plugins/session-log"><img src="https://agentmods.dev/badge/skills/ivanlutsenko/awac-ai-agent-plugins/session-log/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 obsidian-tracker-session-log

Your own site · 80×15
<a href="https://agentmods.dev/skills/ivanlutsenko/awac-ai-agent-plugins/session-log"><img src="https://agentmods.dev/badge/skills/ivanlutsenko/awac-ai-agent-plugins/session-log.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 25 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 595 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 $0.00025 $0.00595
Opus 5.5 $0.00010 $0.00238
Sonnet 5.5 $0.00005 $0.00119
Haiku 4.5 $0.00003 $0.00060

Measured 14d ago against content hash c2c8a74be4bb, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

obsidian-tracker-session-log 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 14d 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.

plugins/obsidian-tracker/skills/generated-from-commands/session-log/SKILL.md · 85 lines

How it starts

The opening of the file, as written. The whole thing — 85 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Converted from Claude Code command /session-log. Review and adapt: hooks and MCP tool IDs may need manual mapping for Codex.

Session Log Command

Logs the current Claude Code session to the specified project.

Step 0: Check Configuration

Вызови MCP tool:

mcp__plugin_obsidian_tracker_obsidian__getConfig

Если initialized: false: выполни инициализацию как в /projects команде.

Arguments

  • project-name (optional) - Project to log session to

Logic

  1. Resolve project:

    Если project-name не указан:

    mcp__plugin_obsidian_tracker_obsidian__listProjects
    

    Покажи нумерованный список:

    # Project Status
    1 name Active

    Пользователь может ввести номер или имя проекта.

  2. Collect session info:

    Сначала проверь .claude/obsidian-tracking.json:

    • Если файл существует — используй данные из него (project, goal, actions)
    • Если goal пустой — сгенерируй из контекста разговора
    • Добавь недостающие actions из контекста

    Если файла нет:

    • Goal: Summarize main topic from conversation
    • Actions: List key tool calls and operations

    Всегда спрашивай:

    • Results: What was achieved
    • Next steps: Ask user via AskUserQuestion
  3. Create session via MCP:

    mcp__plugin_obsidian_tracker_obsidian__addSession
    с параметрами:
      project = project name
      goal = session goal
      actions = ["action1", "action2", ...]
      results = what was achieved
      nextSteps = next steps
    
  4. Output:

    📝 Session logged to "{project}"
    📁 Path: {path}
    
    Summary:
    - Goal: {goal}
    - Actions: {count} recorded
    - Next: {nextSteps}
    
  5. Cleanup tracking: Удали .claude/obsidian-tracking.json после успешного логирования.

Codex differences

  • A non-interactive run (codex exec, CI) has nobody to answer a prompt: continue on defaults, honour whatever the invoking prompt already specified, and report which defaults were used. If the whole point of the command is to ask, say that it needs an interactive session and stop rather than inventing answers.

Read the full file on GitHub · 85 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. 14d ago Changed · +4 lines c2c8a74be4bb
  2. 1mo ago First seen · 81 lines · 25 tokens per session scan A 3e49a0b0c738

Subscribe to this mod's changes

obsidian-tracker-session-log is a skill published in the GitHub repository IvanLutsenko/awac-ai-agent-plugins (3 stars, last pushed 3d ago), licensed MIT. It adds 25 tokens to every session and 595 once invoked, about $0.0001 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 2026-09-05.

Related

Other skills, from other repositories