log-context

log-context is a command for coding agents from indranildchandra/claude-local-starter. It costs 30 tokens per session (368 once invoked), scanned A, original, MIT.

A session-notes command that records the current work, decisions, changed files, and unfinished tasks in tasks/tracker.md.

In plain words
What is it for?
It creates or updates a tracker entry before context is cleared or whenever a detailed progress snapshot is needed.
Why use it?
It prevents important context from being lost when a coding session is shortened or restarted. A later session can use the snapshot to continue from the right place.

Command

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/indranildchandra/claude-local-starter/log-context
Clone the repo
git clone --depth 1 https://github.com/indranildchandra/claude-local-starter

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 log-context

README.md
[![agentmods](https://agentmods.dev/badge/commands/indranildchandra/claude-local-starter/log-context.svg)](https://agentmods.dev/commands/indranildchandra/claude-local-starter/log-context)
Your own site
<a href="https://agentmods.dev/commands/indranildchandra/claude-local-starter/log-context"><img src="https://agentmods.dev/badge/commands/indranildchandra/claude-local-starter/log-context.svg" alt="Measured on agentmods" height="20"></a>
Per session 30 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 368 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 $0.00030 $0.00368
Opus 5 $0.00015 $0.00184
Sonnet 5 $0.00006 $0.00074
Haiku 4.5 $0.00003 $0.00037

Measured 5d ago against content hash bafa10c315c9, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

log-context 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 5d 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.

commands/log-context.md · 33 lines

What it actually says

You are writing a pre-compact context snapshot. Follow these steps exactly.

Step 1 — Load the format

Read aidlc-tracking skill formats.md for the pre-compact snapshot entry format before writing anything.

Step 2 — Gather session context

Reflect on the current conversation and identify:

  • Working on: What is the current task or goal?
  • Completed this session: What has been finished since the session started or since the last snapshot?
  • Key decisions: What significant decisions were made and why?
  • Files changed: Which files were created, modified, or deleted?
  • Open / in-progress: What is unfinished or blocked?
  • Resume from: The exact state a fresh session would need to pick up — specific file, function, step, or error being worked on. Be precise enough that no context is required from the conversation history.

Step 3 — Write to tasks/tracker.md

Prepend the pre-compact snapshot entry to tasks/tracker.md so the newest entry is at the top.

If tasks/tracker.md does not exist: create it with the header from aidlc-tracking formats.md, then write the entry below the header.

If tasks/tracker.md already exists: insert the new entry immediately after the file header (first 3 lines), pushing all prior entries down. Do NOT append to the end of the file.

Step 4 — Confirm

Tell the user: "Context logged to tasks/tracker.md — safe to /compact." Show the Resume from line so the user can verify it captures the current state.

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. 5d ago First seen · 33 lines · 30 tokens per session scan A bafa10c315c9

Subscribe to this mod's changes

log-context is a command published in the GitHub repository indranildchandra/claude-local-starter (13 stars, last pushed 1mo ago), licensed MIT. It adds 30 tokens to every session and 368 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 2026-08-30.