Borrowing it
Nothing to install: this file belongs to launch-it-labs/log-reducer. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/launch-it-labs/log-reducer/master/AGENTS.mdgit clone --depth 1 https://github.com/launch-it-labs/log-reducerWrote 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/instructions/launch-it-labs/log-reducer/agents-md)<a href="https://agentmods.dev/instructions/launch-it-labs/log-reducer/agents-md"><img src="https://agentmods.dev/badge/instructions/launch-it-labs/log-reducer/agents-md/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.
<a href="https://agentmods.dev/instructions/launch-it-labs/log-reducer/agents-md"><img src="https://agentmods.dev/badge/instructions/launch-it-labs/log-reducer/agents-md.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00496 | $0.00496 |
| Opus 5.5 | $0.00198 | $0.00198 |
| Sonnet 5.5 | $0.00099 | $0.00099 |
| Haiku 4.5 | $0.00050 | $0.00050 |
Grade A, and why
log-reducer AGENTS.md 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.
How it starts
The opening of the file, as written. The whole thing — 70 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Log Reducer — Agent Instructions
This repository contains a log reduction tool that compresses verbose log output for AI consumption, achieving 50-90% token reduction while preserving semantic value.
Available tool
CLI (works with any agent that can execute shell commands):
node out/src/cli.js < input.log
Or pipe from another command:
some-command 2>&1 | node out/src/cli.js
The CLI reads log text from stdin and writes the reduced version to stdout.
When to reduce logs
Use the log reducer before inserting log content into a conversation whenever:
- The log is longer than ~50 lines
- The log contains UUIDs, tokens, or long hex strings
- The log has repeated/duplicated lines
- The log contains stack traces with framework internals
What it does
The pipeline applies 11 transforms in order:
- Strip ANSI escape codes
- Normalize whitespace (collapse blank lines, trim trailing spaces)
- Shorten IDs (UUIDs, hex strings, JWT tokens, generated IDs →
$1,$2, ...) - Shorten URLs (strip query params, collapse long paths)
- Simplify timestamps
- Filter noise (health checks, heartbeats, devtools artifacts)
- Strip source locations (browser console
file.js:lineprefixes) - Compress shared prefixes (factor out repeated date/module/time prefixes)
- Deduplicate consecutive identical/near-identical lines
- Detect repeating multi-line cycles
- Fold stack traces (collapse framework internals, shorten file paths)
Project structure
src/pipeline.ts—minify(input: string): string— the main entry pointsrc/transforms/— Individual transform modulessrc/cli.ts— CLI stdin/stdout wrappersrc/mcp-server.ts— MCP server for Claude Codetest/fixtures/— Test fixtures (input.log + expected.log pairs)
Building
npm install
npx tsc -p ./
Testing
npm test
For Claude Code users
This project includes an MCP server configuration in .mcp.json (project root) that automatically exposes a reduce_log tool. See .claude/CLAUDE.md for details.
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.
- 1mo ago First seen · 70 lines · 496 tokens per session scan A dd6e949eccbb
log-reducer AGENTS.md is an instructions file published in the GitHub repository launch-it-labs/log-reducer (0 stars, last pushed 7mo ago), licensed MIT. It adds 496 tokens to every session, about $0.0020 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.
Other instructions, from other repositories
vibetags com-example-service-TransactionalPaymentService.instructions.md
Instructions for PIsberg/vibetags, covering copilot instructions for transactionalpaymentservice and strict exception handling.
vibetags com-example-gmm-platform-FeatureGate.md
Instructions for PIsberg/vibetags, covering amazon kiro steering: featuregate and feature flag gate.
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.