agentlens CLAUDE.md

agentlens CLAUDE.md is an instructions file for coding agents from RogerReed/agentlens. It costs 85 tokens per session, scanned A, original, MIT.

Repository instructions for agentlens, including required checks with its MCP service and a note about recurring maintenance work. MCP is a way for an agent to call an external service or tool.

In plain words
What is it for?
Use them when working on agentlens to review recent sessions, inspect recurring workspace patterns, decide whether past similar tasks are relevant, and check the maintenance runbook.
Why use it?
They tell an agent what context to inspect before starting and where to look for scheduled maintenance tasks.

Instructions file

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 instructions/rogerreed/agentlens/claude-md
Clone the repo
git clone --depth 1 https://github.com/RogerReed/agentlens

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 agentlens CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/rogerreed/agentlens/claude-md.svg)](https://agentmods.dev/instructions/rogerreed/agentlens/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/rogerreed/agentlens/claude-md"><img src="https://agentmods.dev/badge/instructions/rogerreed/agentlens/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 85 This file is loaded in full into every session.
When invoked 85 The same file — it is already loaded in full.
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 $0.00085 $0.00085
Opus 5 $0.00043 $0.00043
Sonnet 5 $0.00017 $0.00017
Haiku 4.5 $0.00009 $0.00009

Measured 5d ago against content hash acebf5708dcb, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

agentlens CLAUDE.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 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.

CLAUDE.md · 9 lines

What it actually says

AgentLens MCP

Before any task: call get_recent_sessions (recent work + cost) and get_workspace_patterns (hot files, recurring issues). Only use find_relevant_context if your task closely matches past prompts by keyword — skip it for novel tasks.

Recurring maintenance tasks

Check runbooks/README.md for periodic maintenance tasks (e.g. refreshing model pricing) that may be relevant or due.

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 · 9 lines · 85 tokens per session scan A acebf5708dcb

Subscribe to this mod's changes

agentlens CLAUDE.md is an instructions file published in the GitHub repository RogerReed/agentlens (11 stars, last pushed 5d ago), licensed MIT. It adds 85 tokens to every session, about $0.0004 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.