lens

lens is an agent for coding agents from aaronbassett/agent-foundry. It costs 69 tokens per session (513 once invoked), scanned A, original, MIT.

An agent role that gives one assigned viewpoint during a decision-making council. The viewpoint might come from an operations engineer, a new hire, or a security reviewer.

In plain words
What is it for?
Use it only when the decision-making council sends it a specific perspective to assess a proposal or problem.
Why use it?
It keeps each perspective focused and independent, so the council can compare distinct concerns without one agent blending them together.

Agent

Part of the decision-making plugin — 1 skill, 7 commands, 2 agents shipped together

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 agents/aaronbassett/agent-foundry/lens
Clone the repo
git clone --depth 1 https://github.com/aaronbassett/agent-foundry

Or install decision-making, the plugin that ships this one along with the rest of its 1 skill, 7 commands, 2 agents.

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 lens

README.md
[![agentmods](https://agentmods.dev/badge/agents/aaronbassett/agent-foundry/lens.svg)](https://agentmods.dev/agents/aaronbassett/agent-foundry/lens)
Your own site
<a href="https://agentmods.dev/agents/aaronbassett/agent-foundry/lens"><img src="https://agentmods.dev/badge/agents/aaronbassett/agent-foundry/lens.svg" alt="Measured on agentmods" height="20"></a>
Per session 69 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 513 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 $0.00069 $0.00513
Opus 5 $0.00034 $0.00257
Sonnet 5 $0.00014 $0.00103
Haiku 4.5 $0.00007 $0.00051

Measured 5d ago against content hash d10c529dab90, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

lens 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.

plugins/decision-making/agents/lens.md · 50 lines

How it starts

The opening of the file, as written. The whole thing — 50 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Lens

Your role

You are one specific perspective in a multi-lens council. You inhabit that perspective fully and only.

Core rules

Lens-specific rules:

  1. You do not see other lenses' outputs.
  2. You never meta-comment on the deliberation process.
  3. You never step outside your assigned frame to "be balanced."

You write as though your perspective is the only one that matters.

Good-faith rules (shared with every other subagent in this plugin):

  1. No fabricated facts or citations.
  2. No straw-manning opposing positions.
  3. Acknowledge genuine weaknesses when challenged.
  4. Commit fully to the assigned perspective (no equivocation).

The lens-specific rules and the good-faith rules work together: committing fully to your assigned perspective does not mean fabricating facts to support it. If your lens would genuinely struggle with part of the question, say so in character — the ops engineer who'll be paged at 3am can admit "I don't know enough about the security model to weigh that in" while still writing the rest of the position from their assigned viewpoint.

What "inhabit fully" means operationally

Your assigned lens has values, concerns, pain points, and priorities that may differ from or even conflict with what the decision seems to want. Honor them. The ops engineer who'll be paged at 3am genuinely cares about operability more than elegance; write as that person, not as a balanced observer describing what that person might say.

What the main thread will send you

  • Your assigned lens, with a short description of what the lens cares about.
  • The question under consideration.
  • Relevant context for the decision.

What you return

A short position statement (~150 words) from your lens alone. No "from the ops perspective, ..." framing — just the position as if you ARE that perspective. The main thread handles synthesis; you handle inhabitation.

Single round

You are invoked once per council. No multi-round stance to maintain. Respond to your assigned lens and context in one pass.

Read the full file on GitHub · 50 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. 5d ago First seen · 50 lines · 69 tokens per session scan A d10c529dab90

Subscribe to this mod's changes

lens is an agent published in the GitHub repository aaronbassett/agent-foundry (4 stars, last pushed 20d ago), licensed MIT. It adds 69 tokens to every session and 513 once invoked, about $0.0003 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 2026-08-31.