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.
npx agentmods add agents/conectlens/lenserfight/workspace-guidegit clone --depth 1 https://github.com/conectlens/lenserfightWrote 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/agents/conectlens/lenserfight/workspace-guide)<a href="https://agentmods.dev/agents/conectlens/lenserfight/workspace-guide"><img src="https://agentmods.dev/badge/agents/conectlens/lenserfight/workspace-guide.svg" alt="Measured on agentmods" 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 | $0.00036 | $0.04182 |
| Opus 5 | $0.00018 | $0.02091 |
| Sonnet 5 | $0.00007 | $0.00836 |
| Haiku 4.5 | $0.00004 | $0.00418 |
Grade A, and why
workspace-guide 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 yesterday.
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 — 423 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent Workspace Guide
The Agent Workspace is the operational home for a single AI Lenser. It is reached from the route:
/lenser/<handle>/ag/<section>
Every left-rail tab routes you to a section; every action inside a section opens a drawer. This page documents each surface so you can pick the right tool, fill the right field, and understand the side effects before you click Save.
Owner-only by default. Public viewers see read-only mirrors. Builder/approval controls remain hidden unless
viewMode === 'agent_owner'.
Sections
Overview
Route: /lenser/<handle>/ag/overview
The control room. Aggregates instruction binding state, active builder team, workflow count, schedule health, active runs, and pending approvals into a single dashboard. Use it as the daily starting point — every "next action" links into a specialized section.
- Stat strip — Instruction / Builder / Workflows / Schedules / Active Runs.
- Active Runs panel — live queue with cancel/inspect controls.
- Recent Incidents — last 25 blocked or failed runs and policy denials.
- Kill switch banner — appears when
settings.global_kill_switch = true; resume clears the global lock. - Cross-agent activity (human owner view only) — fleet-wide feed across every AI lenser you own.
Instructions
Route: /lenser/<handle>/ag/instructions
Binds a Lens version to act as the agent's default system prompt. The binding is owner-only and version-pinned — promoting a new lens version requires an explicit rebind.
- Pick from lenses owned by the agent's lenser profile.
- Unbinding disables the agent's ability to run workflows that depend on a system prompt fallback.
- See also: Lens Instructions Reference.
Personality
Route: /lenser/<handle>/ag/personality
Free-text personality note + selected instruction lens. Personality is injected alongside the system prompt at inference time. Limit: 1 000 characters. See Manage Agent Settings for the full three-step wizard.
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.
- yesterday First seen · 423 lines · 36 tokens per session scan A 32d8f27ccc47
workspace-guide is an agent published in the GitHub repository conectlens/lenserfight (19 stars, last pushed 25d ago), licensed MIT. It adds 36 tokens to every session and 4,182 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 2026-09-03.
Other agents, from other repositories
observability-engineer
OpenTelemetry, Prometheus, Grafana, distributed tracing, SLO design, and alerting specialist. Use when implementing observability, designing monitoring systems, or troubleshooting production issues. Trigger phrases: observability, monitoring, tracing, Prometheus, Grafana, OpenTelemetry, SLO, SLI, alerting, metrics…
ansible-security
Ansible Vault and secrets management specialist.
security-auditor
Deep security analysis for OWASP Top 10, auth vulnerabilities, secrets exposure, and dependency risks. Use when reviewing code security, before deployments, or investigating security concerns.
product-manager
Product requirements, user stories, roadmaps, prioritization frameworks, and sprint planning specialist. Use when writing PRDs, defining user stories, planning sprints, or making product decisions. Trigger phrases: PRD, user story, roadmap, sprint, backlog, prioritization, product requirements, acceptance criteria…
ux-researcher
UX research, usability testing, user interviews, wireframing, and information architecture specialist. Use when planning user research, designing interfaces, conducting heuristic evaluations, or creating wireframes. Trigger phrases: UX research, user research, usability, wireframe, user interview, persona, journey…
security-reviewer
Cross-ecosystem security audit specialist. Proactively reviews code for vulnerabilities static analysis misses — logic flaws, architectural security gaps, ecosystem-specific pitfalls. Use when modifying authentication, authorization, data handling, API endpoints, or any code processing user input, and before PRs…