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 commands/dreadnode/agent-lens/experimentgit clone --depth 1 https://github.com/dreadnode/agent-lensWhat 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 | $0.00000 | $0.03097 |
| Opus 5 | $0.00000 | $0.01548 |
| Sonnet 5 | $0.00000 | $0.00619 |
| Haiku 4.5 | $0.00000 | $0.00310 |
Grade A, and why
experiment 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 — 284 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Experiment Config Generator
The user wants to create a harness experiment config to test a hypothesis about agent behavior. Your job is to design the experiment, write a config, run it, and analyze the results.
Instructions
-
Understand the hypothesis. Ask clarifying questions if needed:
- What behavior are they testing? (memory read/write, tool use patterns, subagent delegation, hallucination, etc.)
- What directory should the agent work in? (can use
./repos/test_repofor simple tests) - How many sessions? What should each session probe?
- Should sessions be isolated (no conversation history), chained (full conversation context), or forked (branching from a prior session)?
- Do they need subagents?
- Do they need replicates (
count) to study variance?
-
Design the experiment. Consider:
- Session mode: Use
isolatedto test if the agent uses memory correctly across fresh conversations. Usechainedto test multi-turn reasoning with full context. Useforkedto compare different prompts from the same starting point. - Memory file: The harness auto-seeds
MEMORY.mdin the working directory. You can customize the filename (memory_file) and initial content (memory_seed). The absolute path is injected into the system prompt automatically. - System prompt: Set up the scenario. Tell the agent about MEMORY.md and any conventions.
- Session prompts: Each session should test a specific aspect of the hypothesis. Be specific about what the agent should do.
- Forking: Use
fork_fromon individual sessions to branch from any prior session, not just session 1. - Replicates: Use
count: Non a session to run it N times as independent replicates. Useful for studying behavioral variance. - Subagents: Define if the hypothesis involves delegation behavior. Give each a name, description, prompt, and tool restrictions.
- Turn limits: Use
max_turns: 10-15for focused tasks,30+for complex exploration. - Capture: Always set
capture_api_requests: trueto enable resampling and intervention testing later. - Tags: Always include
"auto-generated"tag plus hypothesis-specific tags. - Hypothesis: Always include a one-sentence
hypothesisfield in the config.
- Session mode: Use
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 · 284 lines · 0 tokens per session scan A 84454e6d9d3c
experiment is a command published in the GitHub repository dreadnode/agent-lens (114 stars, last pushed 2mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 3,097 tokens. 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.
Other commands, from other repositories
project-hierarchy-check
Use this command before changing organisation, project, or database config behavior.
ship
Create a new git branch, commit changes, and create a pull request.
instrument
Generate a comprehensive instrumentation plan for a mobile codebase.
tma1-peer
List recent sessions on this project by agent — peers (Codex, OpenClaw, Copilot CLI) or your own.
VibeGuard: Stats
View hooks trigger statistics - interception/warning/release times and reason analysis.
optimize
Show TokenJam's savings/optimize report — where quota is going and what's recoverable. Equivalent to running tj optimize.