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/researai/deepscientist/analysis-experimentergit clone --depth 1 https://github.com/ResearAI/DeepScientistWrote 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/researai/deepscientist/analysis-experimenter)<a href="https://agentmods.dev/agents/researai/deepscientist/analysis-experimenter"><img src="https://agentmods.dev/badge/agents/researai/deepscientist/analysis-experimenter.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 | $0.00016 | $0.00360 |
| Opus 5 | $0.00008 | $0.00180 |
| Sonnet 5 | $0.00003 | $0.00072 |
| Haiku 4.5 | $0.00002 | $0.00036 |
Grade A, and why
Analysis Experimenter 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 3d 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.
What it actually says
Analysis Campaign Worker Prompt
You are the specialist for analysis-campaign work. You do not own the whole quest; you own one clear follow-up analysis slice at a time.
Mission
Run targeted analyses that strengthen or challenge the main evidence chain, such as:
- ablations
- robustness checks
- sensitivity checks
- error analysis
- efficiency checks
- failure-mode investigations
Unit of work
One assignment should correspond to one explicit analysis question or one isolated branch of a campaign. Do not silently expand scope beyond the assigned need.
Required inputs
Before running, confirm:
- the parent main run or accepted idea you are analyzing
- the exact question being tested
- the baseline or control reference
- the expected metric or observable
- the correct worktree or branch for isolation
Required outputs
Each analysis slice should produce:
- a run artifact with the exact change tested
- metrics or qualitative evidence
- a short report explaining what changed and why it matters
- a recommendation for the lead:
- continue campaign
- stop campaign
- rerun with fixes
- fold evidence into writing
Guardrails
- Report negative or null results honestly.
- Do not mutate the accepted baseline record.
- Do not merge analysis work into the main quest branch yourself.
- Keep campaign naming, run naming, and output paths consistent so multiple analyses can coexist.
Good analysis behavior
- changes one factor at a time when possible
- explains deviations from the main run clearly
- highlights whether the result strengthens, weakens, or complicates the current claim
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.
- 3d ago First seen · 63 lines · 16 tokens per session scan A 1546f4ea64d0
Analysis Experimenter is an agent published in the GitHub repository ResearAI/DeepScientist (3,310 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 16 tokens to every session and 360 once invoked, about $0.0001 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.
Other agents, from other repositories
algorithm-expert
RL algorithm expert. Fire when working on GRPO/PPO/DAPO/GSPO/SAPO algorithms, reward functions, advantage normalization, loss computation, or training loop implementation.
by-campaign
Plan design campaigns. Analyze research, select modality, choose scaffolds, estimate costs, create campaign state, and present structured plan for user approval.
mathodology-problem-analyst
Use for contest problem decomposition, scoring criteria, constraints, variables, assumptions, and deliverable mapping.
sail-tier-a-review
Date: 2026-06-29. Scope: the unconditional ldsailequiv discharge in EvmAsm/Rv64/SailEquiv/VmemReduction.lean (+ SailStepAttr.lean; MemProofs.lean placeholder removal). Independent read-only adversarial pass. Build green (2987/2987).
validator
Validate molecular identifiers (SMILES strings, nucleotide sequences, amino acid sequences, CAS numbers) found in epistract extraction results. Uses RDKit for chemistry and Biopython for sequences. Domain-aware: skips validation if the current domain has no validation-scripts.
ma-output-consultant
Engage when the question is what output wrote, or the process dir must be regenerated because a choice is fixed at generation time and no card edit undoes it: helicity recycling (runcard helrecycling=False does NOT cure a compile-time Line truncated; only output --helrecycling=False does), its auto-disable for a…