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 skills add rrpauls/hermes-esra --skill experimentergit clone --depth 1 https://github.com/rrpauls/hermes-esraWrote 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/skills/rrpauls/hermes-esra/experimenter)<a href="https://agentmods.dev/skills/rrpauls/hermes-esra/experimenter"><img src="https://agentmods.dev/badge/skills/rrpauls/hermes-esra/experimenter/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/rrpauls/hermes-esra/experimenter"><img src="https://agentmods.dev/badge/skills/rrpauls/hermes-esra/experimenter.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00074 | $0.00507 |
| Opus 5.5 | $0.00030 | $0.00203 |
| Sonnet 5.5 | $0.00015 | $0.00101 |
| Haiku 4.5 | $0.00007 | $0.00051 |
Grade A, and why
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 1mo 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
Experimenter
Role
You design and guide small, safe, hypothesis-driven experiments to test potential improvements in capabilities, workflows, or behavior. You help turn ideas for improvement into structured learning experiences.
When This Skill Activates
Use when there are proposed improvements that need testing before full adoption, or when exploring new approaches with controlled risk.
Core Process
-
Formulate Clear Hypothesis
Turn the proposed improvement into a testable statement. -
Value Alignment Assessment (with Value-Clarifier)
- Explicitly assess how the proposed experiment aligns with core values and long-term direction.
- Provide a short justification (1–3 sentences).
- If there is significant misalignment, either adjust the experiment or clearly flag the conflict and reduce its priority.
-
Design Minimal Experiment
Create the smallest viable test with clear success criteria, timebox, and measurement. -
Assess Risk and Safeguards
Identify downsides and add safety mechanisms (limited scope, rollback plan, monitoring). -
Run and Observe
Execute while collecting relevant observations. -
Analyze Results
Compare outcomes to the hypothesis and extract learnings. -
Decide Next Step
Recommend: adopt, discard, modify, or run follow-up experiment.
Key Principles
- Smaller and shorter experiments are preferred.
- Experiments should be reasonably aligned with core values (Value Alignment Assessment is mandatory).
- Learning is the primary goal.
- Change one variable at a time when possible.
- Always have an exit strategy.
Integration
- Takes inputs from self-improver.
- Performs mandatory Value Alignment Assessment with value-clarifier. Experiments with poor alignment receive lower priority.
- Feeds learnings into mental-model-updater.
- Useful when testing changes suggested by system-dynamics-thinker.
Output Style
Be practical and structured. Always include:
- Hypothesis
- Value Alignment justification
- Experiment design, risks, success criteria
- Expected learnings
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.
- 1mo ago First seen · 57 lines · 74 tokens per session scan A 6f97ec42e53f
experimenter is a skill published in the GitHub repository rrpauls/hermes-esra (1 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 74 tokens to every session and 507 once invoked, about $0.0003 per session on Opus 5.5. 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.
Other skills, from other repositories
pptx-html-fidelity-audit
Audit a python-pptx export against its source HTML deck, identify layout/content drift (footer overflow, cropped content, missing italic/em, lost styling, off-rhythm spacing), and re-export with strict footer-rail + cursor-flow layout discipline. Use this skill whenever the user has a .pptx that was generated from an…
build-test
Run the project's build / typecheck / lint / test commands and emit the build.passing + tests.passing signals devloop convergence reads.
verify-before-done
Before claiming work is fixed, done, passing or deployed.
dogfood
This skill guides you through systematic exploratory QA testing of web applications using the browser toolset. You will navigate the application, interact with elements, capture evidence of issues, and produce a structured bug report.
hermes-change-review
Use when a branch, pull request, Kanban task, or implementation must be reviewed separately for intent fidelity, repository quality, and verification evidence before completion or merge is accepted.
business-logic
Test workflows, state transitions, pricing, and concurrency.