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 CodeInfinity1/Stram --skill spike-experimentgit clone --depth 1 https://github.com/CodeInfinity1/StramWrote 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/codeinfinity1/stram/spike-experiment)<a href="https://agentmods.dev/skills/codeinfinity1/stram/spike-experiment"><img src="https://agentmods.dev/badge/skills/codeinfinity1/stram/spike-experiment/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/codeinfinity1/stram/spike-experiment"><img src="https://agentmods.dev/badge/skills/codeinfinity1/stram/spike-experiment.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 | $0.00024 | $0.00402 |
| Opus 5.5 | $0.00010 | $0.00161 |
| Sonnet 5.5 | $0.00005 | $0.00080 |
| Haiku 4.5 | $0.00002 | $0.00040 |
Grade A, and why
spike-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 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
Spike Experiment
Purpose
Use small experiments to answer uncertain technical questions without letting exploratory code leak into production. A spike is evidence gathering, not the final architecture.
When To Use
Use for unfamiliar APIs, performance questions, parsing approaches, provider behavior, browser/OS feasibility, and risky design choices.
Inputs And Evidence
- Question to answer, time/step budget, success criteria, and allowed workspace.
- Experiment code/output, artifacts, and conclusion.
Tool Map
python_interpreterrun_shell_commandread_filewrite_notebrowser_live_opentool_search
Workflow
- State the narrow question and stop condition.
- Choose a safe sandbox/profile.
- Run the smallest experiment that can answer the question.
- Record results, surprises, and limitations.
- Discard throwaway code unless the user asks to keep it.
- Convert the learning into a production plan or scoped patch.
Native Implementation Boundaries
- Use Stram interpreter/shell/browser tools.
- Do not import external reference spike scripts.
- Do not call external services unless explicitly approved and necessary.
Safety And Approval
- Experiments that execute code or contact networks require the relevant approval.
- Keep writes inside approved workspace/data directories.
- Avoid using secrets in exploratory code.
Verification
- A spike must answer the stated question or explain why it did not.
- Preserve output or notes when useful.
- Do not claim production readiness from a spike alone.
Failure Modes
- Letting spike code become unreviewed production code.
- Running an unbounded experiment.
- Optimizing for interesting results instead of the user's decision.
References
- Shortlist item:
spike-experiment. - Upstream inspiration: external reference spike reference only.
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 · 67 lines · 24 tokens per session scan A 70d3b7e9e631
spike-experiment is a skill published in the GitHub repository CodeInfinity1/Stram (11 stars, last pushed 2mo ago), licensed MIT. It adds 24 tokens to every session and 402 once invoked, about $0.0001 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 2026-09-03.
Other skills, from other repositories
omh-live-incident-response
This is an OMH live-incident-response workflow skill, projected for Agent Skills hosts (Claude Code, Codex, Cursor, opencode, OpenClaw, pi).
debugging
Use this skill when something is broken and the cause is unknown — a failing test, a crash, an error message, wrong output, a regression, a hang, or behaviour that differs between environments — and it has to be found and fixed at the root. Also use it to build the failing proof for a suspected defect before fixing…
thinking-five-whys-plus
When a fault is localized and the proximate cause is known but the systemic root is not, chain evidence-linked whys with a counterfactual stop and a countermeasure.
thinking-map-territory
When a claim, doc, test, metric, or assumption conflicts with observed behavior, stop theorizing from the map and verify the live code or data; let territory overrule.
debug-systematic
Systematic 4-phase debugging methodology for complex, intermittent, or mysterious issues. Use when investigating bugs, race conditions, or unexplained failures.
postmortem
Deliver a structured post-mortem after incidents, mistakes, or stuck sessions. Use when the user requests a structured post-mortem after incidents, mistakes, or stuck sessions.