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 airas-org/airas --skill analyze-resultsgit clone --depth 1 https://github.com/airas-org/airasWrote 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/airas-org/airas/analyze-results)<a href="https://agentmods.dev/skills/airas-org/airas/analyze-results"><img src="https://agentmods.dev/badge/skills/airas-org/airas/analyze-results/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/airas-org/airas/analyze-results"><img src="https://agentmods.dev/badge/skills/airas-org/airas/analyze-results.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00043 | $0.00755 |
| Opus 5 | $0.00022 | $0.00378 |
| Sonnet 5 | $0.00009 | $0.00151 |
| Haiku 4.5 | $0.00004 | $0.00076 |
Grade A, and why
analyze-results 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
Analyze results & make figures
Needs imported results under .research/results/ in a clone.
-
Produce the metrics mechanically with airas-eval. Metrics are never computed by hand: the template ships a Makefile wired to airas-eval, a trusted, versioned scoring layer that computes a fixed metric set per task type from the raw predictions — run
make evaluate RUN_ID=<run_id>per imported run (the plan lives in
.research/evaluation.json;make list-tasksshows what each task type returns). On contract errors,make validate-inputs RUN_ID=<run_id>pinpoints them without scoring. The report includesmetrics,curves,skipped(uncomputable metrics with reasons — report these, never fill them in yourself) andprovenance. Commit the evaluation outputs. -
Read the results:
fetch_experiment_results(reads the repository). -
Author the analysis via
get_generation_prompt("experiment_analysis", ...), passing the experiment code from the clone as{"files": {"<path>": "<content>"}}. Write it in Japanese. Report what the numbers show, including when they do not show what was hoped — the analysis is evidence, not advocacy. -
Result charts: build a Vega-Lite spec and
render_chartit (pass the clone aslocal_path) to.research/results/chart/<name>.png— PNG, not PDF. Data numbers must be metric references ("metric:run_1.accuracy"), never literals: the tool resolves them from.research/results/itself, so a plotted point cannot be invented. The tool appends the chart's spec to.research/record.jsonas its declaration and commits both in the same step — verification re-renders every chart from its declared spec and fails on differences or undeclared chart files. Bars, areas and rects are drawn from zero: when ascale.domainexcludes zero the tool declares them withclip: true(so what is verified is what was drawn), but look at the PNG before citing it — labels, ordering and axis ranges are yours. A chart that needs changing gets a new path, or a superseding declaration viaappend_to_recordand a re-render; the old declaration stays. Render charts beforeupdate_record, or re-runupdate_recordafterwards: the chart declaration is a new record commit, andvalues.texmust be rendered against the latest one. -
Method diagrams: write text notation (mermaid / graphviz / d2) and
render_diagramto.research/results/diagram/<name>.pdf. -
Commit and push. Reference figures in LaTeX as
images/<path>with the full relative path you were given — two runs can each produceaccuracy.pdf, and only the full path resolves.
Output: an analysis in .research/research_history.json and
committed, verifiable figures.
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 Changed · +6 lines b2fc596c0515
- 7d ago First seen · 54 lines · 43 tokens per session scan A 222112f886ce
analyze-results is a skill published in the GitHub repository airas-org/airas (35 stars, last pushed today), licensed MIT. It adds 43 tokens to every session and 755 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 2026-09-04.
Other skills, from other repositories
research-proof
Turn vague research ideas, math-heavy claims, AI-lab style agent loops, benchmark claims, causal claims, prototype-readiness claims, design research, prompt-injection-sensitive evidence reviews, and medical-research style questions into falsifiable proof programs with fixed Claim/Verifier/Current…
proof-checker
A mathematical proof review and repair workflow for LaTeX documents. It checks whether a proof has valid reasoning, addresses identified gaps, reviews the fixes, and produces an audit report.
auto-paper-improvement-loop
An automated editing cycle for a compiled research paper: an external language model reviews it, fixes are applied, and the paper is compiled again.
research-lit
Search and analyze research papers, find related work, summarize key ideas. Use when user says "find papers", "related work", "literature review", "what does this paper say", or needs to understand academic papers.
paper-illustration
A workflow for generating academic illustrations, such as architecture diagrams and method visuals, with image generation and repeated review. Claude plans and checks the figure during the process.
paper-write
A workflow for writing a research paper section by section in LaTeX, a text format used to prepare structured technical documents. It starts from a paper outline and supports several academic venues and citation sources.