Borrowing it
Nothing to install: this file belongs to fbabelle/PrettySeriousResearcher. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/fbabelle/PrettySeriousResearcher/main/.claude/skills/research-algo-design/SKILL.mdgit clone --depth 1 https://github.com/fbabelle/PrettySeriousResearcherWrote 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/fbabelle/prettyseriousresearcher/research-algo-design)<a href="https://agentmods.dev/skills/fbabelle/prettyseriousresearcher/research-algo-design"><img src="https://agentmods.dev/badge/skills/fbabelle/prettyseriousresearcher/research-algo-design/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/fbabelle/prettyseriousresearcher/research-algo-design"><img src="https://agentmods.dev/badge/skills/fbabelle/prettyseriousresearcher/research-algo-design.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 | $0.00059 | $0.02626 |
| Opus 5 | $0.00030 | $0.01313 |
| Sonnet 5 | $0.00012 | $0.00525 |
| Haiku 4.5 | $0.00006 | $0.00263 |
Grade A, and why
research-algo-design 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 7d 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.
How it starts
The opening of the file, as written. The whole thing — 77 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Phase 2 — Algorithm / solution design & implementation
Turn the Phase-1 gap into a concrete, implemented method. The deliverable is a chosen approach implemented with tests, a set of candidate variants for later ablations, and a passed solvability gate.
Step 1 — Per-candidate technical evaluation (depth)
Phase 1 asked "is the topic worth it?" (breadth). Phase 2 asks "can these specific approaches solve the framed problem, and which is best?" For each candidate approach (aim for 2–4), evaluate:
- Effectiveness — does the mechanism plausibly close the gap? On what evidence (prior results, theory, a quick spike)?
- Efficiency — compute/memory/latency cost; does it fit the local-execution envelope (see
research-experiments)? - Limitations & assumptions — where it breaks; what it silently assumes about the data/market. Extract the assumption fine print from primary sources (exact dependence/independence conditions, calibration requirements, what the theorems actually cover) — method-level assumptions routinely decide the whole stack choice, and secondary summaries omit them.
- Maturity — is it rare/underexplored (novelty upside, more risk) or over-exploited (well-understood, lower novelty)?
- The named-SOTA limitation it removes — each candidate must name the specific limitation of a named SOTA method it beats (carried from the Phase-1 candidate card), plus a co-primary efficiency/robustness metric (compute, latency, turnover, drawdown) alongside the headline number — not "it's novel" in the abstract.
Use the host agent's current web-search and page-fetch tools for prior-art lookups on specific methods. This evaluation also defines the baselines the experiments will measure against — capture them now.
Step 2 — The solvability gate (hard checkpoint)
Before building, answer plainly: can at least one candidate plausibly solve the framed problem within our data/compute/budget envelope?
Present the verdict as an advisor-style ranked modification report the user confirms, not a pass/fail the agent self-clears: per candidate, its strengths/weaknesses, prioritized next steps to make it work, and an explicit feasible / unfeasible classification — so the user chooses which approach to build from a pre-critiqued slate (the same confirm surface the orchestrator gates rely on), rather than auditing raw analysis.
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.
- 7d ago Changed · +10 lines 63953eb0b1c7
- 12d ago First seen · 67 lines · 59 tokens per session scan A 9c7aaa3d7a25
research-algo-design is a skill published in the GitHub repository fbabelle/PrettySeriousResearcher (2 stars, last pushed today), licensed Apache-2.0. It adds 59 tokens to every session and 2,626 once invoked, about $0.0003 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 2026-08-31.
Other skills, from other repositories
agent-platform-rag-engine-management
Manage and query Agent Platform RAG Engine Corpora and retrieve grounded contexts using the Google GenAI SDK. Use when listing RAG corpora or files, inspecting a corpus, retrieving contexts, or generating content grounded in a RAG corpus. Do not use for standard database queries (use SQL/Spanner skills), Google…
agent-platform-model-registry
Agent Platform Model Registry Management. Use when you need to upload, list, describe, update, or delete machine learning models (and their versions) in the Agent Platform Model Registry. Don't use for model training, model deployment to endpoints, or managing non-Agent Platform models.
foundry-config-setup
Resolve missing setup caused by a hardcoded Foundry project endpoint or model in a sample. Use when a sample fails because it uses a placeholder/hardcoded projectendpoint (for example "https://your-project.services.ai.azure.com") or a hardcoded model instead of reading them from the environment.
google-cloud-solution-agentic-analytics-spark-knowledge-catalog
Discovers requirements and generates guidance to design and deploy a governed, secure agentic-analytics solution for data that's distributed across Google Cloud, other cloud providers, or on-premises. Data that's outside Google Cloud (such as data from Databricks, Snowflake, Salesforce, SAP, or Oracle systems) is…
training-check
Interactively monitor training metrics from the current Codex session, periodically checking WandB or fallback logs for NaN, divergence, plateaus, and broken runs.
nemo-automodel-launcher-config
Configure NeMo AutoModel job launches for interactive runs, Slurm clusters, and SkyPilot cloud execution.