What is control-literature-search?

A research procedure for finding academic papers and possible research gaps in control science and engineering. It searches a configured collection of journals, translates Chinese topics into English, and treats abstracts as search evidence rather than proof of detailed claims.

Searching prior work, reviewing literature, and finding possible gaps in areas such as robust control, networked control, and model predictive control.

It keeps literature searches within a defined source collection and prevents conclusions that the search results cannot support.

How PrisonBreakPB/control-science-literature-mcp configures Claude Cod

Reuse

Borrowing it

Nothing to install: this file belongs to PrisonBreakPB/control-science-literature-mcp. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/PrisonBreakPB/control-science-literature-mcp/main/.agents/skills/control-literature-search/SKILL.md

Clone the repo

git clone --depth 1 https://github.com/PrisonBreakPB/control-science-literature-mcp

Made for: Claude Code, Codex.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/prisonbreakpb/control-science-literature-mcp/control-literature-search/github.svg)](https://agentmods.dev/skills/prisonbreakpb/control-science-literature-mcp/control-literature-search)

Your own site

<a href="https://agentmods.dev/skills/prisonbreakpb/control-science-literature-mcp/control-literature-search"><img src="https://agentmods.dev/badge/skills/prisonbreakpb/control-science-literature-mcp/control-literature-search/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/prisonbreakpb/control-science-literature-mcp/control-literature-search"><img src="https://agentmods.dev/badge/skills/prisonbreakpb/control-science-literature-mcp/control-literature-search.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 69 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 721 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

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	$0.00069	$0.00721
Opus 5.5	$0.00028	$0.00288
Sonnet 5.5	$0.00014	$0.00144
Haiku 4.5	$0.00007	$0.00072

Measured 2mo ago against content hash 366a2532d7db, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

control-literature-search 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 2mo 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.

.agents/skills/control-literature-search/SKILL.md · 83 lines

How it starts

The opening of the file, as written. The whole thing — 83 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Control Literature Search

Use this skill to turn a control-science research question into a traceable candidate paper list from the configured core journal collection.

This skill requires the search_control_science_papers tool from Control Science Literature MCP. If that tool is unavailable, explain that the MCP server must be installed and enabled. Do not substitute another search tool.

Scope

Search only the configured control science and engineering journal collection.
Use English search queries. Translate Chinese research topics before searching.
Do not call web, arXiv, PDF, browser, file, shell, or validation tools.
Do not claim coverage of conference papers, preprints, or journals outside the configured collection.
Treat returned abstracts and metadata as search evidence, not as sufficient evidence for detailed method, theorem, or research-gap claims.

Workflow

Restate the research target in one sentence.
Extract 3-8 core concepts. Include focused control-domain variants where useful, such as networked control systems, event-triggered control, robust control, model predictive control, Lyapunov stability, LMI, multi-agent systems, or control barrier functions.
Translate Chinese concepts to concise English keywords.
Call search_control_science_papers with the most direct query first.
For a broad topic, run up to three focused query variants. Use citations when the user asks for influential work and date when they ask for recent work.
Deduplicate obvious repeated titles and present the candidates with their returned metadata.
State that the results are limited to the configured control science and engineering journal collection. If the results are thin, say that this collection may not cover the requested venue or paper type.

Tool Parameters

query (required): English research keywords.
max_results: Number of papers to return, from 1 to 20.
sort: relevance, citations, or date.
year_from / year_to: Optional inclusive publication-year bounds.
language: Optional lower-case ISO language code; defaults to en.

Read the full file on GitHub · 83 lines

Changes

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.

2mo ago First seen · 83 lines · 69 tokens per session scan A 366a2532d7db

Subscribe to this mod's changes

control-literature-search is a skill published in the GitHub repository PrisonBreakPB/control-science-literature-mcp (0 stars, last pushed 3mo ago), licensed MIT. It adds 69 tokens to every session and 721 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.

Research Scientific

control-literature-search next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
control-literature-searchPrisonBreakPB/control-science-literature-mcp	Skill	0	3mo ago	MIT	A	69	Claude Code, Codex
instrument-data-to-allotropeanthropics/knowledge-work-plugins	Skill	35k	2d ago	Apache-2.0	A	123	Claude Code
exploratory-data-analysisK-Dense-AI/scientific-agent-skills	Skill	56k	4d ago	MIT	A	83	Claude Code
matlabK-Dense-AI/scientific-agent-skills	Skill	56k	4d ago	MIT	A	44	Claude Code
phylogeneticsK-Dense-AI/scientific-agent-skills	Skill	56k	4d ago	MIT	A	71	Claude Code, Codex
research-engineerdavila7/claude-code-templates	Skill	33k	yesterday	MIT	A	43	Claude Code, Codex
mapping-to-snomedmaziyarpanahi/openmed	Skill	5.8k	yesterday	Apache-2.0	A	205	Claude Code

control-science-literature-mcp: Skill for Claude Code