Context+ is an MCP server that helps developers explore and search large codebases by combining code structure, semantic retrieval, clustering, and links between related files. It is intended for engineering work that requires navigating project architecture and finding relevant functions, classes, variables, and files. The catalogue entry is a skill for using this server.
Borrowing it
Nothing to install: this file belongs to forloopcodes/contextplus. 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/forloopcodes/contextplus/main/.claude/skills/forloop/SKILL.mdgit clone --depth 1 https://github.com/forloopcodes/contextplusWrote 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/forloopcodes/contextplus/forloop)<a href="https://agentmods.dev/skills/forloopcodes/contextplus/forloop"><img src="https://agentmods.dev/badge/skills/forloopcodes/contextplus/forloop/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/forloopcodes/contextplus/forloop"><img src="https://agentmods.dev/badge/skills/forloopcodes/contextplus/forloop.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 | $0.00000 | $0.00349 |
| Opus 5.5 | $0.00000 | $0.00140 |
| Sonnet 5.5 | $0.00000 | $0.00070 |
| Haiku 4.5 | $0.00000 | $0.00035 |
Grade A, and why
forloop 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.
What it actually says
you are a professional refeactoring engineer and software developer
-
no file should have any comments at all except for the file details at the start of the file, only the comments in the file must be on head of the file as 2 lines with 10 words each explaining the file
-
always refractor code into meaningful content, file names, and variable names, understandable but not long, must not look ai generated
-
for the coding logic, it must not make redundant variables initializations and function calling, try to do that in one time. example: instead of doing b = f(a) and c = g(b) just do it all at once - no need for b, its just c = g(f(a))
- if fn <20 lines and used only once, then it must be inlined, no need to make a function for that
- if fn is >20 lines, then decide to refeactor upon need
- if fn is <20 lines and used more than once, then it must be a function
-
IMP: your main goal is to reduce the number of tokens and % of context window used in the whole codebase by removing redundant code, variables, and files, and by making the code as simple as possible without losing readability.
-
every time you must check for non used variables, files and must remove them before bloating the filesystem
-
you must not make a lot of files in the same directory, instead use directory trees for better glance. same goes for files, not exceeding 500-1000 lines of code at max, and trying to refractor and making it as simple as possible
-
strict ordering: imports, then enums, then structs, then logic
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 · 18 lines · 0 tokens per session scan A f1f1aa16be20
forloop is a skill published in the GitHub repository forloopcodes/contextplus (1,986 stars, last pushed 3mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 349 tokens. 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 2026-08-30.
Other skills, from other repositories
trace-mcp-refactoring
Safe refactoring workflow using trace-mcp — assess risk, find candidates, check impact, and rename symbols across all files without missing import sites or cross-file references.
zen-review
Expert code reviewer. Analyze PR changes for correctness, security, performance, and quality. Returns findings as JSON. CRITICAL: this skill is costly, don't use it unless user explicitly requested to use it.
git-workflow
Follow this team's Git conventions for branching, commit messages, and pull requests.
m1nd-first
Use when investigating a repository, searching for implementation, reviewing changes, working from specs/docs, or preparing a risky code change in an environment where m1nd is available. This doctrine makes m1nd the first investigative layer before grep, glob, or manual file reads, except when the task is pure…
reviewing-update-sets
Reviewing, analyzing, and comparing ServiceNow update sets before promotion, singly or in batches. Shows changes, risks, dependencies, and conflicts. Use when the user mentions update sets, customizations, promotion, code review, change tracking, pre-deployment review, sysupdatexml, customer updates, 'what changed in…
review-thread
Record review verdicts and run the StateNote review thread on an agent-operation instance — every ReviewRequest verdict is one atomic batch-direct-write that advances status and co-writes a reviewnote explaining why, and findings are corrected by appending notes rather than editing them.