What it does
This repo is a collection of 19 skills
- Connects Instruction files the AI reads; connects to nothing
- Account or key No key needed
- Category Coding
Maker’s original description
The ripgrep of AI context: a zero-dependency C++23 CLI + MCP server for coding agents. Cut agent token costs by finding code without reading the repo, then keep large codebases off the complexity wall: blast radius, tests to run, quality deltas as you write. Every guess labelled, every loss publish…For makers: add a badge to your README
If you made this, paste this code into your README. The badge links back to this page.
[](https://mcp.popnx.com/en/skills/redhat-et-ripwire)Use together with
MCP servers that connect the AI to services for the same work
Fallow
Codebase intelligence for TypeScript and JavaScript, exposed as structured MCP analysis tools.
Desktop Commander
MCP server for terminal commands, file operations, and process management
Similar Skills
Same kind of work, ordered like the Skills list
| This one ripwire | rea | graphify | archify | security-audit-skill | |
|---|---|---|---|---|---|
| Maker | redhat-et | morluto | Graphify-Labs | tt-a1i | cloudflare |
| Skills | 19 | 1 | 1 | 1 | 1 |
| GitHub stars | 2,544 | 461,751 | 148,352 | 96,757 | 73,156 |
| Last code change | Nov 16, 2026 | Nov 16, 2026 | Nov 16, 2026 | Nov 15, 2026 | Sep 15, 2026 |
| License | Apache-2.0 | MIT | Apache-2.0 | Apache-2.0 | MIT |
19 skills (instruction sets) by redhat-et that an AI reads and follows · not an MCP server
Pick the skill to install
Install only the ones you use. Open a skill to see how to install it
Install the whole set (19)
If you want every one, let the AI install them in one go. Know 2 things first
- Every installed skill’s description is loaded into every chat. The more you install, the easier it is for the AI to pick the wrong one
- Some skills duplicate tools the AI already has built in. Installing only the ones you use works better
Uploading to Claude on the web and apps: you need 19 uploads, one ZIP per skill. Open each skill in the list below to download it
Checked against official docs Nov 12, 2026 · Source: support.claude.com, code.claude.com, learn.chatgpt.com, cursor.com
- emitting-output
Writing or converting formatted output in ripwire's C++ source — std::print/std::format via rw::emitTo, emitRaw and formatTo, which printf specifier maps to which format spec, and how to prove a conversion moved zero bytes. Use when adding any output call site, converting a printf-family one, or to…
- ripwire-before-you-build
Starting a FEATURE (multi-symbol work): the plan, the API boundary, the scope — how big does this change get — from the codebase's real structure. Implementing an EXISTING interface? --lego=Iface lists its contract and current implementors. ONE standalone symbol → reuse-first. A small feature with…
- ripwire-change-check
Merge-SAFETY of an existing diff — yours before you push, or a PR you review: blast radius, tests to run, a broken contract (--edit-check=SYM), branch conflicts and landing order, unmerged work stranded on old branches, which ref defines it. Code QUALITY → quality-bar. Even a one-line leaf fix runs…
- ripwire-find-bug
You have a SYMPTOM — crash, exception, wrong output, failing test, error string — and don't know which code is responsible. Ranks candidates; a stack trace or sanitizer output maps onto frames innermost-first; 'it worked yesterday' / 'my last edit broke it' → --situ. One clear hit plus one focused…
- ripwire-fresh-eyes
Maintenance risk in code you did NOT write — inheriting a module, planning a refactor, a suspected god object, 'what's gnarly / where's the rot / safe to touch?': hotspots, dead or inactive code, switches/defaults (--flags), clones, a function's real shape, bus factor, co-change. Naming the fix or…
- ripwire-graph-query
A call-graph question the fixed verbs can't phrase — 'which high-complexity functions can reach X?', 'what has 10+ callers in src/?', 'untested symbols within one hop of main'. --graph-query: a small closed expression language — kind, complexity, fan-in, tested filters; a file or cluster; bounded h…
- ripwire-handoff
Brief someone ELSE on a subsystem — 'hand this area off' to a successor, teammate or fresh session: purpose, the 2-3 entry points with bodies, the design docs that say WHY, hotspot/bus-factor risk — a compact pasteable brief, not a wall of source. Understanding it yourself → orient.
- ripwire-layers
Architecture HEALTH and ENFORCEMENT — 'is this a dependency mess / does the UI reach into the database / enforce module boundaries in CI?': cycles, the godfile, propagation cost (how far a touch ripples), --arch rules with a baseline gate. Overview without gating → orient. One pass answers it.
- ripwire-mcp
Wire ripwire into an agent as an MCP server — `ripwire wrap AGENT` (Claude Code, Cursor, Codex, Gemini…) — and choose the server verb mid-task. Also tool HEALTH: a symbol you expected is missing from the ranked output, the index feels stale after a rebase, 'is my ripwire setup broken?'
- ripwire-navigate
You can NAME the symbol: who calls it, what it calls, the path from A to B, its full body, or an exact literal/regex match. 'Safe to change or rename X — what breaks downstream?' = the transitive blast radius, not 1-hop callers. Three or more symbols → --connect. Run the one verb that fits, then st…
- ripwire-opt-remarks
Triage clang optimization remarks (-Rpass, -Rpass-missed, opt-record YAML) while editing ripwire's OWN C++: 'loop not vectorized', 'will not be inlined' — worth a diff, or is LTO/PGO the real fix? Contributor-only: about compiling this tool, never about running it.
- ripwire-orient
Landing COLD in an unfamiliar repo or subsystem, or about to open several files for one question: map first, read only what it ranks highest — main subsystems, entry points, 'how does X work / where is Y'. Also recover context after compaction, retrieve saved docs (--recall), divide code for subage…
- ripwire-perf-target
A MEASURED performance problem: start from a benchmark, flame graph, perf sample or profiler run, locate the hot symbol the profile names, test structural hypotheses (memory-bound → cache-line data layout). Static metrics are change-risk signals, not runtime heat. Inspect only the symbols the profi…
- ripwire-quality-bar
Code QUALITY of what YOU just wrote, before commit/'done' or a cleanup: --quality-delta lists what got WORSE in 12 kinds; exit 2 if old code did (new-symbol rows never gate, except defect-shape format-arity and a new function at the ceiling); the fix each shape calls for. Merge safety → change-chec…
- ripwire-repo-map
Use ripwire CLI to map a repo before reading it.
- ripwire-reuse-first
About to write ONE symbol (even a 'quick' one-liner) or add a dependency: reuse before you reinvent. Finds the building block that already exists, the house pattern to imitate, the duplicate you'd recreate, a vendored dependency. An interface or whole feature → before-you-build. One --exemplar or -…
- ripwire-router
Start HERE when unsure which ripwire skill fits, or asked 'how do I use ripwire / where do I start'. A moment→skill map, cold start to handoff, plus the two reflexes that leak most: --exemplar before you write, --quality-delta before you call it done. One hop to the right skill.
- ripwire-security-scan
Security review: (1) vet an untrusted SKILL.md or .mcp.json BEFORE installing it — the injection/exfiltration scanner; CRITICAL blocks the install; (2) audit code on an untrusted-input path (a deserializer, parser, exec of user data, network endpoint): taint reach, untested seams. One scan pass is…
- ripwire-write-tests
Write tests for EXISTING code that has none — 'this is untested, add coverage', 'add a safety net first'; also verify a new test reaches its intended code. Finds what no test reaches: --seams ranks untested cross-module edges, --callers gives the outside contract. Diff test selection → change-check…
How a Skill differs from MCP
MCP = the hands
Connects the AI to an outside service or data, such as reading Notion or creating an invoice. A program or server has to be running.
Skill = the manual
A text file that teaches the AI how to do a task. It connects to nothing.
Some overlap: a few Skills run scripts that call tools, and a few MCP servers only send knowledge. Start from the task you want done.
Works with
Claude CodeCodexCursorWindsurfOpenCode
From the maker’s README and the folders in the repo
Install
Pick a skill first
This repo has 19 skills. Pick one from the list above; its page shows every way to install it, including letting the AI install it and a ZIP
Discussion
Ask, share a tip or report that it does not work. Sorted by what people marked helpful.
No posts yet. Be the first to ask or share.
Posts here are written by users, not the PopNx team.
From GitHub
- GitHub stars
- 2,544
Stars are for the whole repo, not each skill - Maker
- redhat-et
- License
- Apache-2.0
- Last code change
- Nov 16, 2026
- SKILL.md files in the repo (including translated copies and templates)
- 19
- Topics
- agent-tools, call-graph, claude-code, code-analysis, code-intelligence, code-review, code-search, codex, coding-agents, context-engineering, context-window, dependency-graph