Agent skill

Ripwire Reuse First

by redhat-et in redhat-et/ripwire

About to write ONE symbol (even a 'quick' one-liner) or add a dependency: reuse before you reinvent.

Apache-2.0Auto-check: notes

Install Ripwire Reuse First

skills CLI
$ npx skills add redhat-et/ripwire --skill ripwire-reuse-first -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install redhat-et/ripwire ripwire-reuse-first --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/redhat-et/ripwire.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/ripwire-reuse-first .claude/skills/ripwire-reuse-first && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
ripwire-reuse-first
GitHub stars
2.4k
Token cost
~1.3k tokens
SKILL.md length
665 words
Files
1
Skills in repo
19
Repo updated
First seen
Licence
Apache-2.0

At a glance

About to write ONE symbol (even a 'quick' one-liner) or add a dependency: reuse before you reinvent.

  • Works in 4 steps: Find the building block first — ripwire… → Optionally get a style/shape exemplar —… → Find candidates by behavior/shape —… → …
  • SKILL.md covers Retrieve by ROLE, never by raw…, Before you write a function /…, Before you add a dependency and When you do write
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Ripwire Reuse First is an agent skill from redhat-et/ripwire. 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 --grep call at most.

Its SKILL.md is about 1.3k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

The repository describes itself as: The ripgrep of AI context: a zero-dependency C++23 CLI + MCP server for coding agents. Find what you want without reading the repo, then check you built what you meant — blast… The licence is Apache-2.0.

Example prompts

  • “/ripwire-reuse-first”

Requirements

  • Pre-approved tools (allowed-tools): Bash, Read

Workflow steps

4 steps, taken from the first numbered list in SKILL.md.

  1. Find the building block first — ripwire --for="" → ranked existing
  2. Optionally get a style/shape exemplar — if the retrieval result leaves a local-idiom question,
  3. Find candidates by behavior/shape — ripwire --grep="" --legend=compact, or a NARROWED
  4. Don't duplicate — ripwire --clones --legend=compact → if your intended body matches an existing one, call it

What it can do on your machine

Read from SKILL.md and the folder at commit 0852bc0. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves these tools, so the agent can use them without asking each time:

    • Bash
    • Read

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md.

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Ripwire Reuse First loads about 1.3k tokens when it runs. Until then it costs about 85 tokens; SKILL.md has 665 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~85
When it runs · the whole SKILL.md, loaded when a task matches
~1.3k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check: notes

The automated check noted patterns worth knowing about, such as sudo or a known installer.

  • NotePre-approves every shell command (allowed-tools: Bash)SKILL.md
    allowed-tools: Bash, Read

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from redhat-et/ripwire at commit 0852bc0, republished under its Apache-2.0 licence (© redhat-et). 665 words, ~1,317 tokens.

Download SKILL.mdSave it as .claude/skills/ripwire-reuse-first/SKILL.md (or your agent's skills folder).
name
ripwire-reuse-first
description
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 --grep call at most.
allowed-tools
Bash, Read

Reuse before you write

Routing — pick the right door: • Starting a whole FEATURE (multi-symbol, needs a plan / interface / sizing) → ripwire-before-you-build. • The cross-cutting map-before-you-read token discipline for any read → ripwire-orient (map-before-you-read.md). • Judging whether what you wrote got better or worse before "done" → ripwire-quality-bar. • Not sure which skill? → ripwire-router.

The cheapest, simplest, most readable code is the code you don't write. Before authoring anything non-trivial, spend one ripwire call (on PATH) to find what already exists.

Retrieve by ROLE, never by raw similarity

This is the load-bearing rule, not a style preference: similarity-retrieved "here's similar code, paste it" measurably HURTS — up to −15% Pass@1 (arXiv:2503.20589). What helps is API/type-signature context (+17-20%) and dependency-graph-structured retrieval (+6 EM; enabled 5/6 multi-file edits vs 0/6 without a graph). ripwire's shape — signatures + call-graph + role-ranked exemplars — is the validated retrieval shape; "find me a similar-looking snippet" is the anti-pattern to avoid, even though it's the tempting first instinct.

Before you write a function / class / util

  1. Find the building block first — ripwire <dir> --for="<what you're about to build>" → ranked existing signatures (plus, when the code has them, the <lego> / <compose> HAS-A blocks — what a class already owns; a block that would cost more than its count arrives as a counted stub, shown="0" with a next=, and --sections=lego,compose restores both in full). If you can name the helper you suspect exists, query it verbatim (--for="parseByteSize") — --for auto-routes to name-exact retrieval and lands it at recall@1 ~99%. It also carries the quality lens (cx/ccx/in/churn/amp/tested) so you see which candidates are safe to extend. Often the thing exists — compose from it.
  2. Optionally get a style/shape exemplar — if the retrieval result leaves a local-idiom question, ripwire <dir> --exemplar=fn|method|class|struct|iface|var --legend=compact (a kind) or --exemplar="<task in words>" (the top match's kind is inferred) returns the repo's single best-in-class instance of that shape: highest fan-in, lowest cognitive complexity, tested=1 where possible — selected by ROLE, not text similarity. It returns the full body under <bodies>. Copy its shape (structure, error handling, naming), not its text — it is a model to imitate, not a relevant-code search.
  3. Find candidates by behavior/shape — ripwire <dir> --grep="<a word from the behavior>" --legend=compact, or a NARROWED graph query: --graph-query='and(file(all,"<area>"),kind(all,fn))'. (Bare kind(all,fn) is ranked by importance + capped at --top-k, so it's safe — but narrowing by file()/name()/callers() finds the relevant building block, not just the globally-important one.) → implementations to reuse or extend.
  4. Don't duplicate — ripwire <dir> --clones --legend=compact → if your intended body matches an existing one, call it instead. Rule of Three: extract a shared helper on the third occurrence, not the second — and prefer a little duplication over the wrong abstraction (a helper you bend with boolean flags is worse than two honest copies).
Show full SKILL.md (220 more words)Show less

Before you add a dependency

  1. Is it already here? — ripwire <dir> --external-surface --legend=compact (what the tree already depends on; the default is a 100-row window with the sh builtins dropped and counted as builtins_excluded= — --include-builtins keeps them) and --uses=NAME (the import role). Reuse an in-tree dependency before adding a new one: a new dep is build weight, supply-chain surface, and one more thing every reader must learn — it has to earn its place.
  2. Before adding/vendoring a NEW dependency, map the candidate repo first — ripwire <git-url> (https:// or git@; shallow-clones to a temp cache dir, then maps it like any local tree — --refetch forces a fresh clone instead of reusing the cached one). Run --report/--hotspots/--deps on it before you commit to the dependency: is it actually small and well-factored, or a god-file waiting to become your problem?

When you do write

  • Match the local idiom — ripwire <dir> --for="<the area>" shows the surrounding naming, layout, and error-handling style. Mirror it so your diff reads like the file, not like a graft (cache-friendly for the reader and for KV-cache reuse).
  • Less code wins on every metric at once: lower complexity, fewer call edges, smaller blast radius, less to test, less to read. When in doubt, delete a parameter before adding one.

Then hand off to ripwire-quality-bar before you call it done.

© redhat-et, Apache-2.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in skills/ripwire-reuse-first of redhat-et/ripwire.

Open the folder on GitHubat commit 0852bc0

Compare with similar skills

Ripwire Reuse First next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Ripwire Reuse First compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Ripwire Reuse First this skillredhat-et/ripwire2.4k—~1.3kAutomated safety check: NotesApache-2.0
Symbols APIJetBrains/intellij-community21k—~2.7kAutomated safety check: PassCustom licence
Diagnosing Stacktrace SymbolicationPostHog/posthog40k—~2.2kAutomated safety check: PassCustom licence
Poly SymbolsJetBrains/intellij-community21k—~4.2kAutomated safety check: PassCustom licence
Android Tombstone Symbolicationdotnet/skills5.6k1 repos~2.1kAutomated safety check: PassMIT
Octopus Quicknyldn/claude-octopus4.2k1 repos~2.2kAutomated safety check: PassMIT

Similar skills

  • Symbols API

    JetBrains/intellij-community

    Official

    Use IntelliJ Symbol API for declarations, references, and rename.

    21k GitHub stars~2.7k tokensUpdated today
    Auto-check passed
  • Official

    Help users debug PostHog Error Tracking stack-trace symbolication for any supported platform — JavaScript/TypeScript web, React Native (Hermes), Android (Proguard / R8), or iOS / macOS (dSYM).

    40k GitHub stars~2.2k tokensUpdated today
    MobileAuto-check passed
  • Poly Symbols

    JetBrains/intellij-community

    Official

    Implement PolySymbols completion, references, and rename. An agent skill from JetBrains/intellij-community.

    21k GitHub stars~4.2k tokensUpdated today
    Auto-check passed
  • Official

    Resolves native crash frames from .NET Android tombstones to function names, source files and line numbers using BuildIds, Microsoft's symbol server and llvm-symbolizer.

    5.6k GitHub starsUsed in 1 repo~2.1k tokens
    MobileAuto-check passed
  • Octopus Quick

    nyldn/claude-octopus

    Quick execution for ad-hoc tasks without full workflow overhead — use for small, self-contained requests

    4.2k GitHub starsUsed in 1 repo~2.2k tokens
    DevelopmentAuto-check passed
  • GSD Quick Batch

    open-gsd/gsd-core

    Runs several small /gsd-quick tasks as one batch, with a single coordinator that plans them, dispatches workers per item and owns all shared writes and worktree merges.

    10k GitHub stars~1.4k tokensUpdated today
    Agent WorkflowsAuto-check: notes

More from redhat-et/ripwire

All 19 skills in this repo
  • Ripwire Output Emission

    redhat-et/ripwire

    Rules for writing and converting formatted output in ripwire's C++ source with its emit helpers, keeping every printed byte identical to the old printf output.

    2.4k GitHub stars~1k tokensUpdated today
    Auto-check passed
  • Ripwire Change Check

    redhat-et/ripwire

    Checks whether a working-tree diff or a pull request is safe to merge: blast radius, tests to run, contract breaks, branch conflicts and stranded work.

    2.4k GitHub stars~4.4k tokensUpdated today
    Auto-check: notes
  • Ripwire Graph Query

    redhat-et/ripwire

    Answers call-graph questions that combine several conditions, such as complex functions that reach a target or untested symbols near main, using ripwire's graph-query mode.

    2.4k GitHub stars~1.1k tokensUpdated today
    Auto-check: notes
  • Ripwire Subsystem Handoff

    redhat-et/ripwire

    Produces a short brief for handing a code subsystem to a teammate or fresh session, using ripwire to rank symbols, expand bodies and surface design docs.

    2.4k GitHub stars~1.8k tokensUpdated today
    Auto-check: notes
  • Ripwire Code Navigation

    redhat-et/ripwire

    Answers questions about a named symbol, such as its callers, what it calls, the path between two symbols or the downstream impact of changing it, using the ripwire CLI.

    2.4k GitHub stars~4.8k tokensUpdated today
    Auto-check: notes
  • Contributor guide for reading clang optimization remarks while editing ripwire's own C++, deciding between a source change and a build change such as LTO or PGO.

    2.4k GitHub stars~3.1k tokensUpdated today
    Auto-check: notes

Questions about Ripwire Reuse First

What does Ripwire Reuse First do?

About to write ONE symbol (even a 'quick' one-liner) or add a dependency: reuse before you reinvent. Ripwire Reuse First is an agent skill from redhat-et/ripwire. About to write ONE symbol (even a 'quick' one-liner) or add a dependency: reuse before you reinvent.

How do I install Ripwire Reuse First in Claude Code?

Run `npx skills add redhat-et/ripwire --skill ripwire-reuse-first -a claude-code`. Or copy the skill folder (skills/ripwire-reuse-first in redhat-et/ripwire) into .claude/skills/ripwire-reuse-first in your project. Claude Code loads it when a task matches its description.

How do I install Ripwire Reuse First in Codex?

Run `npx skills add redhat-et/ripwire --skill ripwire-reuse-first -a codex`. Or copy the skill folder (skills/ripwire-reuse-first in redhat-et/ripwire) into .agents/skills/ripwire-reuse-first in your project. Codex loads it when a task matches its description.

Can I use Ripwire Reuse First in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add redhat-et/ripwire --skill ripwire-reuse-first -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/ripwire-reuse-first, .gemini/skills/ripwire-reuse-first, .github/skills/ripwire-reuse-first and .opencode/skills/ripwire-reuse-first in your project.

What does Ripwire Reuse First need to run?

SKILL.md names no scripts, command-line tools or credentials: Ripwire Reuse First is instructions for the agent only. Its frontmatter pre-approves these tools: Bash, Read.

Does Ripwire Reuse First access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Ripwire Reuse First safe to install?

Our automated static check of SKILL.md found notes only (pre-approves every shell command (allowed-tools: bash)), nothing it rates as a warning. It is not a guarantee. Review the folder before installing.

What licence does Ripwire Reuse First use?

Ripwire Reuse First is published under the Apache-2.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Ripwire Reuse First use?

About 1.3k tokens (SKILL.md is roughly 5.3k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Ripwire Reuse First?

Skills that share tags, products or a category with Ripwire Reuse First: Symbols API (JetBrains/intellij-community, 21k stars), Diagnosing Stacktrace Symbolication (PostHog/posthog, 40k stars), Poly Symbols (JetBrains/intellij-community, 21k stars) and Android Tombstone Symbolication (dotnet/skills, 5.6k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Ripwire Reuse First?

redhat-et (a GitHub organization) maintains it in redhat-et/ripwire, which has 2,430 GitHub stars. The repository holds 19 skills in this directory. The repository was last updated on October 10, 2026.

Source: redhat-et/ripwire on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.