New: 98,000+ skills indexed from GitHub repos with 100+ stars · every skill safety-checkedBrowse top skillsTop skills
Esc to closeBrowse all skills
Submit a skillBrowse skills
Submit a skillBrowse skills

Agent skill

Context Routing Audit

by withkynam in withkynam/vibecode-pro-max-kit

Audits a project's context routing, skill discoverability and skill wiring by running a chain of validator scripts and fixing whatever they report.

MITAuto-check passedAgent Workflows

Install Context Routing Audit

skills CLI
$ npx skills add withkynam/vibecode-pro-max-kit --skill vc-audit-context -a claude-code

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

GitHub CLI
$ gh skill install withkynam/vibecode-pro-max-kit vc-audit-context --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/withkynam/vibecode-pro-max-kit.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.claude/skills/vc-audit-context .claude/skills/vc-audit-context && 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
vc-audit-context
GitHub stars
1.1k
Token cost
~1.2k tokens
SKILL.md length
442 words
Files
12 (incl. scripts, references)
Skills in repo
32
Repo updated
First seen
Licence
MIT

At a glance

Audits a project's context routing, skill discoverability and skill wiring by running a chain of validator scripts and fixing whatever they report.

  • Works in 4 steps: Run find process/context/ -type f | sort… → Read process/context/all-context.md for… → Read references/audit-context.md for the… → …
  • Checking that context docs are still routed correctly after a move or split
  • SKILL.md covers Workflow, Context Bootstrap (when… and Rules
  • Runs JavaScript scripts from its folder; calls node

What it does

This skill checks that a project's durable context layer is discoverable and well organized. The agent lists the files in process/context/, reads the context routing protocol and the audit reference, then runs a series of Node validators: context discovery, protocol discovery frontmatter, shared-skill routing coverage, skill cross-references, dependency and confusable-skill analysis, and keyword and layer checks on every SKILL.md.

It can also regenerate or check a machine-readable skills catalog. When a script reports failures, the agent inspects the files it names, patches the smallest relevant surface and re-runs the failed validators until they pass. You can give an optional scope, such as a context group, agent, skill or folder, to prioritize. Output should be answer-first and in plain language, and harness checks for agent parity or README sync belong to the separate audit-vc skill.

When your agent uses it

  • Checking that context docs are still routed correctly after a move or split
  • Verifying that every skill has trigger keywords and a valid layer
  • Finding confusable or poorly cross-referenced skills
  • Regenerating the skills catalog and confirming it is in sync

Example prompts

  • “Audit the context routing now that I have split the process/context docs.”
  • “Run the skill validators and fix any failing cross-references.”
  • “Check that every SKILL.md has trigger keywords and that the catalog is up to date.”

Requirements

  • Node.js to run the validator scripts
  • A project laid out with process/context/ and .claude/skills/

Workflow steps

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

  1. Run find process/context/ -type f | sort to get the full file listing before routing.
  2. Read process/context/all-context.md for the context routing protocol.
  3. Read references/audit-context.md for the full audit process.
  4. Run the context discovery validator

What it can do on your machine

Read from SKILL.md and the folder at commit 3bcb2f9. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Ships 9 files in scripts/ (JavaScript), which the agent can run.

    Shell commands in SKILL.md call:

    • node

    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

Context Routing Audit loads about 1.2k tokens when it runs, and up to ~2.5k if it reads all its reference files. Until then it costs about 41 tokens; SKILL.md has 442 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~41
When it runs · the whole SKILL.md, loaded when a task matches
~1.2k
With references · SKILL.md plus every file in references/, read only if the agent opens them
~2.5k

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 passed

The automated check found no risky patterns in SKILL.md.

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); the scripts in this folder are not scanned.

SKILL.md

The full file from withkynam/vibecode-pro-max-kit at commit 3bcb2f9, republished under its MIT licence (© withkynam). 442 words, ~1,158 tokens.

Download SKILL.mdSave it as .claude/skills/vc-audit-context/SKILL.md (or your agent's skills folder). This skill also uses 11 other files; get the full folder from GitHub.
name
vc-audit-context
description
Audit project context routing, shared-skill discoverability, and Claude/Codex wiring. Use when context docs or skill surfaces move, split, or drift.
trigger_keywords
audit context, context gaps, context routing audit, discoverability
layer
contract
metadata.author
vibecode-pro-max-kit
metadata.version
1.0.0

Audit Context

Output style: Follow process/development-protocols/communication-standards.md — answer-first, plain language, no unexplained jargon, TL;DR on long responses.

Use this skill to verify that the project's durable context layer is discoverable and organized.

Optional input: a context group, agent, skill, or folder scope to prioritize during the audit.

Workflow

  1. Run find process/context/ -type f | sort to get the full file listing before routing. This ensures no context file is silently skipped when the router is incomplete or drifted.
  2. Read process/context/all-context.md for the context routing protocol.
  3. Read references/audit-context.md for the full audit process.
  4. Run the context discovery validator:
    bash
    node .claude/skills/vc-audit-context/scripts/validate-context-discovery.mjs

3a. Run the protocol discovery frontmatter validator (enforces discovery frontmatter on every process/development-protocols/**/*.md, recursive incl. vc-system-behavior/; note.md is the only intentional exclusion):

bash
node .claude/skills/vc-audit-context/scripts/validate-protocol-discovery.mjs
  1. Run the shared skill routing coverage validator:
    bash
    node .claude/skills/vc-audit-context/scripts/validate-skill-routing.mjs
  2. Run the skill cross-reference validator:
    bash
    node .claude/skills/vc-audit-context/scripts/validate-skill-cross-refs.mjs
  3. Run the skill dependency/confusable analysis:
    bash
    node .claude/skills/vc-audit-context/scripts/validate-skill-dependencies.mjs
node .claude/skills/vc-audit-context/scripts/validate-confusable-skills.mjs
  4. Regenerate or check the machine-readable skill catalog:
    bash
    node .claude/skills/vc-audit-context/scripts/generate-skills-catalog.mjs --write
node .claude/skills/vc-audit-context/scripts/generate-skills-catalog.mjs --check
  5. Validate that every SKILL.md carries trigger_keywords + a valid layer (contract|helper) and that the catalog is in sync:
    bash
    node .claude/skills/vc-audit-context/scripts/validate-skill-keywords.mjs
  6. If any script reports failures, inspect the referenced files and patch the smallest relevant surface.
  7. Re-run the failed validators until they pass.

For agent/skill harness validation (agent parity, skill frontmatter, README.md sync, protocol wiring), use the audit-vc skill.

Show full SKILL.md (235 more words)Show less

Context Bootstrap (when process/context/ doesn't exist or needs full init)

Use when initializing a new project's context layer from scratch:

  1. Run vc-scout in parallel across major source directories (skip .git, node_modules, .claude, caches) to gather codebase summaries.
  2. Create process/context/all-context.md (routing table, architecture, conventions) and group all-{group}.md entrypoints for any durable domains identified.
  3. Parallel reader strategy for existing context files — before updating, spawn subagents proportional to file count: 1-3 files read directly; 4-6 files use 2-3 reader agents; 7+ files use 4-5 reader agents (max 5), distributing by LOC.
  4. After generating or updating context files, run find process/context -name '*.md' -print0 | xargs -0 wc -l | sort -rn — files over 800 LOC should be split into a context group or the user asked.
  5. Finish by running the discovery validator (step 3 above) before declaring done.

Rules

  • Treat .claude/skills/ as canonical; .agents/skills/ is the Codex discovery symlink.
  • Treat .claude/skills/vc-audit-context/references/skill-routing-policy.json as the explicit allowlist for intentionally non-routed shared skills.
  • Do not move large context files without updating process/context/all-context.md.
  • Do not delete compatibility wrappers unless no current reference points to them.
  • Keep context groups durable-domain based, not one group per temporary feature.
  • When updating agents, mirror Claude markdown and Codex TOML surfaces together.
  • Treat validator warnings as audit findings unless the user asks for a strict cleanup.
  • Prefer validator-backed routing truth over adding more soft prose.
  • Treat process/context/generated-skills-catalog.json as the machine-readable catalog owned by audit-context.

© withkynam, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 11 other files (scripts, references) in .claude/skills/vc-audit-context of withkynam/vibecode-pro-max-kit.

  • SKILL.md
  • references/audit-context.md
  • references/skill-routing-policy.json
  • scripts/generate-skills-catalog.mjs
  • scripts/shared-skill-utils.mjs
  • scripts/validate-confusable-skills.mjs
  • scripts/validate-context-discovery.mjs
  • scripts/validate-protocol-discovery.mjs
  • scripts/validate-skill-cross-refs.mjs
  • scripts/validate-skill-dependencies.mjs
  • scripts/validate-skill-keywords.mjs
  • scripts/validate-skill-routing.mjs

Open the folder on GitHubat commit 3bcb2f9

Compare with similar skills

Context Routing Audit 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.

Context Routing Audit compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Context Routing Audit this skillwithkynam/vibecode-pro-max-kit1.1k—~1.2kAutomated safety check: PassMIT
Claude Code Cost Optimizermergisi/awesome-openclaw-agents4k—~1.1kAutomated safety check: PassMIT
Aspens Multi-Target Outputaspenkit/aspens102—~1.9kAutomated safety check: PassMIT
Using Agent Skillsaddyosmani/agent-skills103k4 repos~2.4kAutomated safety check: PassMIT
Task Observerrebelytics/one-skill-to-rule-them-all3.2k1 repos~12kAutomated safety check: PassCC-BY-4.0
Context Engineeringabashev/vfs-s31069 repos~2.6kAutomated safety check: NotesApache-2.0

Similar skills

  • Claude Code Cost Optimizer

    mergisi/awesome-openclaw-agents

    Audits a project's Claude Code setup for common token-cost leaks and returns a prioritized fix list, using only static inspection of files and settings.

    4k GitHub stars~1.1k tokensUpdated 11 days ago
    Agent WorkflowsAuto-check passed

  • Aspens Multi-Target Output

    aspenkit/aspens

    Explains how the aspens generator routes output to Claude Code or Codex CLI targets and transforms generated skills and instruction files between their formats.

    102 GitHub stars~1.9k tokensUpdated 25 days ago
    Agent WorkflowsAuto-check passed

  • Using Agent Skills

    addyosmani/agent-skills

    Meta-skill for choosing which workflow skill fits the task at hand, plus always-on habits: surface assumptions, stop on confusion, push back, keep it simple and stay in scope.

    103k GitHub starsUsed in 4 repos~2.4k tokens
    Agent WorkflowsAuto-check passed

  • Task Observer

    rebelytics/one-skill-to-rule-them-all

    Monitors task execution for skill improvement opportunities.

    3.2k GitHub starsUsed in 1 repo~12k tokens
    Agent WorkflowsAuto-check passed

  • Context Engineering

    abashev/vfs-s3

    Optimizes agent context setup. An agent skill from abashev/vfs-s3.

    106 GitHub starsUsed in 9 repos~2.6k tokens
    Agent WorkflowsAuto-check: notes

  • Rules Distillation

    affaan-m/ECC

    Scans installed skills for principles that recur across them and proposes rule-file changes: append, revise, add a section, create a file or leave as covered.

    275k GitHub starsUsed in 2 repos~2.3k tokens
    Agent WorkflowsAuto-check passed

More from withkynam/vibecode-pro-max-kit

All 32 skills in this repo

  • Library Documentation Seeker

    withkynam/vibecode-pro-max-kit

    Looks up library and framework documentation through Context7 first, with bundled Node scripts as a fallback that fetch and analyze llms.txt files.

    1.1k GitHub starsUsed in 2 repos~1k tokens
    Auto-check: notes

  • Vc Sequential Thinking

    withkynam/vibecode-pro-max-kit

    Apply step-by-step analysis for complex problems with revision capability.

    1.1k GitHub starsUsed in 2 repos~854 tokens
    Auto-check passed

  • Agent Browser Automation

    withkynam/vibecode-pro-max-kit

    Drives a browser through the agent-browser CLI, using compact snapshots with element refs to keep context small in long sessions, plus video recording and cloud browsers.

    1.1k GitHub stars~2.6k tokensUpdated 3 mo ago
    Auto-check passed

  • Active Plan Audit

    withkynam/vibecode-pro-max-kit

    Reviews a codebase's active plan files for staleness and completion, then archives only the ones confirmed done or obsolete against the real code.

    1.1k GitHub stars~757 tokensUpdated 3 mo ago
    Auto-check passed

  • Systematic Debugging and Investigation

    withkynam/vibecode-pro-max-kit

    Forces root-cause investigation before any fix, combining a four-phase debugging method with log, CI and performance investigation techniques and a rule against unverified completion claims.

    1.1k GitHub stars~1.5k tokensUpdated 3 mo ago
    Auto-check passed

  • Repository Context Generator

    withkynam/vibecode-pro-max-kit

    Generates or refreshes a project's shared repository context file so both Codex and Claude work from the same up-to-date knowledge layer.

    1.1k GitHub stars~817 tokensUpdated 3 mo ago
    Auto-check passed

Categories

Questions about Context Routing Audit

What does Context Routing Audit do?

Audits a project's context routing, skill discoverability and skill wiring by running a chain of validator scripts and fixing whatever they report. This skill checks that a project's durable context layer is discoverable and well organized.md.

When should I use Context Routing Audit?

Context Routing Audit fits situations like: checking that context docs are still routed correctly after a move or split; verifying that every skill has trigger keywords and a valid layer; finding confusable or poorly cross-referenced skills; regenerating the skills catalog and confirming it is in sync.

How do I install Context Routing Audit in Claude Code?

Run `npx skills add withkynam/vibecode-pro-max-kit --skill vc-audit-context -a claude-code`. Or copy the skill folder (.claude/skills/vc-audit-context in withkynam/vibecode-pro-max-kit) into .claude/skills/vc-audit-context in your project. Claude Code loads it when a task matches its description.

How do I install Context Routing Audit in Codex?

Run `npx skills add withkynam/vibecode-pro-max-kit --skill vc-audit-context -a codex`. Or copy the skill folder (.claude/skills/vc-audit-context in withkynam/vibecode-pro-max-kit) into .agents/skills/vc-audit-context in your project. Codex loads it when a task matches its description.

Can I use Context Routing Audit 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 withkynam/vibecode-pro-max-kit --skill vc-audit-context -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/vc-audit-context, .gemini/skills/vc-audit-context, .github/skills/vc-audit-context and .opencode/skills/vc-audit-context in your project.

What does Context Routing Audit need to run?

Going by SKILL.md and its folder, Context Routing Audit needs JavaScript for the scripts in its folder and the command-line tools its instructions call (node). Our summary lists: Node.js to run the validator scripts; A project laid out with process/context/ and .claude/skills/.

Does Context Routing Audit 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 Context Routing Audit safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. The check reads SKILL.md only: the scripts in the folder are not scanned, so read them before running anything.

What licence does Context Routing Audit use?

Context Routing Audit is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Context Routing Audit use?

About 1.2k tokens (SKILL.md is roughly 4.6k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 1.4k tokens, read only when the agent opens those files.

What are the alternatives to Context Routing Audit?

Skills that share tags, products or a category with Context Routing Audit: Claude Code Cost Optimizer (mergisi/awesome-openclaw-agents, 4k stars), Aspens Multi-Target Output (aspenkit/aspens, 102 stars), Using Agent Skills (addyosmani/agent-skills, 103k stars) and Task Observer (rebelytics/one-skill-to-rule-them-all, 3.2k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Context Routing Audit?

withkynam (a GitHub user) maintains it in withkynam/vibecode-pro-max-kit, which has 1,145 GitHub stars. The repository holds 32 skills in this directory. The repository was last updated on June 21, 2026.

Source: withkynam/vibecode-pro-max-kit on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.