What is steering-matcher?

A path-matching tool that finds which steering files apply to the files being changed. Steering files contain project-specific instructions for particular parts of a codebase.

Use it to determine applicable guidance for changed files or to inject matching instructions into an agent's context.

It prevents agents from loading unrelated instructions and helps them use the guidance intended for each file. This keeps task context focused on the relevant project rules.

steering-matcher — Skill for Claude Code by rjmurillo/ai-agents

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent

npx skills add rjmurillo/ai-agents --skill steering-matcher

Clone the repo

git clone --depth 1 https://github.com/rjmurillo/ai-agents

Made for: Claude Code.

Or install project-toolkit, the plugin that ships this one along with the rest of its 125 skills, 25 commands, 33 agents, 5 hooks.

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/rjmurillo/ai-agents/steering-matcher/github.svg)](https://agentmods.dev/skills/rjmurillo/ai-agents/steering-matcher)

Your own site

<a href="https://agentmods.dev/skills/rjmurillo/ai-agents/steering-matcher"><img src="https://agentmods.dev/badge/skills/rjmurillo/ai-agents/steering-matcher/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/rjmurillo/ai-agents/steering-matcher"><img src="https://agentmods.dev/badge/skills/rjmurillo/ai-agents/steering-matcher.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 82 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,139 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. Third-party audits

NVIDIA SkillSpector warn 7 Sept 2026

SkillSpector: 1 finding, up to medium

These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →

medium Excessive Agency · line 7
Skill selects an external model or provider that may use a different account or billing plan than the operator expects. Undisclosed model switches can cause unexpected cost or quota consumption.

Fix: Remove the model/provider override or disclose it prominently and require explicit operator approval before invoking an external coding CLI or billed model.

How audits are shown

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	$0.00082	$0.01139
Opus 5.5	$0.00033	$0.00456
Sonnet 5.5	$0.00016	$0.00228
Haiku 4.5	$0.00008	$0.00114

Measured 18d ago against content hash 8755368c0043, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

steering-matcher 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 18d ago.

The scan reads SKILL.md. This mod also ships 2 executable files (get_applicable_steering.py, scripts/get_applicable_steering.py), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

.claude/skills/steering-matcher/SKILL.md · 131 lines

How it starts

The opening of the file, as written. The whole thing — 131 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Steering File Matcher Skill

Triggers

Trigger Phrase	Operation
`match steering for these files`	get_applicable_steering.py
`which steering applies to this task`	Pattern match against changed files
`inject steering context`	Return applicable steering sorted by priority

Purpose

This skill helps orchestrator determine which steering files to inject into agent context based on the files being modified.

Match file paths against glob patterns in steering file front matter
Return applicable steering files sorted by priority
Enable token-efficient context injection (30%+ savings)

When to Use

Use this skill when:

Orchestrator needs to inject context-aware steering based on files being modified
You want to scope agent guidance to only relevant files (token optimization)
Matching file paths against applyTo glob patterns in steering front matter

Use manual file reading instead when:

You already know which steering file applies
The task affects a single known steering domain

Quick Usage

Using get_applicable_steering.py Script

The script in .claude/skills/steering-matcher/scripts/get_applicable_steering.py handles pattern matching.

# Match files against steering patterns
python3 .claude/skills/steering-matcher/scripts/get_applicable_steering.py \
    --files "src/claude/analyst.md" ".project-toolkit/security/TM-001-auth-flow.md" \
    --steering-path ".agents/steering"

# Output: JSON array of objects with name, path, apply_to, priority

Process

This skill integrates with the orchestrator workflow:

Task Analysis: Orchestrator identifies files affected by task
Pattern Matching: Use this skill to find applicable steering
Context Injection: Include matched steering in agent prompt
Token Optimization: Only inject relevant guidance

Standard Orchestrator Workflow

# 1. Identify files from task
# 2. Get applicable steering
python3 .claude/skills/steering-matcher/scripts/get_applicable_steering.py \
    --files "src/claude/security.md" ".project-toolkit/security/SR-001-oauth-review.md"

# 3. Inject into agent context
# Output: JSON with name, path, apply_to, priority sorted by priority descending

Read the full file on GitHub · 131 lines

Files

What ships with it

2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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.

18d ago Changed 8755368c0043
22d ago Changed · +5 lines ba192ccdf255
24d ago Changed a2d485f19d02
1mo ago First seen · 126 lines · 82 tokens per session scan A 267193c275ad

Subscribe to this mod's changes

steering-matcher is a skill published in the GitHub repository rjmurillo/ai-agents (48 stars, last pushed today), licensed MIT. It adds 82 tokens to every session and 1,139 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 2026-09-03.

Building agents CI and CD Claude Code Code review agentic-ai ai-agents developer-tools github-copilot

install-gemini-code-review-action

Installs, configures, or upgrades Dazbo's PR code review & issue triage GitHub Action (gemini-review-action) in a target repository. Use when the user wants to set up, configure, or update automated AI code reviews, issue triaging, or Gemini model workflows for their GitHub repository.

derailed-dash/dazbo-agent-skills · 73 tokens

steering-matcher