generate-path-instructions

generate-path-instructions is a skill for Claude Code, Codex from canonical/copilot-collections. It costs 89 tokens per session (1,771 once invoked), scanned A, original, Apache-2.0.

A generator for path-specific instruction files in .github/instructions/. It analyses a repository and creates rules that load only for matching files, such as tests, framework code, or particular directories.

In plain words
What is it for?
Use it to create scoped guidance for directory-specific, file-type-specific, or framework-specific development and testing.
Why use it?
It keeps specialised rules out of unrelated work and makes them available when the relevant files are opened.

Skill for Claude CodeCodex ✓ vendor

Written for no agent in particular: nothing here depends on one.

Needs its repository: it runs a file that does not travel with it, so clone the repository first. The line is python3 .github/skills/generate-agent-skills/scripts/validate_skill.py --path .github/instructions/.

Good fit Use it to create scoped guidance for directory-specific, file-type-specific, or framework-specific development…

Compare 6 skills from other repositories ↓
About the project

Canonical Copilot Collections is a repository for organizing and distributing GitHub Copilot instructions, prompts, agents, and skills across Canonical repositories. Teams configure repositories to subscribe to shared collections, such as Python, documentation, or Juju development guidance, and keep those assets synchronized.

canonical/copilot-collections · 29 stars · on GitHub

Install

Getting it into your agent

It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.

Clone the repo
git clone --depth 1 https://github.com/canonical/copilot-collections
agentmods
npx agentmods add skills/canonical/copilot-collections/generate-path-instructions

Made for: Claude Code, Codex.

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.

agentmods badge for generate-path-instructions

README.md
[![agentmods](https://agentmods.dev/badge/skills/canonical/copilot-collections/generate-path-instructions.svg)](https://agentmods.dev/skills/canonical/copilot-collections/generate-path-instructions)
Your own site
<a href="https://agentmods.dev/skills/canonical/copilot-collections/generate-path-instructions"><img src="https://agentmods.dev/badge/skills/canonical/copilot-collections/generate-path-instructions.svg" alt="Measured on agentmods" height="20"></a>
Per session 89 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,771 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.
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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00089 $0.01771
Opus 5 $0.00044 $0.00886
Sonnet 5 $0.00018 $0.00354
Haiku 4.5 $0.00009 $0.00177

Measured 7d ago against content hash 3b66b49de9b1, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

generate-path-instructions 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 7d ago.

The scan reads SKILL.md. This mod also ships 1 executable file (scripts/test_glob_pattern.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.

.github/skills/generate-path-instructions/SKILL.md · 226 lines

How it starts

The opening of the file, as written. The whole thing — 226 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Path-Specific Instructions Generator

Overview

This skill generates scoped .github/instructions/*.md files that load Just-In-Time (JIT) when specific files are opened. It autonomously analyzes your repository to discover file patterns, extract scope-specific rules from existing code and documentation, and generate precise glob patterns for targeted instruction loading.

Key advantages over global instructions:

  • Context Economics: Load rules only when needed (vs always-on global instructions)
  • Higher Priority: Path instructions override global instructions
  • Precision: Target specific frameworks, file types, or directories

Key principle: Leverage LLM strengths for pattern discovery and rule extraction rather than manual specification.


Workflow

Step 1: Intent Validation

Confirm the user wants path-specific instructions (not global).

Decision tree:

  • User wants scoped/directory/framework-specific rules? → Continue to Step 2
  • User wants global repository instructions?
    • → STOP. Redirect them to use generate-repo-instructions skill instead
    • Explain: Global instructions go in .github/copilot-instructions.md
  • User wants a custom agent or skill?
    • → STOP. Clarify asset type using Asset Decision Matrix
    • Agent = role-based, Skill = capability-based, Instructions = rules

Proceed only if creating path-specific instructions.


Step 2: Scope Discovery

Goal: Understand what files/directories to target and what patterns exist.

Load the scope analysis checklist:

cat references/scope_analysis_checklist.md

Work through the checklist to discover:

  1. Target identification - What files does the user want to scope?
  2. Repository exploration - What file patterns actually exist?
  3. Framework detection - What tools/frameworks are in use?
  4. Existing conventions - What patterns are already established?

Output: Clear understanding of target scope with concrete file examples.

Read the full file on GitHub · 226 lines

Files

What ships with it

6 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.

  1. 7d ago First seen · 226 lines · 89 tokens per session scan A 3b66b49de9b1

Subscribe to this mod's changes

generate-path-instructions is a skill published in the GitHub repository canonical/copilot-collections (29 stars, last pushed 4d ago), licensed Apache-2.0. It adds 89 tokens to every session and 1,771 once invoked, about $0.0004 per session on Opus 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 2026-08-30.

Related

Other skills, from other repositories

incident-postmortem-report

Produce a thorough incident post-mortem report after an outage or customer-impacting event. Covers executive summary, impact, detailed timeline, root cause, contributing factors, corrective and preventive actions, and lessons learned. Use when the user asks to write, draft, or complete a post-mortem, blameless review…

caipe-io/ai-platform-engineering · 76 tokens

documentation-search

Search the internal knowledge base for runbooks, architecture documentation, ADRs, best practices, and troubleshooting guides using RAG. Use when looking for internal documentation, deployment procedures, architecture decisions, or operational runbooks.

caipe-io/ai-platform-engineering · 46 tokens

incident-investigation

Correlate PagerDuty incidents with Jira tickets and recent ArgoCD deployments to accelerate root cause analysis. Orchestrates multiple agents to build a timeline of events. Use when investigating active incidents, performing post-mortems, or correlating alerts with changes.

caipe-io/ai-platform-engineering · 56 tokens

review-specific-pr

Perform a comprehensive code review of a specific GitHub Pull Request. Analyzes code changes, checks for bugs, security issues, test coverage, and coding standards compliance. Use when a user provides a PR URL or asks to review a specific pull request.

caipe-io/ai-platform-engineering · 55 tokens

oncall-handoff

Generate a comprehensive on-call handoff document by aggregating open incidents, ongoing issues, recent deployments, and systems to watch. Orchestrates PagerDuty, Jira, and ArgoCD agents. Use during on-call rotation changes or shift handoffs.

caipe-io/ai-platform-engineering · 55 tokens

sprint-progress-report

Generate a comprehensive sprint progress report from Jira with velocity metrics, burndown analysis, blocker identification, and team workload distribution. Use when preparing sprint reviews, standups, or tracking sprint health mid-cycle.

caipe-io/ai-platform-engineering · 46 tokens