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.
npx agentmods add skills/bostonorange/claude-code-framework/add-referencenpx skills add BostonOrange/claude-code-framework --skill add-referencegit clone --depth 1 https://github.com/BostonOrange/claude-code-frameworkWhat 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 | $0.00042 | $0.00678 |
| Opus 5 | $0.00021 | $0.00339 |
| Sonnet 5 | $0.00008 | $0.00136 |
| Haiku 4.5 | $0.00004 | $0.00068 |
Grade A, and why
add-reference 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 yesterday.
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.
How it starts
The opening of the file, as written. The whole thing — 124 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Add Reference
Create or update structured reference documentation under a skill's references/ directory.
Usage
/add-reference my-domain entities # Update entity inventory
/add-reference my-domain api-endpoints # Document API surface
/add-reference my-domain # Update all references for skill
/add-reference my-domain new-topic # Create new reference
Reference Types
Domain Knowledge
Business rules, regulations, external system behavior. Not generated from code.
Codebase Inventories
Generated by scanning project source. Kept in sync as codebase evolves.
Process
1. Determine Scope
Parse skill name and topic. If no topic, update all references.
2a. Domain Knowledge
- Ask user for source material
- If none, scan codebase for clues
- Structure with tables and categories
- Include source attribution
2b. Codebase Inventories
Scan relevant directories:
| Reference Type | What to Extract |
|---|---|
| Entities/Models | Names, key fields, types, relationships |
| Classes/Modules | Names, purpose, category, key methods |
| API Endpoints | Routes, methods, parameters, responses |
| Configuration | Config keys, types, defaults |
| Test Helpers | Factories, fixtures, builder patterns |
3. Generate or Update
- Existing file: Read current, merge new findings, preserve manual notes
- New file: Create using formats below
Write to: .claude/skills/{skill}/references/{topic}.md
Output Formats
Domain Knowledge
# {Topic} Reference
## Overview
{One paragraph context}
## {Category}
| {Key Column} | {Details} | {Notes} |
|--------------|-----------|---------|
## Source
{Attribution}
Codebase Inventory — Entities
# {Skill} Entities Reference
## {Entity_Name}
**Purpose:** {one-line description}
| Property | Type | Notes |
|----------|------|-------|
| `field` | String | {note} |
**Key Relationships:**
- Parent: `ParentEntity` via `parent_id`
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.
- yesterday First seen · 124 lines · 42 tokens per session scan A 6eb9b01517ae
add-reference is a skill published in the GitHub repository BostonOrange/claude-code-framework (2 stars, last pushed 1mo ago), licensed MIT. It adds 42 tokens to every session and 678 once invoked, about $0.0002 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 2026-08-31.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
babysit-pr
Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…
imagegen
Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…