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/frap129/opencode-rules/crafting-rulesnpx skills add frap129/opencode-rules --skill crafting-rulesgit clone --depth 1 https://github.com/frap129/opencode-rulesWhat 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 | $0.00058 | $0.02224 |
| Opus 5 | $0.00029 | $0.01112 |
| Sonnet 5 | $0.00012 | $0.00445 |
| Haiku 4.5 | $0.00006 | $0.00222 |
Grade A, and why
crafting-rules 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 2d ago.
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 — 221 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Crafting Rules
Overview
Rules are markdown files with optional YAML frontmatter, injected into the system prompt to guide agent behavior. Scope them with filters or leave unconditional for global standards.
Field Reference
| Field | Type | Category | Purpose |
|---|---|---|---|
globs |
string[] |
Legacy | Apply when any observed file's path matches a pattern |
fileContains |
string | string[] |
Legacy | Apply when an observed file's text contains a literal substring |
keywords |
string[] |
Legacy | Apply when the user's latest prompt matches a keyword |
tools |
string[] |
Legacy | Apply when any listed tool ID is available |
model |
string[] |
Runtime | Match against the current LLM model ID |
agent |
string[] |
Runtime | Match against the current agent type (e.g., programmer) |
command |
string[] |
Runtime | Match against the current slash command (e.g., /plan) |
project |
string[] |
Runtime | Match against detected project tags (e.g., node, rust) |
branch |
string[] |
Runtime | Match against git branch name (supports glob patterns) |
os |
string[] |
Runtime | Match against OS (linux, darwin, win32) |
ci |
boolean |
Runtime | Match against CI environment (true = in CI) |
match |
'any' | 'all' |
Combinator | any (default): OR logic. all: AND logic. |
- All fields are optional; no frontmatter means the rule always applies.
- With
match: any(default), the rule applies if ANY declared condition matches. - With
match: all, the rule applies only if ALL declared conditions match. globsandfileContainsform one file-observation family: when both are declared, the same observed file must satisfy both. The family counts as one condition in the algebra.- File observations come only from successful live Read, Write, Edit, Apply Patch, and path-associated LSP tool events. Grep, Glob, shell, custom/MCP tools, message prose, and historical tool events contribute nothing to
globs/fileContains. - A durable rule first matched by a live file observation takes effect at that earliest dispatch — not on the next user message.
- When a runtime value is unavailable (e.g., no git repo), that dimension is a non-match.
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.
- 2d ago First seen · 221 lines · 58 tokens per session scan A adf32cd2b1b5
crafting-rules is a skill published in the GitHub repository frap129/opencode-rules (112 stars, last pushed 2d ago), licensed MIT. It adds 58 tokens to every session and 2,224 once invoked, about $0.0003 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.
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…