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/markerikson/opencode-config-example/diffloupenpx skills add markerikson/opencode-config-example --skill diffloupegit clone --depth 1 https://github.com/markerikson/opencode-config-exampleWhat 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 | $0.00016 | $0.00745 |
| Opus 5 | $0.00008 | $0.00373 |
| Sonnet 5 | $0.00003 | $0.00149 |
| Haiku 4.5 | $0.00002 | $0.00075 |
Grade A, and why
diffloupe 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 — 118 lines — stays where its author put it; the contents beside it link to each section on GitHub.
DiffLoupe Skill
DiffLoupe is an AI-powered diff analysis tool that provides:
- Intent derivation (what the change does and why)
- Risk assessment (bugs, security, breaking changes)
- Intent alignment (comparing stated vs actual changes)
When to Use
- Pre-commit review of staged changes
- Reviewing a PR before merge
- Understanding unfamiliar code changes
- Checking if changes match stated intent
Invocation
Use the wrapper script:
~/.config/opencode/scripts/diffloupe.ts <command> [args]
CLI Reference
Analyze Local Changes
diffloupe.ts analyze [target]
Targets:
staged (default) # git diff --cached
unstaged # git diff
HEAD # git diff HEAD
branch:NAME # git diff NAME...HEAD
commit:HASH # single commit
range:A..B # commit range
Options:
-i, --intent "..." # Stated intent for alignment
--intent-file PATH # Read intent from file
-v, --verbose # Full output
--json # JSON output
-C, --cwd PATH # Run in directory
Analyze GitHub PRs
diffloupe.ts pr <identifier>
Identifiers:
123 # PR number (current repo)
owner/repo#123 # Cross-repo PR
https://github.com/.../pull/123 # URL
Options:
-R, --repo owner/repo # Specify repository
-v, --verbose # Full output
--json # JSON output
Preview Without API Call
diffloupe.ts summarize [target]
Options:
--stats # Only file list + tokens
--files-only # Only file list
--json # JSON output
Output Structure (JSON)
{
"intent": {
"summary": "...",
"purpose": "...",
"scope": "feature|bugfix|refactor|config|docs|test|mixed",
"affectedAreas": ["..."],
"suggestedReviewOrder": ["file1.ts", "file2.ts"]
},
"risks": {
"overallRisk": "low|medium|high|critical",
"summary": "...",
"confidence": "high|medium|low",
"risks": [
{
"severity": "low|medium|high|critical",
"category": "security|breaking-change|performance|...",
"description": "...",
"evidence": "...",
"file": "...",
"mitigation": "..."
}
]
},
"alignment": {
"alignment": "aligned|partial|misaligned",
"confidence": "high|medium|low",
"summary": "...",
"matches": ["..."],
"mismatches": ["..."],
"missing": ["..."],
"unstated": ["..."]
}
}
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 · 118 lines · 16 tokens per session scan A 949caf3c96e1
diffloupe is a skill published in the GitHub repository markerikson/opencode-config-example (44 stars, last pushed 3mo ago), licensed MIT. It adds 16 tokens to every session and 745 once invoked, about $0.0001 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…