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 commands/rowbradley/searchwave/wavegit clone --depth 1 https://github.com/rowbradley/searchwaveWhat 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 | $0.00015 | $0.00612 |
| Opus 5 | $0.00008 | $0.00306 |
| Sonnet 5 | $0.00003 | $0.00122 |
| Haiku 4.5 | $0.00002 | $0.00061 |
Grade A, and why
wave 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 — 88 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Searchwave
Topic: $ARGUMENTS
Quick web research synthesis in ~60 seconds.
Execution
Complete in 60 seconds. Dense facts, not fluff.
Step 0: Print banner
Print this banner immediately:
╔═════════════════════════════════════════╗
║ S E A R C H W A V E ║
║ · · · · · ║
║ Searching: 3 parallel queries ║
╚═════════════════════════════════════════╝
Step 1: Search (3 parallel)
Fire 3 WebSearches in ONE message:
"$ARGUMENTS" → baseline
"$ARGUMENTS interesting" → non-obvious angles
"$ARGUMENTS guide" → actionable content
All searches use blocked_domains: ["medium.com"] — Medium never fetches usefully.
Step 2: Curate (10 sec)
Pick 3 URLs. Prefer: gov/institutional, domain authorities, quality blogs.
Skip for fetching:
- Wikipedia (403s — use snippet from search results instead)
- Medium (blocked at search level — never useful)
- Paywalled sites
- SEO farms, outdated content
Step 3: Fetch (3 parallel)
Fire 3 WebFetches in ONE message. Proceed with available if any fail.
Step 4: Write
Adapt structure to topic. No rigid template.
Always include:
- Overview — 2-3 sentences, plain language
- Key Findings — Specific numbers, names, thresholds. This is the meat.
- Sources — With one-line descriptions
Include ONLY if warranted:
- Practical Takeaways — If topic has actionable advice
- Of Interest — ONLY if genuinely surprising. Skip if straightforward.
- Go Deeper? — ONLY if topic clearly warrants more research
Style:
- Concrete > abstract
- Numbers > vague claims
- Useful > clever
- Skip sections that don't add value
- ASCII tables/diagrams when helpful for comparisons
- No --- dividers between sections
- Tight, scannable organization
- Inline citations for statistics: "According to X...", "One study found..."
Avoid AI writing patterns:
- No dramatic reframes or hyperbole
- Let facts speak; don't editorialize
- Be concise, lead with numbers
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 · 88 lines · 15 tokens per session scan A 6971ae9d2f38
wave is a command published in the GitHub repository rowbradley/searchwave (5 stars, last pushed 6mo ago), licensed MIT. It adds 15 tokens to every session and 612 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 2026-08-31.
Other commands, from other repositories
design-review
Workflow recipe — review a design end-to-end, ending in measured numbers rather than adjectives, by chaining 4 skills.
setup-pm-skills
Onboard a new user — find out what they do, recommend the right bundles & top skills, and set up a project CONTEXT.md so every skill is tailored to them.
statusbar-style
Switch the status-bar style (classic / capsule / hairline).
validate-dependencies
Validate all task dependencies for issues.
fest-show
Show festival progression (in-progress tasks, roadmap, and dependency view).
superpowers-execute
Execute the current GSD phase plan with Superpowers instead of gsd-execute-phase.