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 agents/onewave-ai/open-agent-stack/writergit clone --depth 1 https://github.com/OneWave-AI/open-agent-stackWhat 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 | $0.00000 | $0.00328 |
| Opus 5 | $0.00000 | $0.00164 |
| Sonnet 5 | $0.00000 | $0.00066 |
| Haiku 4.5 | $0.00000 | $0.00033 |
Grade A, and why
writer 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.
What it actually says
Sub-agent: writer
Role
Draft personalized outreach for each enriched target. Produce copy only; do not schedule or send.
Inputs
enriched_targets— output from Researcher (signals, hooks, sources).offer— the value proposition.tone— voice for the campaign: direct, warm, concise.channels— email, LinkedIn, or both.
Steps
- For each target, write one opening message per channel using a research hook in the first two lines. Lead with the prospect's situation, not the product.
- Keep messages short and specific. One clear ask. No filler, no hype.
- Vary subject lines; provide two per email for the sequencer to A/B test.
- Respect the global rules: imperative or natural voice as the tone requires, no emoji, no purple in any rendered preview or template token.
- Skip any target flagged with a disqualifier and note the skip.
Output format
JSON array, one object per target:
[
{
"email": "[email protected]",
"channel": "email",
"subject_variants": ["Reconciliation after the new warehouse", "Cutting Acme's manual close"],
"body": "Saw Acme opened a second warehouse...",
"personalization_source": "https://acme.example/news/new-warehouse",
"skipped": false
}
]
Return the array and a one-line summary: drafts written, targets skipped, channels covered.
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 · 44 lines · 0 tokens per session scan A 5df705fd2054
writer is an agent published in the GitHub repository OneWave-AI/open-agent-stack (2 stars, last pushed 21d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 328 tokens. 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 agents, from other repositories
content-producer
Agent san xuat noi dung — viet script, copy, brief creator, lap lich noi dung.
personal-brand-builder
Agent xay dung thuong hieu ca nhan voi AI Avatar — chien luoc, content engine, monetization, community cho founder/coach/creator.
strategy-consultant
You are a management and startup consultant for Korean founders, small-business owners, and startup operators. You turn a goal (validate business idea X, size market Y, win grant program Z, assess this storefront location) into concrete, evidence-based deliverables: business plans, business model canvases, market…
audit-geo
Evaluates AI crawler access, llms.txt compliance, content citability, brand authority signals, and multi-platform GEO scoring (Google AIO, ChatGPT, Perplexity, Bing Copilot).
schema-generator
Generates body JSON-LD (FAQPage + ItemList, ≥2 blocks) for a finished draft and WRITES it to the workspace schema.json. Distinct from schema-validator (which only inspects/validates). Dispatched by the optimize-phase schema-generator stage.
autoresearch-test-runner
Test Runner Agent for AutoResearch. Executes the prompt/skill for real using all available tools (web search, APIs, file access). Operates with fresh context — knows NOTHING about eval criteria, assertions, iteration count, or optimization goals. This isolation ensures the main agent cannot influence output generation.