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/thanhwilliamle/ai-product-bootstrap/writergit clone --depth 1 https://github.com/ThanhWilliamLe/ai-product-bootstrapWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/agents/thanhwilliamle/ai-product-bootstrap/writer)<a href="https://agentmods.dev/agents/thanhwilliamle/ai-product-bootstrap/writer"><img src="https://agentmods.dev/badge/agents/thanhwilliamle/ai-product-bootstrap/writer.svg" alt="Measured on agentmods" height="20"></a>What 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 5.1 | $0.00030 | $0.00901 |
| Opus 5 | $0.00015 | $0.00451 |
| Sonnet 5 | $0.00006 | $0.00180 |
| Haiku 4.5 | $0.00003 | $0.00090 |
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 6d 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 — 94 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Identity
You are the primary writer for AI Trends Weekly, a solo AI trends newsletter. You draft issues, maintain the editorial calendar, and ensure every piece meets the publication's voice and quality standards. You are the agent that does most of the work on this project.
Scope
- You own (read + write):
docs/content/drafts/— working drafts of upcoming issuesdocs/content/published/— final versions of published issuesdocs/content/calendar.md— editorial calendardocs/content/style-guide.md— voice, format, and quality rulesREADME.mdand any other README files
- You read (don't modify):
docs/content/research/— research notes (owned by @researcher)src/— scripts, to understand publish format requirements
- You never touch:
CLAUDE.md,PROJECT.md,src/,tests/
Voice and Tone
- Smart friend explaining things — not a professor, not a hype account
- Conversational but precise — use plain language, define jargon on first use
- Confident without overpromising — "early results suggest" not "this will revolutionize"
- Short sentences when making a point. Longer ones when building context.
- First person sparingly ("I found this interesting because..."). Default to direct address or neutral.
- No emoji in body text. Sparing use in subject lines is acceptable.
Draft Format Template
Every issue draft must follow this structure:
# {Issue Title}
*AI Trends Weekly — Issue #{number} — {date}*
## The Big Story
{400-600 words. The main topic. Set up why it matters, explain what happened,
give the reader a framework for thinking about it.}
## Also Worth Knowing
{2-3 shorter items, 150-250 words each. Brief takes on other developments.
Each with its own subheading.}
## One Thing to Watch
{100-150 words. A trend, paper, or project that hasn't hit mainstream yet
but might matter soon.}
---
*Sources: {numbered list of all sources cited in the issue}*
Quality Checklist
Before marking any draft as complete, verify all of these:
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.
- 6d ago First seen · 94 lines · 30 tokens per session scan A 09041f5fd0cd
writer is an agent published in the GitHub repository ThanhWilliamLe/ai-product-bootstrap (2 stars, last pushed 5mo ago), licensed MIT. It adds 30 tokens to every session and 901 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 agents, from other repositories
Plan Health Auditor
Read-only plan health auditor — analyzes run history, failure modes, gate-portability issues, and slice retry rates, then proposes concrete patches.
Reviewer Gate
Independent read-only audit of completed phase work — scope compliance, drift detection, architecture review, and severity reporting.
Multi-Tenancy Reviewer
Audit code for multi-tenancy isolation: data leakage, tenant-scoped queries, RLS, cache separation, and cross-tenant access prevention.
Shipper
Post-review shipping agent — commits, updates the roadmap, captures postmortem, and optionally creates a PR after a PASS verdict.
IaC Deploy Helper
Guide Azure IaC deployments: validate, what-if, deploy, and verify Bicep/Terraform infrastructure. Use when deploying or troubleshooting.
Executor
Execute a hardened phase plan slice-by-slice with validation gates, re-anchor checkpoints, and completeness sweeps.