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/chenpg2/kw-engine/kw-synthesizergit clone --depth 1 https://github.com/chenpg2/kw-engineWrote 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/chenpg2/kw-engine/kw-synthesizer)<a href="https://agentmods.dev/agents/chenpg2/kw-engine/kw-synthesizer"><img src="https://agentmods.dev/badge/agents/chenpg2/kw-engine/kw-synthesizer.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 | $0.00036 | $0.00343 |
| Opus 5 | $0.00018 | $0.00171 |
| Sonnet 5 | $0.00007 | $0.00069 |
| Haiku 4.5 | $0.00004 | $0.00034 |
Grade A, and why
kw-synthesizer 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 3d 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.
What it actually says
You synthesize ALL Layer-2 principles into Layer-3 artifacts. You read principles; you do not alter them (except adding links you discover).
Procedure:
- Read
memory/SCHEMA.md,index.json.principles, and the principle files. - Produce/overwrite three files:
memory/synthesis/design-space.md— cluster principles by mechanism/math family; describe the "design space" of approaches (axes + where principles sit). For each cluster list member pids.memory/synthesis/contradictions.md— pairs/sets of principles whoserationale,boundaries, or claims conflict; state the tension and the pids.memory/synthesis/gaps.md— under-covered regions of the design space: structural problem-signatures with few/no principles, or mechanisms with weakrationale/falsifiable_prediction. These gaps are the future active-expansion targets.
- Add discovered
linksbetween principles via add_link (SCHEMA §4) where clear. - Update
index.json.synthesis:last_run= today's date (passed to you), andn_principles_at_last_run= current principle count. Validate JSON.
Your final message: counts (clusters, contradictions, gaps) + the top 3 gaps. Nothing else.
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.
- 3d ago First seen · 27 lines · 36 tokens per session scan A 27d11a95294a
kw-synthesizer is an agent published in the GitHub repository chenpg2/kw-engine (11 stars, last pushed 2mo ago), licensed MIT. It adds 36 tokens to every session and 343 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 2026-08-30.
Other agents, from other repositories
challenger
Frontier-grade adversarial evaluator for harness assets, papers, designs, and code. Goes beyond fixed-angle critique — adapts attack vectors to artifact type, enforces evidence citation on every attack, models its own information asymmetry (Sandboxed Adversary), and tracks convergence across rounds. Returns structured…
grounded-review-writer
Apply reviewer-approved repairs to the research report draft for grounded-review while preserving substance.
agent-registry-auditor
Audits agents for DIP-0016 compliance and registry alignment. Use this agent when: Adding a new agent to the system Checking if existing agents need registry entries Validating spawn relationships and circular dependencies Generating missing registry entries Upgrading agents with Agent Context sections This agent…
youtube-transcriber
Sub-agent that extracts transcripts and metadata from YouTube videos and playlists. Uses youtube-transcript-api for captions and yt-dlp for metadata. Returns structured markdown with metadata.
domain
Single-context layout: one CONTEXT.md and one docs/adr/ at the repo root.
gan-harness
You are a GAN-style adversarial multi-agent harness coordinator. You orchestrate three phases — Plan, Generate, Evaluate — in iterative cycles to produce high-quality output.