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/orin-dx/agent-plugins/synthesizergit clone --depth 1 https://github.com/orin-dx/agent-pluginsWhat 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 | $0.00139 | $0.00859 |
| Opus 5 | $0.00069 | $0.00430 |
| Sonnet 5 | $0.00028 | $0.00172 |
| Haiku 4.5 | $0.00014 | $0.00086 |
Grade A, and why
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 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.
What it actually says
{
"question": "string",
"findings": [
{
"claim": "string",
"evidence": "string — file path, URL, doc section, or test output",
"source": "string (optional)",
"confidence": "confirmed | likely | assumed"
}
],
"recommendation": "string — the recommended direction, with explicit rationale",
"confidence": "high | medium | low",
"open_questions": ["string"],
"linked_requirement": "string (optional)",
"reasoning": "string"
}
findings carries reader's array through — do not drop a finding or silently merge two into one without preserving each one's own evidence and confidence. reasoning is a scratchpad, not forwarded downstream.
IF confirmed and assumed findings point in different directions, NEVER resolve by picking a side — surface both in recommendation and name the contradiction.
WHEN open questions exist, frame each entry as "IF <question> THEN recommendation changes to <alternative>" to make the dependency explicit.
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 · 56 lines · 139 tokens per session scan A 6c50ed3f61c2
synthesizer is an agent published in the GitHub repository orin-dx/agent-plugins (1 stars, last pushed 6d ago), licensed MIT. It adds 139 tokens to every session and 859 once invoked, about $0.0007 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
test-engineer
QA engineer specialized in test strategy, test writing, and coverage analysis. Use for designing test suites, writing tests for existing code, or evaluating test quality.
eval-curator
Authors and maintains the brooks-lint eval suite in evals/evals.json — the benchmark scenarios covering R1–R6 (code decay) and T1–T6 (test decay), including the false-positive / tradeoff cases that must NOT be flagged. Ensures every new risk code or skill gets paired coverage and that the suite passes npm run evals.…
ring:streaming-reviewer
Conditional Gate 8 specialist for lib-streaming, business events, outbox, event producers, broker publishing, CloudEvents, and event manifests/catalogs.
performance-reviewer
Performance reviewer subagent. Auto-loads the performance skill; applies any .review-pro/ stack signals; returns structured findings.
qa-fixer
Bounded test-fix loop agent for beast. Diagnoses test failures and applies targeted fixes, max 5 cycles.
rust-perf-engineer
Reviews diffs touching poly's per-file runner / discovery / cache / engine paths for hot-path regressions — needless allocations/clones, missed borrows, parser-pool misuse, and non-rayon parallelism.