synth

A command that combines lens evaluation files from a folder into one summary file.

In plain words
What is it for?
Use it after several probe evaluations to create `probe-synthesis.md` with an executive summary, verdict, and missing-lens list.
Why use it?
It avoids reading and merging separate evaluation notes by hand. It also records which expected evaluations are missing without making up results.

Command

Install

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.

agentmods
npx agentmods add commands/ds1/probe/synth
Clone the repo
git clone --depth 1 https://github.com/ds1/probe
Per session 11 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 228 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00011 $0.00228
Opus 5 $0.00005 $0.00114
Sonnet 5 $0.00002 $0.00046
Haiku 4.5 $0.00001 $0.00023

Measured yesterday against content hash 4aed024acec0, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

synth 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.

commands/synth.md · 25 lines

What it actually says

Probe: Synthesis

Consolidate whatever lens evaluations exist in a directory into probe-synthesis.md. The synthesis template lives in the synthesis agent; this command only launches it.

Arguments

$ARGUMENTS is the directory holding probe-*.md lens files. If it is empty, use ./probe-output/. Quote paths that contain spaces.

Run

Use the Agent tool with subagent_type: "probe:synthesis". If that agent type is not available (the files were installed by script rather than as a plugin), use synthesis.

Launch prompt: Directory: the directory from the arguments.

The agent tolerates a partial set of lenses. It names the missing ones in the synthesis rather than inventing findings for them, and stops if none are present.

Reply

Relay the agent's executive summary, final verdict, and any lenses it reported missing, plus the path of probe-synthesis.md.

Changes

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.

  1. yesterday First seen · 25 lines · 11 tokens per session scan A 4aed024acec0

Subscribe to this mod's changes

synth is a command published in the GitHub repository ds1/probe (2 stars, last pushed 5d ago), licensed MIT. It adds 11 tokens to every session and 228 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.