synthesizer

synthesizer is an agent for coding agents from tacoda/keystone. It costs 14 tokens per session (223 once invoked), scanned A, original, MIT.

An agent that reviews learning notes and decides where each useful idea belongs in a project’s documentation. It can place an idea in a guide, a reasoning document, an existing rule, or an archive.

In plain words
What is it for?
Use it to process candidate files, decide whether to promote or merge them, and record the decision in a table with the destination and reasoning.
Why use it?
It prevents one-off incidents from becoming permanent rules too quickly and reduces duplicate documentation. It also keeps new learning connected to the project’s existing guidance.

Agent

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 agents/tacoda/keystone/synthesizer
Clone the repo
git clone --depth 1 https://github.com/tacoda/keystone

Wrote 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.

agentmods badge for synthesizer

README.md
[![agentmods](https://agentmods.dev/badge/agents/tacoda/keystone/synthesizer.svg)](https://agentmods.dev/agents/tacoda/keystone/synthesizer)
Your own site
<a href="https://agentmods.dev/agents/tacoda/keystone/synthesizer"><img src="https://agentmods.dev/badge/agents/tacoda/keystone/synthesizer.svg" alt="Measured on agentmods" height="20"></a>
Per session 14 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 223 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 $0.00014 $0.00223
Opus 5 $0.00007 $0.00112
Sonnet 5 $0.00003 $0.00045
Haiku 4.5 $0.00001 $0.00022

Measured 4d ago against content hash 035fa1dcab29, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

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 4d 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.

.charter/agents/synthesizer.md · 38 lines

What it actually says

Synthesizer

You read candidate files under .charter/learning/inbox/ and decide: promote to a guide (binding rule), promote to corpus (reasoning doc), merge into an existing primitive, or archive as a one-off.

Posture

  • Conservative on promotion. A single incident rarely warrants an iron-law rule; prefer corpus first.
  • Cite the existing primitive when merging. Don't duplicate rules.
  • One candidate per output entry.

Output

Markdown table, one row per candidate:

candidate action target rationale

actionpromote-guide | promote-corpus | merge | archive. target is the destination path (existing or new).

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. 4d ago First seen · 38 lines · 14 tokens per session scan A 035fa1dcab29

Subscribe to this mod's changes

synthesizer is an agent published in the GitHub repository tacoda/keystone (44 stars, last pushed 2mo ago), licensed MIT. It adds 14 tokens to every session and 223 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 2026-08-30.