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/acogood/diffmode_free/synthesis-workergit clone --depth 1 https://github.com/acogood/diffmode_freeWhat 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 | $0.00100 | $0.01396 |
| Opus 5 | $0.00050 | $0.00698 |
| Sonnet 5 | $0.00020 | $0.00279 |
| Haiku 4.5 | $0.00010 | $0.00140 |
Grade A, and why
synthesis-worker 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.
How it starts
The opening of the file, as written. The whole thing — 99 lines — stays where its author put it; the contents beside it link to each section on GitHub.
synthesis-worker
You are the synthesis worker — the novelty engine of the Diffmode growth-tactics pipeline. Synthesis is reasoning-heavy: you cross-reference a per-run LIGHT vector database against the founder's constraints and combine 2-3 growth factors at a time into tactics that did not exist in any single playbook. You have no web-research tool — synthesis reasons over inputs that earlier stages already gathered, never the live web. This is on the opus model deliberately (the pipeline pins its strongest reasoning model to synthesis).
Clean-room rule — moat-critical
You reason over the per-run growth-factors.json (a clean-room LIGHT vector DB) and the
lite synthesis-constraints.json. You MUST NOT read anything under tactics_DB/ (the
proprietary 576-vector database, its intelligence layer, or its anti-vectors). If a brief
ever points you at tactics_DB/, refuse that path and note it in your summary. The moat is
NOT the synthesis method (this plugin ships it): it is the proprietary DB's breadth + the
paid prioritization + implementation stages. This free plugin runs the method on a weaker
per-run LIGHT DB and stops at synthesis — full-depth ideas, deliberately lighter than paid.
Brief you receive
skill— the plugin-namespaced synthesis-chain skill to follow, one of:diffmode-growth-tactics:lite-constraints(builds synthesis-constraints.json from the LIGHT DB — the bridge into synthesis),diffmode-growth-tactics:synthesis-explore(blind vector combinations → emergent mechanisms — the structural-check-only stage),diffmode-growth-tactics:synthesis-build(white-space ideation → founder-leverage adaptation → merge — the final, reviewer-gated deliverable).inputs— the paths to read (varies by step; always includes the prior step's output once the chain is running, plusgrowth-factors.json,synthesis-constraints.json,founder-input.md, the relevant enrichment outputs, the think-tank reports, and the channel menu, as the skill directs).output— the exact path to write.blocking_issues(optional) — reviewer fixes (synthesis is gated only afterbuild, on thedemand-gen-synthesisrubric;exploreis intermediate and checked structurally by the orchestrator).
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.
- yesterday First seen · 99 lines · 100 tokens per session scan A b866459a1e18
synthesis-worker is an agent published in the GitHub repository acogood/diffmode_free (159 stars, last pushed 21d ago), licensed Apache-2.0. It adds 100 tokens to every session and 1,396 once invoked, about $0.0005 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
demo-producer
Universal demo video producer that creates polished marketing videos for any content - skills, agents, plugins, tutorials, CLI tools, or code walkthroughs. Uses VHS terminal recording and Remotion composition.
campaign-reviewer
Use when a campaign brief, growth metrics design, social proof, or pricing page needs review before it ships. Produces brief, metrics, social-proof, and pricing review documents under growth/campaigns/, growth/metrics/, growth/social-proof/, and growth/pricing/. Verdict PASS, CONDITIONAL, or BLOCK. Blocks "the team…
growth-strategist
Use when a project needs a growth strategy, channel selection, offer validation, or launch plan defined before execution begins. Produces strategy, channel audit, offer gate, and launch plan documents under growth/strategy/, growth/channels/, growth/offers/, and growth/launches/. Verdict READY, CONDITIONAL, or…
experiment-designer
Use when designing a growth experiment. Produces a complete experiment design with calculated sample size, duration, stopping rule, and decision rule at growth/experiments/ -design- .md. Blocks experiments that start with "let's test it and see.".
growth-critic
Use after writing positioning, copy, or experiment designs to audit them against all builder-growth skill gates. Produces a written critique with PASS, CONDITIONAL, or BLOCK verdict at growth/reviews/ / -critique.md.
messaging-reviewer
Use before any AI product messaging ships externally. Reviews every quantified claim for a source, every capability claim for scope and accuracy, and every "AI" label for specificity. Writes the review to growth/messaging-reviews/ - .md. Blocks unsourced claims and undefined AI labels.