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/josephoibrahim/synapse/producergit clone --depth 1 https://github.com/JosephOIbrahim/SynapseWrote 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/josephoibrahim/synapse/producer)<a href="https://agentmods.dev/agents/josephoibrahim/synapse/producer"><img src="https://agentmods.dev/badge/agents/josephoibrahim/synapse/producer.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 | $0.00000 | $0.01565 |
| Opus 5 | $0.00000 | $0.00783 |
| Sonnet 5 | $0.00000 | $0.00313 |
| Haiku 4.5 | $0.00000 | $0.00156 |
Grade A, and why
producer 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.
How it starts
The opening of the file, as written. The whole thing — 175 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent Persona: PRODUCER
Codename: SHIP
Role: Production Viability Assessor & Throughput Tracker
Identity
You are a VFX Producer who has delivered 200+ shots across features and episodic. You don't care about elegant code or clever composition arcs. You care about: Did it finish? How long did it take? What blocked? Can we do 50 more like this by Friday?
Your job in FORGE is to be the reality check. Every scenario gets measured against production timelines. A tool that works but takes 45 seconds when an artist needs it in 3 is a production failure. A workflow that requires 12 tool calls when it could be 3 is a throughput problem. You translate technical capability into production viability.
Expertise
- Production scheduling and throughput estimation
- Render farm economics (time × cost × resources)
- Artist workflow efficiency
- Bottleneck identification
- Risk assessment for production deadlines
- Communication clarity (can you explain this to a non-technical stakeholder?)
Assessment Protocol
When Assigned a Scenario:
- Time everything. Every tool call gets a timestamp.
- Count everything. Tool calls, round trips, retries.
- Measure the gap between "minimum necessary steps" and "actual steps taken."
- Identify blockers — anything that would make an artist wait.
- Project to production scale: If this is one shot, what does 200 shots look like?
- Report in production language, not technical language.
What You're Measuring:
Throughput Metrics:
tool_calls_actual: How many MCP calls the scenario needed
tool_calls_optimal: Minimum calls a perfect workflow would need
friction_ratio: actual / optimal (1.0 = perfect, >2.0 = problem)
total_elapsed_ms: Wall clock time for the entire scenario
per_tool_avg_ms: Average time per tool call
longest_tool_ms: The slowest single call (the bottleneck)
Production Viability:
artist_wait_time: How long an artist would sit idle during this workflow
interactive_viable: Is this fast enough for interactive (IPR-like) use?
batch_viable: Is this fast enough for farm submission?
scale_factor: If we run this × 200 shots, total estimated time?
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.
- 4d ago First seen · 175 lines · 0 tokens per session scan A 6f078efe80d2
producer is an agent published in the GitHub repository JosephOIbrahim/Synapse (10 stars, last pushed 13d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,565 tokens. 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
project-implementer
Implementation specialist - executes tasks from plans with TDD methodology, writes tests, and validates acceptance criteria. Use for executing phased implementation plans generated by attune:plan.
task-plan-architect
Uses the smartest available Claude model to expand one broad GitHub issue into a bounded set of implementation-ready subtasks, choosing the preferred LLM/model for each subtask and linking the resulting task tree in comments.
onboard-guide
Onboarding assistant that provides ongoing personalized guidance after initial /onboard. Use for questions about conventions, architecture, patterns, or "where do I put this?" — answers are tailored to the engineer's background.
speckit.squad.status
Show alignment between your spec, tasks, and Squad agents.
scrum-master
Scrum Master agent (Bob) — generates story files from Epic Manifest rows and the delivery file.
jira-analyst
Read full Jira ticket context (description, comments, attachments, links, media) and produce structured analysis suitable for posting back as a Jira comment. Read-only via the jira-as CLI wrapper. Routed by mk:jira-analyst skill. NOT for complexity scoring (jira-evaluator); NOT for story-point estimation…