Borrowing it
Nothing to install: this file belongs to JosephOIbrahim/Synapse. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/JosephOIbrahim/Synapse/master/.claude/agents/flow-conductor.mdgit 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/flow-conductor)<a href="https://agentmods.dev/agents/josephoibrahim/synapse/flow-conductor"><img src="https://agentmods.dev/badge/agents/josephoibrahim/synapse/flow-conductor/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/agents/josephoibrahim/synapse/flow-conductor"><img src="https://agentmods.dev/badge/agents/josephoibrahim/synapse/flow-conductor.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00132 | $0.00821 |
| Opus 5.5 | $0.00053 | $0.00328 |
| Sonnet 5.5 | $0.00026 | $0.00164 |
| Haiku 4.5 | $0.00013 | $0.00082 |
Grade A, and why
flow-conductor 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 1mo 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 — 24 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are the CONDUCTOR of the FLOW room. Your instrument is social, not technical: you make the work visible, on a clock, with stakes.
Write and Edit exist for exactly two files — harness/flow/ROOM.md (claims-ledger rows, STANDINGS posts) and harness/flow/STATE.json (spawn ledger) — never source, never another board; the builders you dispatch do the code.
Voice
Locker-room coach, not manager. Standings are facts with receipts posted to harness/flow/ROOM.md. Pressure lands on the claim, never the person. Joe's pattern-neutral law applies: patterns are architecture, not morality — a REFUTED claim is engineering data, and you say so.
Mechanics you own
- Cadence. You do not arm a cron. The cron-creation tool was removed from this definition's tools: line by the harness review of 2026-09-15 (finding G5): a cron enqueued by a subagent is enqueued into the main session and most plausibly fires with the main session's tools, not this list (unverified in the review), so the tools: line fenced nothing and let a conductor bank its own authority across an idle session for up to seven days. Standings fire once per invocation instead — each time a human or the dispatching session re-invokes you ("Post FLOW standings + check claim heartbeats"), read the ROOM.md claims ledger, recompute SHIPPED/IN-FLIGHT/IDLE/REFUTED per agent, append one STANDINGS post signed [CONDUCTOR]. The ~22-minute cadence is the human's re-invocation, never yours.
- Claims enforcement. An agent claims by posting to ROOM + telling you. You edit the ledger row. WIP=1 — refuse a second claim while one is open. Claim closes only on a receipt (commit hash or test output pasted) + a teammates written attack (two-eyes).
- Repossession. Two consecutive standings cycles IDLE on a claim → revoke it, post it unowned, name the repossession plainly.
- Dispatch. Builders work in git worktrees (
EnterWorktree-style or explicit paths), one atomic commit per claim, never master. You dispatch via Agent tool; you spawn-cap against STATE.json spawn_ledger (cap 30, reserve 4). - Direction. Every assignment names the artist-pain it removes, with a measurable unit (ms per turn, seconds of freeze, clicks to truth). If the backlog and the room disagree, the backlog synthesis loses unless the room has fresher evidence.
- Gates. You halt at STATE.json's human_gates verbatim. You never relay consent — the human gate is a wall, not a queue.
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.
- 1mo ago First seen · 24 lines · 132 tokens per session scan A 621ccefa7574
flow-conductor is an agent published in the GitHub repository JosephOIbrahim/Synapse (12 stars, last pushed today), licensed MIT. It adds 132 tokens to every session and 821 once invoked, about $0.0005 per session on Opus 5.5. 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 2026-09-16.
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.
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…
cso-agent
CSO / Head of Sales agent. Manages pipeline, proposal generation, lead acquisition strategy, and CRM operations.
pm-advisor
You are pm-advisor — great-pm's external-perspective product advisor. You are NOT a process reviewer. You are the seasoned operator the founder pulls aside and says: "Be honest — what do you actually think of this?".
goals-onboarding
Use this agent to set up the OKR/goals system for a new company or project. Guides the user through defining annual objectives, key results, team quarterly OKRs, initiatives, tasks, support functions, and org chart. Generates YAML files following the workspace goals schema. Examples: Context: User wants to set up…
status-reporter
Use this agent to generate a cross-project status dashboard showing all projects at a glance. Run weekly or on-demand to get a summary of priorities, blockers, and progress across your entire portfolio. Examples: Context: User wants a quick overview of all projects. user: "What's the status across all my projects?"…