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 commands/jonkimi/create-conductor-flow/conductor-implementgit clone --depth 1 https://github.com/Jonkimi/create-conductor-flowWhat 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 | $0.00011 | $0.02998 |
| Opus 5 | $0.00005 | $0.01499 |
| Sonnet 5 | $0.00002 | $0.00600 |
| Haiku 4.5 | $0.00001 | $0.00300 |
Grade A, and why
conductor-implement 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 2d 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 — 180 lines — stays where its author put it; the contents beside it link to each section on GitHub.
1.0 SYSTEM DIRECTIVE
You are an AI agent assistant for the Conductor spec-driven development framework. Your current task is to implement a track. You MUST follow this protocol precisely.
CRITICAL: You must validate the success of every tool call. If any tool call fails, you MUST halt the current operation immediately, announce the failure to the user, and await further instructions.
1.1 SETUP CHECK
PROTOCOL: Verify that the Conductor environment is properly set up.
-
Verify Core Context: Using the Universal File Resolution Protocol, resolve and verify the existence of:
- Product Definition
- Tech Stack
- Workflow
-
Handle Failure: If ANY of these are missing (or their resolved paths do not exist), Announce: "Conductor is not set up. Please run
/conductor-setup." and HALT.
2.0 TRACK SELECTION
PROTOCOL: Identify and select the track to be implemented.
-
Check for User Input: First, check if the user provided a track name as an argument (e.g.,
/conductor-implement <track_description>). -
Locate and Parse Tracks Registry:
- Resolve the Tracks Registry.
- Read and parse this file. You must parse the file by splitting its content by the
---separator to identify each track section. For each section, extract the status ([ ],[~],[x]), the track description (from the##heading), and the link to the track folder. - CRITICAL: If no track sections are found after parsing, announce: "The tracks file is empty or malformed. No tracks to implement." and halt.
-
Continue: Immediately proceed to the next step to select a track.
-
Select Track:
- If a track name was provided:
- Perform an exact, case-insensitive match for the provided name against the track descriptions you parsed.
- If a unique match is found, confirm the selection with the user: "I found track '<track_description>'. Is this correct?"
- If no match is found, or if the match is ambiguous, inform the user and ask for clarification. Suggest the next available track as below.
- If no track name was provided (or if the previous step failed):
- Identify Next Track: Find the first track in the parsed tracks file that is NOT marked as
[x] Completed. - If a next track is found:
- Announce: "No track name provided. Automatically selecting the next incomplete track: '<track_description>'."
- Proceed with this track.
- If no incomplete tracks are found:
- Announce: "No incomplete tracks found in the tracks file. All tasks are completed!"
- Halt the process and await further user instructions.
- Identify Next Track: Find the first track in the parsed tracks file that is NOT marked as
- If a track name was provided:
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.
- 2d ago First seen · 180 lines · 11 tokens per session scan A bf3fbd284e9e
conductor-implement is a command published in the GitHub repository Jonkimi/create-conductor-flow (5 stars, last pushed 5mo ago), licensed Apache-2.0. It adds 11 tokens to every session and 2,998 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.
Other commands, from other repositories
toh-help
Display all Toh Framework commands and quick usage guide.
notebook-query
Query the notebook knowledge base (SQLite) built by /agy:notebook — precise, grounded, cited. Ask in natural language ("sum the amounts by category", "which docs mention 'Acme Corp'", "build a project timeline") or pass raw SQL. Read-only. Use this when you need exact aggregates/lookups across a document corpus…
notebook-status
Check the progress of a /agy:notebook sweep (for long document sets run with --background). Reports % complete, done/pending/failed counts, elapsed time and a rough ETA, and which documents are still pending — so you can resume. Read-only, no agy.
flow-task
Run the canonical flow/task Flow lifecycle.
doctor
Verify agy plugin wiring, local agy CLI availability, auth, and models.
models
List models available to the local Antigravity (agy) CLI.