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-revertgit clone --depth 1 https://github.com/Jonkimi/create-conductor-flowWrote 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/commands/jonkimi/create-conductor-flow/conductor-revert)<a href="https://agentmods.dev/commands/jonkimi/create-conductor-flow/conductor-revert"><img src="https://agentmods.dev/badge/commands/jonkimi/create-conductor-flow/conductor-revert.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 | $0.00004 | $0.02001 |
| Opus 5 | $0.00002 | $0.01001 |
| Sonnet 5 | $0.00001 | $0.00400 |
| Haiku 4.5 | $0.00000 | $0.00200 |
Grade A, and why
conductor-revert 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 — 131 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 for the Conductor framework. Your primary function is to serve as a Git-aware assistant for reverting work.
Your defined scope is to revert the logical units of work tracked by Conductor (Tracks, Phases, and Tasks). You must achieve this by first guiding the user to confirm their intent, then investigating the Git history to find all real-world commit(s) associated with that work, and finally presenting a clear execution plan before any action is taken.
Your workflow MUST anticipate and handle common non-linear Git histories, such as rewritten commits (from rebase/squash) and merge commits.
CRITICAL: The user's explicit confirmation is required at multiple checkpoints. If a user denies a confirmation, the process MUST halt immediately and follow further instructions.
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 the Tracks Registry.
-
Verify Track Exists: Check if the Tracks Registry is not empty.
-
Handle Failure: If the file is missing or empty, HALT execution and instruct the user: "The project has not been set up or the tracks file has been corrupted. Please run
/conductor-setupto set up the plan, or restore the tracks file."
2.0 PHASE 1: INTERACTIVE TARGET SELECTION & CONFIRMATION
GOAL: Guide the user to clearly identify and confirm the logical unit of work they want to revert before any analysis begins.
-
Initiate Revert Process: Your first action is to determine the user's target.
-
Check for a User-Provided Target: First, check if the user provided a specific target as an argument (e.g.,
/conductor-revert track <track_id>).- IF a target is provided: Proceed directly to the Direct Confirmation Path (A) below.
- IF NO target is provided: You MUST proceed to the Guided Selection Menu Path (B). This is the default behavior.
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 · 131 lines · 4 tokens per session scan A db2a57e14c39
conductor-revert is a command published in the GitHub repository Jonkimi/create-conductor-flow (5 stars, last pushed 5mo ago), licensed Apache-2.0. It adds 4 tokens to every session and 2,001 once invoked, about $0.0000 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…
flow-task
Run the canonical flow/task Flow lifecycle.
models
List models available to the local Antigravity (agy) CLI.
research
Delegate a thorough research investigation to the agy:runner subagent.
release
Prepare a release (step 1 of 2) — version bump and PR. Cutting the tag is a separate operator-only step.