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/madappgang/claude-code/new-trackgit clone --depth 1 https://github.com/MadAppGang/claude-codeWrote 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/madappgang/claude-code/new-track)<a href="https://agentmods.dev/commands/madappgang/claude-code/new-track"><img src="https://agentmods.dev/badge/commands/madappgang/claude-code/new-track.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 | $0.00012 | $0.02000 |
| Opus 5 | $0.00006 | $0.01000 |
| Sonnet 5 | $0.00002 | $0.00400 |
| Haiku 4.5 | $0.00001 | $0.00200 |
Grade A, and why
new-track 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 — 260 lines — stays where its author put it; the contents beside it link to each section on GitHub.
<user_request> $ARGUMENTS </user_request>
<conductor_required>
FIRST check if conductor/ directory exists with required files.
If not, HALT and guide user to run /conductor:setup first.
</conductor_required>
<context_awareness>
ALWAYS read these files before planning:
- conductor/product.md (understand project goals)
- conductor/tech-stack.md (know technical constraints)
- conductor/workflow.md (follow team processes)
</context_awareness>
<track_id_format>
Format: {shortname}_{YYYYMMDD}
Examples:
- feature_auth_20260105
- bugfix_login_20260105
- refactor_api_20260105
</track_id_format>
</critical_constraints>
<core_principles> Always create spec.md BEFORE plan.md. Spec defines WHAT, Plan defines HOW.
<principle name="Hierarchical Plans" priority="critical">
Plans must have:
- 2-6 Phases (major milestones)
- 2-5 Tasks per phase
- 0-3 Subtasks per task (optional)
</principle>
<principle name="Actionable Tasks" priority="high">
Each task must be:
- Specific (clear outcome)
- Estimable (roughly 1-4 hours)
- Independent (minimal dependencies)
</principle>
</core_principles>
<phase number="2" name="Context Loading">
<step>Read conductor/product.md</step>
<step>Read conductor/tech-stack.md</step>
<step>Read conductor/tracks.md for existing tracks</step>
</phase>
<phase number="3" name="Track Type">
<step>Ask: What type of work? [Feature, Bugfix, Refactor, Task, Other]</step>
<step>Ask: Short name for this track? (3-10 chars, lowercase)</step>
<step>Generate track ID: {type}_{shortname}_{YYYYMMDD}</step>
</phase>
<phase number="4" name="Spec Generation">
<step>Ask: What is the goal of this work? (1-2 sentences)</step>
<step>Ask: What are the acceptance criteria? (list 3-5)</step>
<step>Ask: Any technical constraints or dependencies?</step>
<step>Ask: Any edge cases or error scenarios to handle?</step>
<step>Generate conductor/tracks/{track_id}/spec.md</step>
</phase>
<phase number="5" name="Plan Generation">
<step>Based on spec, propose 2-6 phases</step>
<step>Ask user to confirm or modify phases</step>
<step>For each phase, generate 2-5 tasks</step>
<step>Add subtasks where complexity warrants</step>
<step>Generate conductor/tracks/{track_id}/plan.md</step>
</phase>
<phase number="6" name="Finalization">
<step>Create conductor/tracks/{track_id}/metadata.json</step>
<step>Update conductor/tracks.md with new track</step>
<step>Present summary to user</step>
</phase>
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 · 260 lines · 12 tokens per session scan A 070869e78c0c
new-track is a command published in the GitHub repository MadAppGang/claude-code (279 stars, last pushed 5mo ago), licensed MIT. It adds 12 tokens to every session and 2,000 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 2026-08-30.
Other commands, from other repositories
git
Git operations with intelligent commit messages and workflow optimization.
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.