Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/varienos/agentic-workflownpx agentmods add commands/varienos/agentic-workflow/task-conductor.skeletonWrote 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/varienos/agentic-workflow/task-conductor.skeleton)<a href="https://agentmods.dev/commands/varienos/agentic-workflow/task-conductor.skeleton"><img src="https://agentmods.dev/badge/commands/varienos/agentic-workflow/task-conductor.skeleton/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/commands/varienos/agentic-workflow/task-conductor.skeleton"><img src="https://agentmods.dev/badge/commands/varienos/agentic-workflow/task-conductor.skeleton.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 | $0.00000 | $0.04914 |
| Opus 5.5 | $0.00000 | $0.01966 |
| Sonnet 5.5 | $0.00000 | $0.00983 |
| Haiku 4.5 | $0.00000 | $0.00491 |
Grade A, and why
task-conductor.skeleton 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 22d 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 — 542 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Task Conductor — plan-first phase orchestrator
Turns several backlog tasks into a phase plan first, and applies them only in an explicit
runmode. Usage:/task-conductor plan top 5,/task-conductor run top 5 --max-parallel 2,/task-conductor resume,/task-conductor status,/task-conductor abort
Basic Usage
- The default mode is PLAN. When the user does not type
run, the code will use the backlog's status, state, or change. runcommand requires explicit intent. Old commands (top 5,3,5,8,keyword auth) should be used with a comment like/task-conductor plan ....run allruns only with--confirm-all. Running all tasks at once is a high-risk operation; if the flag is not present, create a plan and stop.- Parallel writes only with an isolated worktree/branch. If isolation is missing or cannot be verified, process tasks in the same phase sequentially.
- Scoring agreement is identical to
/task-master. When formulas or weights change, both commands should be updated together. - Resume only continues from conductor state. State does not exist or schema is incompatible; start a new run and report to the user.
Command Usage
| Command | Example | Behavior |
|---|---|---|
| Plan Top X | plan top 5 |
Creates a plan for the top 5 highest-scoring tasks, stops execution |
| Plan All | plan all |
Plans and runs all tasks, with confirmation flag |
| Plan Manual ID | plan 3,5,8 |
Creates a plan for specific tasks by ID |
| Plan Keyword | plan keyword auth |
Plans tasks using a keyword-based authentication method |
| Run Top X | run top 5 --max-parallel 2 |
Runs the top 5 highest-scoring tasks with up to 2 parallel executions |
| Run All | run all --confirm-all |
Runs all tasks without confirmation flag, high-risk operation |
| Run Manual ID | run 3,5,8 |
Runs specific tasks by ID according to the plan |
| Run Keyword | run keyword auth |
Runs tasks using a keyword-based authentication method according to the plan |
| Resume | resume |
Continues from the last saved state in /conductor-state.json |
| Status | status |
Reads the current status and lock files, does not modify anything |
| Abort | abort |
Marks the active state as aborted, releases the lock, and does not modify the code |
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.
- 22d ago Changed · -35 lines 64e283446c83
- 1mo ago First seen · 577 lines · 0 tokens per session scan A 9ebfc7956e1a
task-conductor.skeleton is a command published in the GitHub repository varienos/agentic-workflow (59 stars, last pushed 23d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 4,914 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 2026-08-30.
Other commands, from other repositories
team-review
Coordinate a multi-role review of the current change.
review
A command for reviewing code with security checks and a check for compliance with MX tags. The available description does not explain what MX tags are.
repo-architect
Repository structure optimization and multi-repo management with ruv-swarm coordination for scalable project architecture and development workflows.
pr-enhance
Command "pr-enhance" from ruvnet/ruflo, covering pr-enhance, usage, options, examples and enhance pr.
gh-security-review
Use to perform a dedicated security review of current branch changes before pushing.
analytics-review
Review analytics and recent commits, then create tasks.