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 skills/dowwie/tasker/orchestratornpx skills add Dowwie/tasker --skill orchestratorgit clone --depth 1 https://github.com/Dowwie/taskerWrote 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/skills/dowwie/tasker/orchestrator)<a href="https://agentmods.dev/skills/dowwie/tasker/orchestrator"><img src="https://agentmods.dev/badge/skills/dowwie/tasker/orchestrator.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 | $0.00049 | $0.13989 |
| Opus 5 | $0.00024 | $0.06994 |
| Sonnet 5 | $0.00010 | $0.02798 |
| Haiku 4.5 | $0.00005 | $0.01399 |
Grade A, and why
orchestrator 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 — 1,703 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Orchestrator v2
A thin coordination layer with two distinct modes:
- Plan Mode (
/plan) - Decompose spec into task DAG - Execute Mode (
/execute) - Run tasks via isolated subagents
Workflow Integration
The full workflow from requirements to implementation:
/specify → /plan → /execute
| Skill | Purpose | Input | Output |
|---|---|---|---|
/specify |
Design vision & capabilities | User requirements | {TARGET}/docs/specs/<slug>.md + .capabilities.json + ADRs |
/plan |
DAG construction (files → tasks) | Spec + capability map | Task DAG in .tasker/tasks/ |
/execute |
Implementation | Task DAG | Working code |
Entry points:
- From scratch → Run
/specifyfirst to develop spec and extract capabilities - Existing spec → Run
/plan {TARGET}/docs/specs/<slug>.mddirectly (may need capability extraction) - From /specify → Run
/plan {TARGET}/docs/specs/<slug>.md(skips to physical mapping)
Philosophy
The orchestrator does NOT:
- Track state itself (tasker CLI does this)
- Validate artifacts (tasker CLI does this)
- Compute ready tasks (tasker CLI does this)
The orchestrator ONLY:
- Queries state via
tasker state - Dispatches agents based on mode/phase
- Handles user interaction
- Ensures commits happen via
.claude/hooks/post-task-commit.sh(defense in depth)
Directory Initialization (After target_dir is known)
CRITICAL: After obtaining target_dir from the user, the orchestrator MUST initialize the .tasker/ directory structure. This is the ONLY place where directories are created - sub-agents assume directories already exist.
Setup (Run after target_dir is confirmed)
Initialize the .tasker/ directory structure:
TASKER_DIR="$TARGET_DIR/.tasker"
mkdir -p "$TASKER_DIR"/{artifacts,inputs,tasks,reports,bundles,logs}
This creates:
$TARGET_DIR/.tasker/artifacts/- For capability-map.json, physical-map.json$TARGET_DIR/.tasker/inputs/- For spec.md$TARGET_DIR/.tasker/tasks/- For T001.json, T002.json, etc.$TARGET_DIR/.tasker/reports/- For task-validation-report.md$TARGET_DIR/.tasker/bundles/- For execution bundles$TARGET_DIR/.tasker/logs/- For activity logging
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 · 1,703 lines · 49 tokens per session scan A 3982486dd482
orchestrator is a skill published in the GitHub repository Dowwie/tasker (19 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 49 tokens to every session and 13,989 once invoked, about $0.0002 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 skills, from other repositories
debug
Run /debug to find and fix a bug's root cause: a test failing for an unclear reason, /check verify finding a failure, or behavior being wrong. Runs a reproduce, localize, hypothesize, test, fix, verify loop, makes the minimal fix, and hands a regression test to /test. No features, no extra refactors.
red-team-adversarial
Adversarial security and resilience analysis — auto-triggered during /review and /test based on task classification. Provides attack surface analysis, boundary testing, auth bypass attempts, dependency chain attacks, and Beast Mode stress testing.
karpathy-principles
Behavioral guidelines to reduce common LLM coding mistakes — Think Before Coding, Simplicity First, Surgical Changes, Goal-Driven Execution.
database-design
Design schemas and migrations when persistent data structures change.
verification-before-completion
Enforce "no evidence = no completion"; run Gate Function verification before declaring done.
subagent-driven-development
Decompose tasks via subagent collaboration; define interface contracts and integration checkpoints.