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/anombyte93/prd-taskmaster/execute-tasknpx skills add anombyte93/prd-taskmaster --skill execute-taskgit clone --depth 1 https://github.com/anombyte93/prd-taskmasterWhat 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 | $0.00098 | $0.04972 |
| Opus 5 | $0.00049 | $0.02486 |
| Sonnet 5 | $0.00020 | $0.00994 |
| Haiku 4.5 | $0.00010 | $0.00497 |
Grade A, and why
execute-task 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 yesterday.
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 — 420 lines — stays where its author put it; the contents beside it link to each section on GitHub.
execute-task
The execution loop. Three sources converge:
- Plan (HOW) —
docs/superpowers/plans/*.mdproduced by GENERATE - TaskMaster (WHAT) —
.taskmaster/tasks/tasks.jsonwith dependencies and complexity scores - CDD (PROOF) — acceptance cards per task, evidence-gated
execute-task is the single skill that runs the full build from "tasks are ready" to SHIP_CHECK_OK. It is autonomous — no AskUserQuestion inside the loop. Any gap that would require user input is surfaced through the recon escalation ladder (step 11) or the inbox (steps 4 and 8), never via a modal prompt.
Entry
This skill is invoked either:
- Directly by the user once HANDOFF has completed and a task-execution mode (A/B/C) has been dispatched, or
- By the
prd-taskmasterorchestrator whencurrent_phaseisEXECUTE.
On entry, confirm that:
.atlas-ai/state/pipeline.jsonexists and recordsphase: EXECUTE.taskmaster/tasks/tasks.jsonexists with at least one ready task.atlas-ai/customizations/system-prompt-template.mdis present (may be empty — absence is a setup bug, empty is fine)
If any of the above are missing, report the gap and halt. Do NOT attempt to bootstrap the missing artifact from inside this loop — that is the orchestrator's job.
Cycle (per iteration)
Each pass through this cycle moves exactly one TaskMaster task from pending
to done. Do the 13 steps in order. Do not skip.
Task-start SHA — at the very beginning of each iteration (before step 2), capture the current git HEAD:
task_start_sha=$(git rev-parse HEAD)Record
$task_start_shain the execute-log row for this iteration. It is the oracle of truth for every reachability sweep in step 9b below: "what modules did THIS task add?" isdiff $task_start_sha..HEAD. The oracle flow already issues per-task start commits; this surfaces the same value in the loop prose.
- Heartbeat check: verify the execute-task heartbeat timer is running.
If missing, register one via
CronCreate("execute-task-heartbeat", "* * * * *", "echo heartbeat"). Abort the iteration if the timer cannot be created — a missing heartbeat means a missing stuck-session detector, and that is load-bearing.
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.
- yesterday First seen · 420 lines · 98 tokens per session scan A 401a4088d221
execute-task is a skill published in the GitHub repository anombyte93/prd-taskmaster (592 stars, last pushed 18d ago), licensed MIT. It adds 98 tokens to every session and 4,972 once invoked, about $0.0005 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
PRD Mastery: Context-Aware, Expert-Driven, and Token-Efficient Refinement
A skill that blends the wisdom of top industry experts, ensures token-efficient PRDs, and organizes outputs in a clear folder structure.
PRD Mastery: Context-Aware, Expert-Driven, and Token-Efficient Refinement
A skill that blends the wisdom of top industry experts, ensures token-efficient PRDs, and organizes outputs in a clear folder structure.
agent-creator
Create and configure AiderDesk agent profiles by defining tool groups, approval rules, system prompts, subagent settings, subagent filtering, and provider/model selection. Use when setting up a new agent, creating a profile, or configuring agent tools, permissions, and subagent behavior.
ai-delivery-spec
Use for creating, changing, reviewing, reverse-engineering or accepting requirements, PRDs, prototypes, competitor material or existing systems, including any small UI, field, column, tab, dropdown or legacy-HTML change. Supports /ads, /dig, /prd and /proto intent shortcuts where the host routes them. Always invoke…
pm-skill-creator
Design a new PM skill through guided conversation. Use when you have raw content or an idea and want to shape it into a compliant skill.
productspec
Use when implementing, reviewing, planning, or changing work governed by a Product Spec. Treat .product-spec.md files as the product contract for the work.