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/customise-workflownpx skills add anombyte93/prd-taskmaster --skill customise-workflowgit 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 | $0.00137 | $0.02033 |
| Opus 5 | $0.00068 | $0.01017 |
| Sonnet 5 | $0.00027 | $0.00407 |
| Haiku 4.5 | $0.00014 | $0.00203 |
Grade A, and why
customise-workflow 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 2d 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 — 236 lines — stays where its author put it; the contents beside it link to each section on GitHub.
customise-workflow
AI-driven workflow customisation for the prd-taskmaster plugin.
Replaces manual JSON editing. Part of the plugin's companion-skills family.
Script: skills/customise-workflow/script.py (all commands output JSON)
Plugin config root: .atlas-ai/ (per-project, lives alongside TaskMaster's
.taskmaster/)
When to Use
Activate when the user says: "customise workflow", "customize workflow", "adjust PRD settings", "tune the skill", "change my defaults", or "personalise prd-taskmaster".
Skip: generating a new PRD (use /prd:go), executing tasks (use
HANDOFF modes), or running research expansion (use /expand-tasks).
The One Rule
The AI asks the questions and writes the config. The user never manually
edits JSON. The config file is the output, not the input. If the user wants
tweaks beyond the curated questions, point them at .atlas-ai/customizations/
(see "Customizations directory" below) — do not hand them raw JSON.
Flow
LOAD → ASK → VALIDATE → WRITE → VERIFY
Phase 1: LOAD current config
Run the script to load existing preferences (or defaults if first run):
python3 skills/customise-workflow/script.py load-config
Returns JSON with current preferences across 6 categories: provider,
validation, execution, template, autonomous, gates. Writes to
.atlas-ai/config/atlas.json if missing, seeding defaults.
Phase 2: ASK curated questions
Read questions/curated-questions.md and ask each one via AskUserQuestion.
The questions are curated so plain-English answers map cleanly to config keys.
Example:
Q1: Which AI provider do you prefer for task generation?
Options: Gemini (free, token-efficient), Claude Code (free, Max only),
OpenAI GPT-4, Anthropic Direct API, OpenRouter, Ollama (local)
Q2: How strict should PRD validation be?
Options: Strict (block on NEEDS_WORK), Normal (warn but allow GOOD+),
Lenient (accept ACCEPTABLE+)
Q3: Which execution mode should prd-taskmaster default to?
Options: A (Plan Mode), B (Ralph loop), C (Atlas Fleet), ...
...
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.
- 2d ago First seen · 236 lines · 137 tokens per session scan A 95fee6da01b8
customise-workflow is a skill published in the GitHub repository anombyte93/prd-taskmaster (593 stars, last pushed 19d ago), licensed MIT. It adds 137 tokens to every session and 2,033 once invoked, about $0.0007 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
recipe-define
Creates a delivery-ready PRD from validated hypotheses with material 4 Risks evidence and necessary traceability. Use when turning validation results into requirements or user stories.
prd-os
PRD creation and PRD execution operating system. Use when the founder asks to turn a rough idea into a PRD, run a Codex review on a PRD or issue, decompose an approved PRD into issue specs, or execute an issue with scope enforcement and receipt-based closeout. Not for general product ideation or casual drafting; this…
feature-prioritization
Prioritize features and backlog items using RICE scoring and Linear's enablers vs blockers lens. Use when asked to rank features, prioritize a backlog, decide what to build next, or evaluate feature requests against each other.
roadmap-planning
Create outcome-based roadmaps using Now/Next/Later instead of Gantt charts. Use when asked to create a roadmap, plan quarterly, organize milestones, or figure out what to build over the next few months. Anti-date, anti-feature-list, pro-outcome.
scope-cutting
Cut scope ruthlessly using Shape Up's appetite-first approach. Use when asked to reduce scope, find the MVP, trim features, ship faster, or figure out what to cut. Applies fixed time variable scope thinking and scope hammering techniques.
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.