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/anombyte93/prd-taskmasternpx agentmods add skills/anombyte93/prd-taskmaster/customise-workflowWrote 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/anombyte93/prd-taskmaster/customise-workflow)<a href="https://agentmods.dev/skills/anombyte93/prd-taskmaster/customise-workflow"><img src="https://agentmods.dev/badge/skills/anombyte93/prd-taskmaster/customise-workflow/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/skills/anombyte93/prd-taskmaster/customise-workflow"><img src="https://agentmods.dev/badge/skills/anombyte93/prd-taskmaster/customise-workflow.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 2 findings, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Excessive Agency · line 174 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
- medium Excessive Agency · line 225 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
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 | $0.00137 | $0.02033 |
| Opus 5.5 | $0.00055 | $0.00813 |
| Sonnet 5.5 | $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 1mo 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.
- 1mo 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 (606 stars, last pushed 2mo ago), licensed MIT. It adds 137 tokens to every session and 2,033 once invoked, about $0.0005 per session on Opus 5.5. 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
ai-prd-generator
PRD generator for AI features (LLM or ML). Before an AI feature goes to engineering, lists the decisions still open - failure handling, human review, evaluation - then builds a PRD with problem, users, scope, non-goals, user stories, and Given/When/Then acceptance criteria through 4 user-approved stages (or a one-shot…
meeting-notes
Estructura y formatea notas de reunión siguiendo las mejores prácticas de PM. Úsalo cuando te pidan crear notas de reunión, formatear notas de discusión, capturar elementos de acción, o documentar decisiones de cualquier tipo de reunión. Produce notas estructuradas con decisiones, elementos de acción (responsable +…
incident-postmortem
Escribe un postmortem de incidente estructurado o revisión post-incidente. Úsalo cuando se te pida escribir un postmortem, reporte de incidente, revisión P1/P2, reporte de apagón o RCA (análisis de causa raíz). Produce un postmortem sin culpables con cronología, causa raíz, factores contribuyentes, resumen de impacto…
stakeholder-update
Crear actualizaciones ejecutivas concisas para stakeholders usando el framework BLUF (Bottom Line Up Front). Usa cuando te pidan escribir una actualización de estado, reporte de progreso, comunicación de proyecto o briefing ejecutivo para liderazgo o stakeholders. Produce una actualización encabezada por BLUF con…
technical-debt-register
Documenta y prioriza un backlog de deuda técnica con impacto empresarial, estimaciones de esfuerzo y estrategia de resolución. Úsalo cuando se te pida auditar deuda técnica, crear un registro de deuda, priorizar deuda técnica para un trimestre, documentar atajos arquitectónicos o construir una hoja de ruta de…
cs-health-scorecard
Construir un cuadro de mando de salud del cliente para una cuenta específica. Úsalo cuando te pidan calificar la salud de la cuenta, evaluar el riesgo de renovación, construir un panel de salud o evaluar la probabilidad de que una cuenta se renueve o expanda. Produce un cuadro de mando de salud estructurado con estado…