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.
git clone --depth 1 https://github.com/mrvladd-d/memobankWrote 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/mrvladd-d/memobank/prd-to-tasks)<a href="https://agentmods.dev/commands/mrvladd-d/memobank/prd-to-tasks"><img src="https://agentmods.dev/badge/commands/mrvladd-d/memobank/prd-to-tasks.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 5.1 | $0.00018 | $0.02570 |
| Opus 5 | $0.00009 | $0.01285 |
| Sonnet 5 | $0.00004 | $0.00514 |
| Haiku 4.5 | $0.00002 | $0.00257 |
Grade A, and why
prd-to-tasks 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 8d 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 — 249 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/prd-to-tasks — Feature → Implementation plan → JSON tasks
0) Вход
Ожидается $ARGUMENTS:
FT-<NNN>для одной фичи--allдля декомпозиции всехFT-*по приоритету
Если аргумент не дан:
- interactive → попроси выбрать фичу
- autonomous → используй
--all
1) Decomposition preflight
Перед созданием или обновлением implementation plan и JSON task records проверь, что feature can be decomposed.
/prd-to-tasks does not require feature clarification metadata. The normal path is /write-prd → /spec-init → /prd → /spec-design → /spec-improve FT-<NNN> → /prd-to-tasks FT-<NNN>.
Для FT-<NNN>:
- Найди
.memory-bank/features/FT-<NNN>-*.md. - Прочитай frontmatter.
- Block only if the feature explicitly says clarification is not complete:
clarification_status: pending|blocked
Missing clarification metadata does not block decomposition.
clarification_status: complete is allowed but not required.
Block if relevant unresolved markers appear in behavior / acceptance / data / contracts / security / UX / operations / verification sections:
NEEDS CLARIFICATIONTBDTODO???
Do not block on those words in unrelated notes, changelog-like text, or historical context unless they affect task decomposition or verification.
If blocked:
- interactive mode: report the feature and tell the user to run
/clarify-feature FT-<NNN>or resolve the marker directly - autonomous mode: set terminal state
HALT_CLARIFICATION_REQUIRED - stop immediately before decomposition
- do not create or update implementation plans
- do not create, update, or index task records
For --all:
- resolve the full targeted feature set first
- if any targeted feature is missing, has
clarification_status: pending|blocked, or has blocking unresolved markers, halt before creating or updating task records for any feature - report all blocked feature IDs and their blockers
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.
- 8d ago First seen · 249 lines · 18 tokens per session scan A 31459a6c8bd7
prd-to-tasks is a command published in the GitHub repository mrvladd-d/memobank (55 stars, last pushed 3mo ago), licensed MIT. It adds 18 tokens to every session and 2,570 once invoked, about $0.0001 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 commands, from other repositories
template
Manage issue templates for streamlined issue creation.
sync-linear
Sync current work with Linear ticket status.
add-note
Add an internal or external note to a ConnectWise PSA ticket.
fest-show
Show festival progression (in-progress tasks, roadmap, and dependency view).
dispatcher
Pick the next-best repo to work on across the portfolio — rank free repos, recommend one, claim its lease atomically, and route to the entry command.
workpm
A project-management workflow for coordinating multiple AI workers through five stages. It includes task assignment, shared activity logs, worker replacement, and final checks.