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 skills add jpoutrin/product-forge --skill parallel-task-formatgit clone --depth 1 https://github.com/jpoutrin/product-forgeWrote 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/jpoutrin/product-forge/parallel-task-format)<a href="https://agentmods.dev/skills/jpoutrin/product-forge/parallel-task-format"><img src="https://agentmods.dev/badge/skills/jpoutrin/product-forge/parallel-task-format/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/jpoutrin/product-forge/parallel-task-format"><img src="https://agentmods.dev/badge/skills/jpoutrin/product-forge/parallel-task-format.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00030 | $0.01705 |
| Opus 5.5 | $0.00012 | $0.00682 |
| Sonnet 5.5 | $0.00006 | $0.00341 |
| Haiku 4.5 | $0.00003 | $0.00170 |
Grade A, and why
parallel-task-format 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 — 214 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Task Specification Format
Compact YAML format for parallel task files in parallel/TS-XXXX-slug/tasks/.
Complete Task Example
---
id: task-001
component: users
wave: 1
deps: []
blocks: [task-004, task-005]
agent: python-experts:django-expert
skills: [python-experts:python-style, python-experts:django-dev, python-experts:django-api]
tech_spec: TS-0042
contracts: [contracts/types.py, contracts/api-schema.yaml]
---
# task-001: User Management
## Scope
CREATE: apps/users/{models,views,serializers,urls}.py, apps/users/tests/*.py
MODIFY: config/urls.py
BOUNDARY: apps/orders/*, apps/products/*, apps/*/migrations/*
## Requirements
- User model with email authentication
- UserSerializer with explicit fields
- UserViewSet (list, retrieve, create, update)
- Email uniqueness validation
## Checklist
- [ ] Model matches UserDTO in contracts/types.py
- [ ] API matches /api/users/* in contracts/api-schema.yaml
- [ ] pytest apps/users/ passes
- [ ] mypy apps/users/ passes
- [ ] ruff check apps/users/ passes
- [ ] No files modified outside scope
YAML Frontmatter Fields
| Field | Required | Description |
|---|---|---|
id |
Yes | Task identifier (task-NNN or task-NNN-component) |
component |
Yes | System component name |
wave |
Yes | Dependency wave number (1, 2, 3...) |
deps |
Yes | Task IDs this depends on (empty list [] if none) |
blocks |
No | Task IDs this blocks (optional) |
agent |
Yes | Recommended agent type |
skills |
Yes | Skills the agent should invoke (list from agent-skills-mapping.yaml) |
tech_spec |
No | Tech Spec ID (if applicable) |
contracts |
Yes | Contract files to reference (relative paths) |
Note: skills are stored in task files so prompt generation can include them in === REQUIRED SKILLS === sections. They are NOT stored in manifest.json.
Scope Section Format
Use compact notation with three directives:
CREATE
Files to create (use glob patterns). A file can only be in CREATE for ONE task.
CREATE: apps/users/{models,views,serializers,urls}.py, apps/users/tests/*.py
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 · 214 lines · 30 tokens per session scan A 32c9c5f4b16b
parallel-task-format is a skill published in the GitHub repository jpoutrin/product-forge (16 stars, last pushed 7mo ago), licensed MIT. It adds 30 tokens to every session and 1,705 once invoked, about $0.0001 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 2026-09-03.
Other skills, from other repositories
story-readiness
Checks whether a story is ready to implement: clear acceptance criteria, no open questions, valid ADR and dependencies. Use when the user asks if a story, or the sprint's stories, are ready to start or build.
recipe-create-meet-space
Create a Google Meet meeting space and share the join link.
workthreads
SpecStory Workthreads - a weekly work-thread rollup across a team's repos from SpecStory coding histories (any agent - Claude Code, Codex, Cursor, Gemini, and more). It groups the window's sessions into threads of work per project and labels each new / open / recently closed, so a lead sees what shipped, what is still…
atmos-config
Atmos root configuration: atmos.yaml discovery, precedence, deep merging, basepath, imports, minimal bootstrap, and routing to narrower Atmos skills.
handle-linkedin-connection-request-signal
Use this skill when someone sends a team member an inbound LinkedIn connection request. An inbound request is a deliberate, ACTIVE first-party intent signal — meaningfully stronger than a passive profile view — and it deserves different scoring rules. The skill resolves and enriches the requester, gates them through…
remove
Remove a deployed framework or addon from the current workspace.