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/jpoutrin/product-forgenpx agentmods add skills/jpoutrin/product-forge/prd-progressWrote 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/prd-progress)<a href="https://agentmods.dev/skills/jpoutrin/product-forge/prd-progress"><img src="https://agentmods.dev/badge/skills/jpoutrin/product-forge/prd-progress/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/prd-progress"><img src="https://agentmods.dev/badge/skills/jpoutrin/product-forge/prd-progress.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 | $0.00009 | $0.01194 |
| Opus 5.5 | $0.00004 | $0.00478 |
| Sonnet 5.5 | $0.00002 | $0.00239 |
| Haiku 4.5 | $0.00001 | $0.00119 |
Grade A, and why
prd-progress 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 — 162 lines — stays where its author put it; the contents beside it link to each section on GitHub.
prd-progress
Category: Product & Strategy
Usage
prd-progress <prd-file> [--detailed] [--format <format>]
Arguments
<prd-file>: Required - Path to the PRD file--detailed: Optional - Show individual task status--format: Optional - Output format (simple, detailed, json). Default: simple
Execution Instructions for Claude Code
When this command is run, Claude Code should:
- Read the PRD file and extract the task_file reference from metadata
- If no task file is linked, check standard locations:
./tasks/<prd-name>-tasks.md../tasks/<prd-name>-tasks.mdproduct-docs/tasks/<prd-name>-tasks.md
- Read the linked task file and parse task structure
- Count total tasks and completed tasks (marked with [x])
- Calculate completion percentage and other metrics:
- Tasks by priority (if specified)
- Parent vs subtask completion
- Estimated completion date (based on velocity)
- Display progress information in requested format
Task Parsing Rules
Recognize these task formats:
- [ ] Task not started
- [x] Task completed
- [-] Task in progress (count as 0.5 for progress)
- [~] Task cancelled (exclude from totals)
Parent/Child structure:
- [ ] 1.0 Parent task
- [x] 1.1 Subtask completed
- [ ] 1.2 Subtask pending
Output Formats
Simple Format (default)
📊 PRD Progress: user-authentication-frd.md
Progress: ████████████░░░░░░░░ 60% (12/20 tasks)
✅ Completed: 12 tasks
🔄 In Progress: 2 tasks
⏳ Remaining: 6 tasks
❌ Blocked: 0 tasks
Estimated completion: 2025-01-10 (4 days)
Detailed Format
📊 PRD Progress: user-authentication-frd.md
Overall: 60% complete (12/20 tasks)
By Section:
1. Database Setup ██████████ 100% (3/3)
2. API Implementation ████████░░ 80% (4/5)
3. Frontend UI ████░░░░░░ 40% (2/5)
4. Testing ██░░░░░░░░ 20% (1/5)
5. Documentation ████░░░░░░ 40% (2/5)
Recent Progress:
- ✅ 2025-01-05: Completed "Create user model"
- ✅ 2025-01-05: Completed "Setup auth endpoints"
- 🔄 2025-01-06: Started "Build login form"
By Priority:
- High: 75% (6/8)
- Medium: 50% (4/8)
- Low: 50% (2/4)
Velocity: 3 tasks/day (last 7 days)
Est. Completion: 2025-01-10
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 · 162 lines · 9 tokens per session scan A e8ebc5f87f89
prd-progress is a skill published in the GitHub repository jpoutrin/product-forge (16 stars, last pushed 7mo ago), licensed MIT. It adds 9 tokens to every session and 1,194 once invoked, about $0.0000 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.