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/firatcand/forge/draft-prdnpx skills add firatcand/forge --skill draft-prdgit clone --depth 1 https://github.com/firatcand/forgeWhat 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 | $0.00043 | $0.00521 |
| Opus 5 | $0.00022 | $0.00260 |
| Sonnet 5 | $0.00009 | $0.00104 |
| Haiku 4.5 | $0.00004 | $0.00052 |
Grade A, and why
draft-prd 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.
What it actually says
/draft-prd
Preconditions
spec/BRIEF.md must exist. If not, refuse and direct the user to /forge.
Orchestration
- Read
spec/BRIEF.md - Check if user has a
product-specskill globally — if yes, invoke it with BRIEF as input - Otherwise, use
templates/PRD.template.mdand walk Claude through filling each section - Per-feature discovery loop — for each item in
BRIEF.v1 scope:- Ask: "What does this feature do? What's the user flow?"
- Ask: "What's the success criteria for this feature? Edge cases or failure modes?"
- Ask: "What does this feature NOT do?" (per-feature non-goals)
- Capture answers as a per-feature subsection in PRD
- Cross-check generated PRD against BRIEF — flag any drift (new features outside v1 scope, definition-of-done that conflicts with BRIEF)
- Write to
spec/PRD.md
Required PRD sections
- Problem (synthesized from BRIEF, made concrete with specific user/moment/workaround)
- Target user (specific persona, JTBD format)
- Per-feature breakdown — for each v1 feature: what it does, user flow, acceptance criteria, edge cases, per-feature non-goals
- Acceptance criteria (overall v1) — testable bullets that prove v1 is done end-to-end
- Non-goals (must include all from BRIEF.non-goals)
- Constraints (budget, timeline, regulatory, integrations, secret management, task tracker)
Output
Print:
PRD written to spec/PRD.md
Per-feature acceptance preview:
- [feature 1]: [criterion]
- [feature 2]: [criterion]
Gate 2 — review the PRD. To proceed:
• /draft-spec to generate the technical SPEC
• /draft-design to generate the DESIGN doc (if UI surface)
• Edit spec/PRD.md directly
• /draft-prd --refine [section] to re-generate a section
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 · 52 lines · 43 tokens per session scan A 30cbd75aa6bc
draft-prd is a skill published in the GitHub repository firatcand/forge (13 stars, last pushed 1mo ago), licensed MIT. It adds 43 tokens to every session and 521 once invoked, about $0.0002 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
ospec-goal
Create or advance a full OSpec goal using the current document, task graph, worker, review, and evidence workflow.
ospec
Document-driven OSpec workflow for initialization, change/goal routing, validation, archiving, and durable project knowledge.
ospec-change
Create or advance a lightweight OSpec change using the classic fast workflow.
prospec-verify
Verify Implementation - Run 5+1 dimension audit (tasks, spec compliance, constitution, knowledge-implementation consistency, tests, design consistency) and assign quality grade (S/A/B/C/D). Triggers: verify, audit, quality check, 驗證, 稽核, 品質檢查, 評級.
prospec-archive
Archive Changes - Archive completed changes, generate summary, sync requirements to feature specs, and gate archiving on Knowledge sync. Triggers: archive, spec sync, finalize change, 封存, 歸檔, 收尾, 規格同步.
prospec-knowledge-generate
Generate AI Knowledge - Read raw-scan.md, analyze project structure, autonomously decide module boundaries, and produce Recipe-First module READMEs and index. Triggers: generate knowledge, analyze project, module split, 產生知識, 知識庫, 分析專案, 模組拆分.