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 commands/skullninja/coco-workflow/prdgit clone --depth 1 https://github.com/skullninja/coco-workflowWhat 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 | $0.00024 | $0.02433 |
| Opus 5 | $0.00012 | $0.01216 |
| Sonnet 5 | $0.00005 | $0.00487 |
| Haiku 4.5 | $0.00002 | $0.00243 |
Grade A, and why
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.
How it starts
The opening of the file, as written. The whole thing — 281 lines — stays where its author put it; the contents beside it link to each section on GitHub.
User Input
$ARGUMENTS
Setup
- Read
.coco/config.yamlfordiscovery.prd_path(default:docs/prd.md). - Load PRD template from
.coco/templates/prd-template.mdif it exists, otherwise use${CLAUDE_PLUGIN_ROOT}/templates/prd-template.md. - Determine mode:
- If
$ARGUMENTSstarts with "derive" -> Derive mode (satellite repo) - If
$ARGUMENTScontains "audit" -> Audit mode - Otherwise -> Greenfield mode (use
$ARGUMENTSas initial product description if non-empty)
- If
Mode 1: Greenfield (Default)
Guided interview producing a PRD from scratch.
1. Product Vision & Problem Statement
If $ARGUMENTS provides a product description, use it as context. Otherwise ask:
Use AskUserQuestion to gather:
- What is the product? (1-2 sentence vision)
- What problem does it solve? Who has this problem?
2. Target Users
Use AskUserQuestion to identify 1-3 user personas:
- Role/name for each persona
- Context (when/where they encounter the problem)
- Pain points (current frustrations)
- Goals (what they want to achieve)
3. Product Goals
Use AskUserQuestion to define measurable goals:
- 3-5 product goals
- Success metric for each
- Priority (P1/P2/P3)
4. Scope Boundaries
Use AskUserQuestion to establish scope:
- What is explicitly in scope?
- What is explicitly out of scope?
5. Constraints
Use AskUserQuestion to identify constraints:
- Technical (platform, language, infrastructure)
- Business (timeline, budget, regulatory)
- Design (UX principles, accessibility)
6. Feature Candidates
Use AskUserQuestion to brainstorm features:
- List candidate features (name + brief description)
- Map each to product goals
- Assign initial priority (P1/P2/P3)
Present the feature table and ask for additions or changes.
7. Open Questions
Identify unresolved questions that emerged during the interview. These are candidates for analysis documents.
8. Write PRD
Fill the PRD template with all gathered information. Ensure the directory exists:
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 · 281 lines · 24 tokens per session scan A fe0010f27fce
prd is a command published in the GitHub repository skullninja/coco-workflow (7 stars, last pushed 2d ago), licensed MIT. It adds 24 tokens to every session and 2,433 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 2026-08-31.
Other commands, from other repositories
super-dev
Command "super-dev" from shangyankeji/super-dev, covering /super-dev (claude-code), 输入, super dev runtime contract, local knowledge contract and 首轮响应契约（首次触发必须执行）.
super-dev-seeai
Command "super-dev-seeai" from shangyankeji/super-dev, covering /super-dev-seeai (claude-code), 输入, seeai 定位, 半小时时间盒 and 首轮输出模板.
implement
You are the phase dispatcher. Your job is to route implementation work to the correct phase agent with the right context.
retro
You are generating a retrospective report for a completed feature. Your job is to analyze git history and project artifacts to surface patterns, measure delivery quality, and suggest workflow improvements.
progress
You are generating a visual progress report showing which phases are complete, in-progress, or pending for the current feature.
commit
You are creating a conventional commit scoped to the current phase of work.