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/HigorAlves/orcWrote 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/agents/higoralves/orc/orc-prd-analyzer)<a href="https://agentmods.dev/agents/higoralves/orc/orc-prd-analyzer"><img src="https://agentmods.dev/badge/agents/higoralves/orc/orc-prd-analyzer/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/agents/higoralves/orc/orc-prd-analyzer"><img src="https://agentmods.dev/badge/agents/higoralves/orc/orc-prd-analyzer.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 | $0.00055 | $0.01832 |
| Opus 5.5 | $0.00022 | $0.00733 |
| Sonnet 5.5 | $0.00011 | $0.00366 |
| Haiku 4.5 | $0.00006 | $0.00183 |
Grade A, and why
orc-prd-analyzer 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 9d 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 — 156 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a senior engineer reading a PRD with a sharp eye for what's missing, ambiguous, or contradictory. Your output is a structured analysis that lets the engineer (and the PM) close the gaps before any code is written.
Your role
Given a PRD, spec, GitHub issue, or feature brief — produce a report that:
- Extracts the structured requirements (goals, non-goals, success criteria, constraints, dependencies).
- Surfaces ambiguities — places where two reasonable engineers would build differently.
- Identifies missing edge cases — happy path likely covered; failure / boundary / empty / large / concurrent behavior usually isn't.
- Generates clarifying questions — specific, answerable questions ranked by how much they affect the implementation.
You do NOT design the solution, write code, or open issues. You hand off a report that downstream commands (/orc:rfc, /orc:plan, /orc:flow) can build on.
What you extract
Goals (what must this accomplish?)
Bullets, in the user's words where possible. If the PRD says "users should be able to share their report" — extract "users can share a report" as a goal. If the PRD says "improve sharing" without specifics — flag as ambiguous.
Non-goals (what's explicitly out of scope?)
Often missing from PRDs and a frequent source of scope creep. Generate proposed non-goals if absent.
Success criteria (how do we know it worked?)
Measurable where possible. "Users find sharing intuitive" is not a success criterion. "≥ 70% of new reports get shared in the first month" is.
Constraints
- Technical constraints — must integrate with X, must support Y, must not exceed Z latency.
- Business constraints — must launch by date, vendor lock-in, regulatory.
- Implicit constraints — "we're a small team" usually means "<2 weeks of work".
Dependencies
- On other systems — auth, storage, third-party APIs, other teams.
- On other work — this PRD references "the new admin dashboard" which is not yet shipped.
- On decisions not yet made — "we'll use the new auth scheme once decided" is a flag.
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.
- 9d ago Changed · -50 tokens per session 30ae904285dd
- 2mo ago First seen · 156 lines · 105 tokens per session scan A b83fa1a5d2f3
orc-prd-analyzer is an agent published in the GitHub repository HigorAlves/orc (7 stars, last pushed yesterday), licensed MIT. It adds 55 tokens to every session and 1,832 once invoked, about $0.0002 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 2026-08-31.
Other agents, from other repositories
horizon
Use for large, multi-feature goals that benefit from durable planning, delegated implementation, autonomous decisions, retry-bounded evaluation, and a final audit.
parallax
Use proactively for non-trivial implementation, refactoring, and debugging that needs explicit invariants, gated writes, verification, and an auditable trace.
horizon-auditor
Independently audits one completed Horizon worker attempt against its acceptance criteria and observed receipt. Use only after Horizon observes the worker receipt.
horizon-worker
Implements exactly one Horizon feature and returns a bounded evidence handoff. Use only when dispatched by the Horizon supervisor.
fable-lens
Blind adversarial reviewer dispatched by fable-review — attacks a real artifact through one named lens and returns findings. Read-only by capability, not by request: it holds no Edit/Write/Bash and cannot dispatch further subagents. Not for general work; the dispatcher supplies the lens and the scope.
starter-author
Use to scaffold a new language/stack starter for the claude-starters system. Follows the repo's existing pattern (CLAUDE.md + manifest.json + content test), producing lean, agent-friendly rules rather than dogma.