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 OutlineDriven/odin-gemini-cli-extension --skill to-prdgit clone --depth 1 https://github.com/OutlineDriven/odin-gemini-cli-extensionWrote 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/outlinedriven/odin-gemini-cli-extension/to-prd)<a href="https://agentmods.dev/skills/outlinedriven/odin-gemini-cli-extension/to-prd"><img src="https://agentmods.dev/badge/skills/outlinedriven/odin-gemini-cli-extension/to-prd/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/outlinedriven/odin-gemini-cli-extension/to-prd"><img src="https://agentmods.dev/badge/skills/outlinedriven/odin-gemini-cli-extension/to-prd.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 | $0.00069 | $0.00982 |
| Opus 5 | $0.00034 | $0.00491 |
| Sonnet 5 | $0.00014 | $0.00196 |
| Haiku 4.5 | $0.00007 | $0.00098 |
Grade A, and why
to-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 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.
This is a copy
100% identical to to-prd — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 77 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Synthesize a PRD from what you already know. Do NOT interview — extract from context, codebase exploration, and prior decisions. Iterate the artifact in place; commit when the user signs off.
Emission Modes [LOCKED]
Default (file mode): Write to <project-root>/docs/prd/<feature>.md. Idempotent — overwrite on rerun. Use file mode when no flag is passed, when working offline, when the repo has no GitHub remote, or when the user explicitly wants a tracked file.
Flag mode (--emit-issue): Submit via gh issue create --title "PRD: <feature>" --body-file <tmp>. Use only when the user explicitly opts in or the project's convention is issue-tracked PRDs (check <project-root>/CONTRIBUTING.md and .github/ISSUE_TEMPLATE/).
When ambiguous, default to file mode and ask the user one targeted question rather than guessing.
Process
1. Reuse priming if available; explore only when context is thin
If conversation context already covers domain language, naming conventions, and module shape, skip discovery and proceed to step 2. Otherwise dispatch an Explore agent over the codebase. Goal: current architectural state, naming conventions, ADRs, domain language. Read CONTEXT.md, AGENTS.md, docs/adr/, and any UBIQUITOUS_LANGUAGE.md. Use fd -e md . docs/ then bat -P -p -n -r for targeted reads.
2. Identify deep modules
Sketch modules to build or modify. Prefer deep modules — large functionality behind a narrow, stable interface — over shallow modules. Surface 3-7 candidates and their interfaces. Recommend which modules deserve isolated tests; defer to user on edge cases.
3. Verify intent only when blocked
If the module breakdown is unambiguous from prior context, skip this step and proceed to writing. Ask the user only when an axis (scope, depth, or test coverage) is genuinely unresolved or when a decision is reversible-but-costly. Surface one unresolved axis at a time with a recommendation; never ask three default-bound axes at once.
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 First seen · 77 lines · 69 tokens per session scan A 987bfc065b09
to-prd is a skill published in the GitHub repository OutlineDriven/odin-gemini-cli-extension (5 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 69 tokens to every session and 982 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. It is 100% identical to to-prd, differing in 0 lines, and is treated as a copy.
Other skills, from other repositories
design
Set visual and interaction direction for any UI surface (web, React, TUI, CLI, desktop, Qt, design-system tokens) before any UI code. Direction-first: generates 3-4 distinct directions via verbalized sampling, picks one via per-axis single-select, then derives palette, typography, spacing, motion budget. Loads when…
askme
Verbalized Sampling (VS) protocol for intent exploration before planning, mode-aware. Default exhaustive runs full VS; collaborative runs tip-sharing dialogue; adversarial walks the design tree one fork at a time. Auto-detects from phrasing ("help me refine" → collaborative, "poke holes" → adversarial); override via…
git-branchless
Enforce idiomatic git-branchless during planning and executing tasks — detached-HEAD-first work, in-memory rebase via git move, event-log recovery via git undo, deferred branch creation, speculative-merge git sync for base updates. Use when planning or executing multi-commit work, history rewrites, stack edits…
grill-ai-mastery
Hybrid interview that probes AI-engineering mastery by tip-vocabulary depth — entity referencing, loop closure, observability, harness improvement — not by token usage or LOC. Start collaborative (two-way tip exchange), escalate to adversarial probing when depth is lacking. Trigger when the user says "interview me on…
grill-me
Adversarial relentless interview against any plan or design until shared understanding is reached. Walk the decision tree, resolve dependencies one answer at a time, recommend a default per question. Trigger when the user says "grill me", "stress-test this", "interview me about this design", or otherwise asks for…
proof-driven
Proof-driven development. Use when implementing with formal verification using property-based testing, theorem proving, or proof tactics; zero unproven property policy enforced.