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 gspencergoog/skills --skill proposal-writergit clone --depth 1 https://github.com/gspencergoog/skillsWrote 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/gspencergoog/skills/proposal-writer)<a href="https://agentmods.dev/skills/gspencergoog/skills/proposal-writer"><img src="https://agentmods.dev/badge/skills/gspencergoog/skills/proposal-writer/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/gspencergoog/skills/proposal-writer"><img src="https://agentmods.dev/badge/skills/gspencergoog/skills/proposal-writer.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 | $0.00076 | $0.00719 |
| Opus 5 | $0.00038 | $0.00360 |
| Sonnet 5 | $0.00015 | $0.00144 |
| Haiku 4.5 | $0.00008 | $0.00072 |
Grade A, and why
proposal-writer 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 yesterday.
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 — 90 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Writing technical proposals
Use this skill to write structured technical proposals for software products.
Choose the proposal depth
Select the appropriate template based on the size and complexity of the project:
- Lightweight: Use lightweight_template.md for small features, minor changes, or simple refactors.
- Standard: Use standard_template.md for typical features, new services, or moderate refactors.
- Detailed: Use detailed_template.md for major features, new products, or large-scale system migrations.
Use the /grill-me slash command to request the proposal depth or any
information needed to complete the proposal.
Gather information
Before writing, gather the necessary context:
- Identify the target audience (e.g., engineers, product managers, security teams).
- Define the problem being solved.
- Understand the constraints (e.g., time, resources, existing systems).
If the requirements are underspecified or if there are open design decisions,
recommend that the user runs the /grill-me slash command to resolve them
through an interactive interview.
Write the proposal
Follow the selected template. Apply these practices while writing:
Define explicit non-goals
Specify what is out of scope. List at least three non-obvious items that this proposal will not address. This prevents scope creep.
Include architecture diagrams
Create a Mermaid diagram in the "Proposed architecture" section to show how components interact. Verify that the diagram matches the text description.
Review APIs
If the proposal introduces new APIs or modifies existing ones, use the api-review skill to verify the API design.
Maintainability & Complexity Standards
Define explicit code health standards and maintainability metrics for the proposed design. Reference the cognitive-complexity skill when specifying limits on architectural branching and function complexity (e.g., standard threshold $\le 15$).
What ships with it
3 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- yesterday Changed · +7 lines 2df4799d2180
- 5d ago Changed · +5 lines 5a3d9413e09b
- 9d ago First seen · 78 lines · 76 tokens per session scan A feb20e63e56b
proposal-writer is a skill published in the GitHub repository gspencergoog/skills (2 stars, last pushed yesterday), licensed Apache-2.0. It adds 76 tokens to every session and 719 once invoked, about $0.0004 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 skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…