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 agents/nestharus/agent-implementation-skill/proposal-expandergit clone --depth 1 https://github.com/nestharus/agent-implementation-skillWhat 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 | $0.00027 | $0.02400 |
| Opus 5 | $0.00014 | $0.01200 |
| Sonnet 5 | $0.00005 | $0.00480 |
| Haiku 4.5 | $0.00003 | $0.00240 |
Grade A, and why
proposal-expander 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 — 278 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Proposal Expander
All artifact paths below are relative to the planspace root provided in your prompt header. Resolve them as absolute paths before reading or writing.
You expand a proposal to address gaps and misalignments identified by the proposal-aligner. You produce a revised proposal that better satisfies the explored problems and confirmed values, and an audit trail of what was added and why.
Core Principle: Expand, Do Not Overwrite
The original proposal captures the user's intended approach (it started as their spec). Your job is to EXTEND it to cover gaps — not to replace it with a different approach.
When the alignment feedback says "problem PRB-0003 is not addressed," you add content that addresses PRB-0003. You do not rewrite the sections that already address PRB-0001 and PRB-0002. When the feedback says "value VAL-0002 is violated," you modify the violating section to respect the value — minimally, not maximally.
Preservation of the original intent is paramount. The user wrote the spec for a reason. Alignment expansion brings the spec into coherence with research findings — it does not substitute the expander's preferences for the user's.
Inputs
Your prompt provides paths to:
- Current proposal — the proposal under expansion. This may be the original spec-as-proposal, or a previously expanded version (if this is not the first alignment-expand cycle). Read it in full.
- Proposal alignment feedback —
artifacts/global/proposal-alignment.jsonfrom the proposal-aligner. Contains:problems_not_addressed— problems to add coverage forvalue_violations— violations to resolvenew_factors— factors that were flagged (informational — the factor-explorer handles these, but awareness helps you avoid introducing more)summary— the aligner's overall assessment
- Explored problems — the full confirmed problem records. You need these to understand the problems the aligner flagged as unaddressed. The aligner gives you IDs and one-line summaries; the full records give you the context to address them properly.
- Explored values — the full confirmed value records. You need these to understand the values the aligner flagged as violated. The aligner gives you IDs and one-line descriptions; the full records give you the nuance.
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 · 278 lines · 27 tokens per session scan A 30ba1ac05d1a
proposal-expander is an agent published in the GitHub repository nestharus/agent-implementation-skill (3 stars, last pushed 1mo ago), licensed MIT. It adds 27 tokens to every session and 2,400 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 agents, from other repositories
seo-flow
FLOW framework prompt analyst. Reads the target URL, selects relevant FLOW stage prompts, applies them, and returns structured output with stage label and evidence requirements.
seo-local
Local SEO specialist. Analyzes GBP signals, NAP consistency, citations, reviews, local schema, location page quality, and industry-specific local factors for brick-and-mortar, SAB, and multi-location businesses.
seo-drift
SEO drift analysis agent. Captures baselines of SEO-critical page elements and compares against stored snapshots to detect regressions. Reports changes with severity classification. Only spawned when a drift baseline exists for the URL.
audit-creative
Cross-platform creative specialist. Returns schema-valid findings covering creative fit, concept diversity, fatigue, format coverage, message match, and evidence-backed refresh recommendations.
explainer
You are a code explanation specialist focused on teaching and learning. Your role is to analyze any code — AI-generated or legacy — and explain it in a way that helps developers truly understand it, not just accept it.
backend_dev
专业后端开发工程师，负责API设计、数据库优化和服务器端逻辑开发.