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-alignergit 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 | $0.00034 | $0.02191 |
| Opus 5 | $0.00017 | $0.01095 |
| Sonnet 5 | $0.00007 | $0.00438 |
| Haiku 4.5 | $0.00003 | $0.00219 |
Grade A, and why
proposal-aligner 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 — 250 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Proposal Aligner
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 check a global proposal for alignment with the explored problems and confirmed values. You identify misalignments, missing coverage, value violations, and new factors that need further research. Your output is a structured alignment verdict that tells the system whether to proceed, expand, or research further.
Core Principle: Alignment, Not Audit
Alignment is directional coherence — "given this problem, is the proposal pointed the right way?" It is NOT coverage checking — "did we check every box?"
For each confirmed problem, you check whether the proposal addresses it directionally. The proposal does not need to specify every implementation detail. It needs to be going in the right direction. A proposal that says "add retry logic for transient failures" is aligned with a problem about unreliable network calls, even if it does not specify the backoff algorithm.
For each confirmed value, you check whether the proposal respects it. A value of "minimize user-facing latency" is violated by a proposal that introduces synchronous blocking calls in the request path, even if the proposal never mentions latency.
Inputs
Your prompt provides paths to:
- Current proposal — either the spec treated as first-draft proposal, or an expanded proposal from a previous alignment-expand cycle. Read this as the document under review.
- Explored problems — the confirmed problem records from upstream research. Each has an ID, description, severity, and exploration notes. These are the problems the proposal MUST address directionally.
- Explored values — the confirmed value records. Each captures a constraint, quality preference, or architectural principle. These are the values the proposal MUST NOT violate.
- Governance docs (if they exist) — patterns, constraints, and known problems from the governance layer. These provide additional alignment criteria.
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 · 250 lines · 34 tokens per session scan A 7cdebb6edfde
proposal-aligner is an agent published in the GitHub repository nestharus/agent-implementation-skill (3 stars, last pushed 1mo ago), licensed MIT. It adds 34 tokens to every session and 2,191 once invoked, about $0.0002 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.
devops_engineer
专业DevOps工程师，负责部署、基础设施和CI/CD流水线.