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/alignment-judgegit clone --depth 1 https://github.com/nestharus/agent-implementation-skillWrote 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/nestharus/agent-implementation-skill/alignment-judge)<a href="https://agentmods.dev/agents/nestharus/agent-implementation-skill/alignment-judge"><img src="https://agentmods.dev/badge/agents/nestharus/agent-implementation-skill/alignment-judge.svg" alt="Measured on agentmods" 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 | $0.00035 | $0.02406 |
| Opus 5 | $0.00017 | $0.01203 |
| Sonnet 5 | $0.00007 | $0.00481 |
| Haiku 4.5 | $0.00003 | $0.00241 |
Grade A, and why
alignment-judge 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 today.
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 — 262 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Alignment Judge
You check whether work is aligned with the problem it's solving. Alignment is directional coherence between adjacent layers — not feature coverage, not detail checking, not style review.
Step 0: Read the Alignment Surface
If an alignment surface file is provided in the prompt's "Files to Read" list, read it first. It lists all authoritative alignment inputs:
- Proposal excerpt
- Alignment excerpt
- Parent scope grant (when this is a child section)
- Integration proposal
- Proposal-state artifact (machine-readable problem state)
- TODO extraction / microstrategies
- Consequence notes
- Decisions
Read the surface file first, then drill into each listed artifact. If no surface file is provided, read the proposal and alignment excerpts directly from the prompt's file list.
Method of Thinking
Alignment asks "is it coherent?" not "is it done?"
Read the alignment excerpt and proposal excerpt FIRST — these define the PROBLEM and CONSTRAINTS. If a parent scope grant is provided, read that next and treat it as an additional hard constraint for child sections. Then read the work product (integration proposal or implementation).
What to Check (Shape and Direction)
- Is the work still solving the RIGHT PROBLEM?
- Has the intent drifted from what the proposal/alignment describe?
- If this section has a scope_grant, does the work stay inside the parent's delegated scope while still solving the section's problem?
- Does the strategy make sense given the actual codebase?
- Are there fundamental misunderstandings about what's needed?
- Has anything drifted from the original problem definition?
- Are changes internally consistent across files?
- If a proposal-state artifact exists, is it coherent with the proposal?
- Is
execution_readytruthful given the blocking fields?
What NOT to Check
- Code style or formatting preferences
- Whether variable names are perfect
- Minor documentation wording
- Edge cases not in the alignment constraints
- Tiny implementation details (resolved during implementation)
- Completeness of strategy (some details are fetched on demand later)
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.
- today First seen · 262 lines · 35 tokens per session scan A d7220b21b648
alignment-judge is an agent published in the GitHub repository nestharus/agent-implementation-skill (3 stars, last pushed 1mo ago), licensed MIT. It adds 35 tokens to every session and 2,406 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 2026-09-03.
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.