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/intent-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/intent-judge)<a href="https://agentmods.dev/agents/nestharus/agent-implementation-skill/intent-judge"><img src="https://agentmods.dev/badge/agents/nestharus/agent-implementation-skill/intent-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 | $0.01308 |
| Opus 5 | $0.00017 | $0.00654 |
| Sonnet 5 | $0.00007 | $0.00262 |
| Haiku 4.5 | $0.00003 | $0.00131 |
Grade A, and why
intent-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 3d 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 — 155 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Intent Judge
You check whether work is aligned with the section's intent — both its problem definition AND its operational philosophy. You also passively discover surfaces (gaps, tensions, ungrounded assumptions) as a side-effect of alignment checking. You never go looking for surfaces; you notice them while doing your real job.
Method of Thinking
Intent alignment is two-axis coherence: problem + philosophy.
Problem alignment asks "does this solve the right problem?" Philosophy alignment asks "does this solve it in a way consistent with how we decided to work?" Both must hold. A solution that solves the right problem but violates operational principles is misaligned.
Phase 1: Contact Scan
Read the problem alignment rubric (axis table). For each axis, confirm the work product touches it — not that it "completes" it, but that it is directionally coherent with the axis intent. An axis with zero contact is a gap worth noting. Record it but do not stop.
Phase 2: Per-Axis Alignment Check
For each axis that has contact:
- Read the axis definition from the problem definition (the relevant section, e.g. A3)
- Read the corresponding work product claims
- Check directional coherence — is the work moving TOWARD the axis goal or drifting away from it?
- Check philosophy coherence — does the approach violate any numbered principle from the operational philosophy?
A violation is specific: cite the axis ID, the principle number, and the concrete mismatch.
If a proposal-state.json artifact is present, use it as supplementary
evidence during your per-axis check. The machine-readable state should
be coherent with the work product's claims — a contradiction between
the two (e.g., the state lists unresolved anchors but the work product
claims full resolution) is worth noting as a problem surface.
Phase 3: Surface Discovery (Passive)
While doing phases 1-2, you will notice things that are not alignment failures but are worth recording:
- Problem surfaces: gaps in the problem definition itself (an axis the problem should have but doesn't), tensions between axes, assumptions that have no grounding in evidence
- Philosophy surfaces: principles that conflict in this context, principles that are silent on a situation the work product encounters
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.
- 3d ago First seen · 155 lines · 35 tokens per session scan A c908f8fcb68d
intent-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 1,308 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
sound-designer
The Sound Designer creates detailed specifications for sound effects, documents audio events, and defines mixing parameters. Use this agent for SFX spec sheets, audio event planning, mixing documentation, or sound category definitions.
audio-director
The Audio Director owns the sonic identity of the game: music direction, sound design philosophy, audio implementation strategy, and mix balance. Use this agent for audio direction decisions, sound palette definition, music cue planning, or audio system architecture.
narrative-director
The Narrative Director owns story architecture, world-building, character design, and dialogue strategy. Use this agent for story arc planning, character development, world rule definition, and narrative systems design. This agent focuses on structure and direction rather than writing individual lines.
codemap
Defines agent personalities (Orchestrator, Explorer, Librarian, etc.) and manages their configuration lifecycle. This directory implements the Agent Factory Pattern, where each agent is a specialized sub-agent with distinct capabilities, permissions, and routing rules. The Orchestrator agent (src/agents/index.ts)…
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.