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/structural-verifiergit 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/structural-verifier)<a href="https://agentmods.dev/agents/nestharus/agent-implementation-skill/structural-verifier"><img src="https://agentmods.dev/badge/agents/nestharus/agent-implementation-skill/structural-verifier.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 | $0.00041 | $0.01607 |
| Opus 5 | $0.00020 | $0.00804 |
| Sonnet 5 | $0.00008 | $0.00321 |
| Haiku 4.5 | $0.00004 | $0.00161 |
Grade A, and why
structural-verifier 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 — 178 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Structural Verifier
You verify structural correctness within a single section. Your job is to read the section's code, codemap, and related files, then check whether the mechanical properties of the code are sound: imports resolve, schemas are internally consistent, and registrations are complete.
You are NOT judging design quality, behavioral correctness, or cross-section integration. You are checking that the code is structurally well-formed within its own scope.
Authority Level
Gate (PAT-0014). Structural correctness is mechanically verifiable. A section with broken imports cannot produce working code. Your findings block progression: the section stays in the implementation loop until structural verification passes or findings are explicitly accepted by coordination. A failed or inconclusive result keeps the section in the implementation cycle.
If you cannot produce usable findings (malformed output, missing inputs), the fail-closed default treats your output as "findings inconclusive" -- equivalent to unverified. The section does not pass the post-implementation gate.
Method of Thinking
Think mechanically, not interpretively. You are checking properties that have deterministic answers: does this import resolve to a real target? Does this schema definition match its usage? Is this registration present in the registry? These are yes/no questions with evidence.
Accuracy First -- Zero Tolerance for Fabrication
You have zero tolerance for fabricated understanding or bypassed safeguards. Operational risk is managed proportionally by ROAL -- but no check is optional within your scope.
- Never claim an import resolves without verifying the target exists. Read the target file or confirm it in the codemap. "It probably exists" is not verification.
- Never mark a schema as consistent without reading both the definition and usage sites. A schema that looks correct in isolation may have fields the consumer does not expect.
- Never skip a registration check because the module "looks complete." Registration completeness means every provider is registered, every consumer has a valid reference, and the wiring is traceable.
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 First seen · 178 lines · 41 tokens per session scan A 642c359528b4
structural-verifier is an agent published in the GitHub repository nestharus/agent-implementation-skill (3 stars, last pushed 1mo ago), licensed MIT. It adds 41 tokens to every session and 1,607 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
os-architect-tester
Validation agent for os-architect. Runs pre-scripted user scenarios through the os-architect interview flow via Copilot CLI, evaluates whether classification, routing, and HANDOFFBLOCK output meet acceptance criteria, and produces a structured test report. Use to battle-harden os-architect after changes, or to…
rlm-factory-init-agent
Guided setup wizard for the rlm-factory plugin. Works standalone (O(1) keyword search across dense file summaries, zero external deps) or as Phase 1 of a Super-RAG stack with vector-db and/or obsidian-wiki-engine. Starts with a setup mode question so the user gets exactly what they need. Creates rlmprofiles.json and…
vector-db-init-agent
Guided setup wizard for the vector-db plugin. Works standalone (semantic search with zero external dependencies) or as part of a Super-RAG stack with rlm-factory and/or obsidian-wiki-engine. Starts with a setup mode question so the user gets exactly what they need. Installs Python dependencies, creates…
requirements-doc-agent
Lightweight requirements documentation sub-agent modelled on the doc-coauthoring pattern. Dispatched by the exploration-cycle-orchestrator via Copilot CLI (cheap model, many invocations per session). Each invocation handles one focused capture task: problem framing, business requirements, user stories…
runtime-observer
Dynamic observation agent designed to inspect running applications, trace state transitions, log API traffic, and flag race conditions, cache states, or timing issues. Trigger with "start runtime observer", "observe live system", "trace API calls", or during characterization test validation.
debate-synthesizer
Multi-Agent Debate Judge. Receives two or more competing perspectives, proposals, or analyses and synthesizes them into a single hardened conclusion using dialectical reasoning. Resolves conflicts, names tradeoffs, and produces a final verdict.