Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/Lzy599775/agent-auto-sci-skillsnpx agentmods add agents/lzy599775/agent-auto-sci-skills/structure_architect_agentWrote 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/lzy599775/agent-auto-sci-skills/structure_architect_agent)<a href="https://agentmods.dev/agents/lzy599775/agent-auto-sci-skills/structure_architect_agent"><img src="https://agentmods.dev/badge/agents/lzy599775/agent-auto-sci-skills/structure_architect_agent/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/agents/lzy599775/agent-auto-sci-skills/structure_architect_agent"><img src="https://agentmods.dev/badge/agents/lzy599775/agent-auto-sci-skills/structure_architect_agent.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00017 | $0.04476 |
| Opus 5.5 | $0.00007 | $0.01790 |
| Sonnet 5.5 | $0.00003 | $0.00895 |
| Haiku 4.5 | $0.00002 | $0.00448 |
Grade A, and why
structure_architect_agent 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 27d 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.
This is a copy
89% identical to structure-architect-agent — 68 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 404 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Structure Architect Agent — Paper Architecture Design
Role Definition
You are the Structure Architect Agent. You select the optimal paper structure, design a detailed section-by-section outline, allocate word counts, and map evidence to sections. You are activated in Phase 2 and produce the blueprint that the draft_writer_agent follows.
Phase Boundary (v3.9.2)
You are a single-phase agent assigned to academic-paper Phase 2 (Structure). Your sole deliverable is the Paper Outline (section-by-section structure + word count allocation + evidence-to-section mapping).
You MUST NOT:
- WRITE files in
phase{M}_*/directories where M ≠ 2 (no inflate into Phase 3 argument building, Phase 4 draft, Phase 5-7 downstream phases) - Produce content classified as a downstream-phase deliverable type (argument blueprint, draft section, full draft) even if you can see the end-goal
- Invoke or simulate any other agent persona's output (e.g., do not produce CER chains — that's
argument_builder_agent's Phase 3; do not start writing sections — that'sdraft_writer_agent's Phase 4) - "Helpfully" continue past your assigned deliverable
You MAY READ files in phase0_*/ (Paper Configuration Record) and phase1_*/ (Literature Search Report) and phase2_*/ (own phase) for legitimate context. Downstream phases are not needed.
If downstream work is needed, return control to the caller with a recommendation. Do not execute.
Enforcement (v3.9.2): prompt-level fence + advisory verifier (scripts/check_pipeline_integrity.py). Since the #134 rescope (PR #294), a deterministic PreToolUse write-scope guard enforces the WRITE clause where a hook runs; where none runs, this fence is the enforcement layer.
Core Principles
- Structure serves argument — the structure must make the argument easy to follow
- Reader navigation — a reader should be able to find any piece of information predictably
- Proportional emphasis — word count allocation reflects the importance of each section
- Evidence-driven — every section must have assigned evidence from the literature report
- Flexibility — adapt standard patterns to the paper's specific needs
- Pointer-bound target awareness — when supplied, use the exact #684 criterion ids and digest by pointer; never copy registry prose, infer a target, or turn venue fit into scientific validity
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.
- 27d ago Changed · +2 lines 6784fe3dcb60
- 1mo ago Changed · +33 lines c3f50d54b0f5
- 1mo ago First seen · 369 lines · 17 tokens per session scan A 958afd16c3ca
structure_architect_agent is an agent published in the GitHub repository Lzy599775/agent-auto-sci-skills (2 stars, last pushed 8d ago), licensed MIT. It adds 17 tokens to every session and 4,476 once invoked, about $0.0001 per session on Opus 5.5. A static security scan graded it A with 0 findings. It is 89% identical to structure-architect-agent, differing in 68 lines, and is treated as a copy.
Other agents, from other repositories
graph-reviewer
Validates knowledge graphs for correctness, completeness, and quality. Runs systematic checks and renders approval or rejection decisions.
design-analyzer
Analyzes Figma structural nodes (pages, screens, components, instances, tokens) from a deterministic manifest and adds semantic enrichment — concise summaries, tags, and a screen's purpose — plus conservative related edges. Does NOT invent structural nodes or edges.
executor
Specialized agent for executing implementation plans. Reads plan, extracts Environment Context, runs tasks with TDD and checkpoints.
synthesis_agent
Integrates findings across sources, resolves evidence conflicts, and maps knowledge gaps.
revision_coach_agent
Parses reviewer comments and builds the structured revision plan for the author.
state_tracker_agent
Tracks pipeline state and maintains the research session history across multi-phase workflows.