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 skills add mmTheBest/Research-Architect --skill research-architect-auditgit clone --depth 1 https://github.com/mmTheBest/Research-ArchitectWrote 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/skills/mmthebest/research-architect/research-architect-audit)<a href="https://agentmods.dev/skills/mmthebest/research-architect/research-architect-audit"><img src="https://agentmods.dev/badge/skills/mmthebest/research-architect/research-architect-audit/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/skills/mmthebest/research-architect/research-architect-audit"><img src="https://agentmods.dev/badge/skills/mmthebest/research-architect/research-architect-audit.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00051 | $0.00855 |
| Opus 5.5 | $0.00020 | $0.00342 |
| Sonnet 5.5 | $0.00010 | $0.00171 |
| Haiku 4.5 | $0.00005 | $0.00085 |
Grade A, and why
research-architect-audit 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 1mo 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 — 61 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Research Architect Audit
Audit the available artifact trail and route each problem to the artifact that owns the decision. Do not turn missing evidence or provenance into a pass.
Inputs and shared resources
Read all available artifacts under paper_output/, especially the project configuration, terminology/object ledger, exemplar profile/adaptation, selected or confirmed spine, study design, evidence bank, claim register, display-system plan, evidence-display map, citation bank, promise-resolution map, blueprint, rationale matrix, and draft.
Read ../research-architect/references/quality-gates.md. Use ../research-architect/templates/audit_report.md as the output structure.
Create:
paper_output/audit_report.md
paper_output/revision_queue.md
paper_output/final_artifact_manifest.md
paper_output/run_manifest.json
paper_output/pipeline_state.json
Revised-draft and standalone path
Accept an external draft or a partial paper_output/ directory. If intake has not happened, collect the draft location, project scope, and constraints first. Record each missing upstream artifact as an intake_debts.md entry with its affected claim/gate, severity, and next owner. Audit the material that exists; label debts BLOCKED or scoped limitations instead of inventing a clean trail.
Use the audit to review a draft gate by gate: target-reference logic, adaptation, spine, feasibility, literature grounding, design, evidence, displays, citations, independence, completeness, and inference boundaries. Within the existing gates, also check that terminology/Object IDs are stable, the manuscript-wide display sequence assigns one non-overlapping job per display before panel detail, and every material promise resolves to evidence/warrant and bounded closure. Route framing failures to literature/brainstorm, design failures to design, evidence/display-readiness failures to evidence, citation failures to citation, and prose-only or promise-structure issues to draft.
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 1mo ago First seen · 61 lines · 51 tokens per session scan A 6fb25ddfd9e1
research-architect-audit is a skill published in the GitHub repository mmTheBest/Research-Architect (69 stars, last pushed 2mo ago), licensed MIT. It adds 51 tokens to every session and 855 once invoked, about $0.0002 per session on Opus 5.5. 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 2026-08-30.
Other skills, from other repositories
running-cluster-experiments
Use when planning, budgeting, submitting or resuming a multi-job experiment campaign on a Slurm/HPC cluster — sizing walltime, shaping jobs and arrays, deciding what to submit first, or after a job hit its walltime, produced no results, silently ran the wrong configuration, or got the wrong number of GPUs.
explaining-derivations
Use when a proof or derivation needs to be made explicit step by step — expanding a paper's algebra for a reader without formal mathematical training, producing a worked companion document, or establishing whether a derivation can be justified at all. Triggers on "explain this derivation", "walk me through this…
self-surveying-literature
Audit a research paper draft (LaTeX sources + .bib) for related work it should cite but does not, above all close prior work that undermines its novelty claims. Searches Semantic Scholar, arXiv, DBLP and Crossref, follows citation graphs, verifies every hit, and produces a prioritized, evidence-backed report plus…
paper-writer
Medical/scientific paper writing workflow skill. Manages the full pipeline from literature search to submission-ready manuscript. Creates and manages a project directory with IMRAD-format section files, literature matrix, reference management, and quality checklists. Supports both English and Japanese papers.…
proofreading-paper-writing
Use when asked to proofread, polish, or critique the writing of an academic paper from its LaTeX sources — grammar and mechanics, sentence clarity and style, paragraph flow, terminology and framing — and deliver the proposals as coloured track changes with margin comments plus a numbered writing report. Triggers on…
verifying-proofs
Use when checking the mathematics of a paper rather than its claims — verifying a theorem's proof, an algebraic derivation, a bound, or an appendix full of lemmas. Triggers on "check this proof", "verify the derivation", "is Lemma 3 correct", "does the algebra work", a paper directory containing theorem/proof…