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-draftgit 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-draft)<a href="https://agentmods.dev/skills/mmthebest/research-architect/research-architect-draft"><img src="https://agentmods.dev/badge/skills/mmthebest/research-architect/research-architect-draft/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-draft"><img src="https://agentmods.dev/badge/skills/mmthebest/research-architect/research-architect-draft.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 | $0.00049 | $0.00977 |
| Opus 5 | $0.00024 | $0.00489 |
| Sonnet 5 | $0.00010 | $0.00195 |
| Haiku 4.5 | $0.00005 | $0.00098 |
Grade A, and why
research-architect-draft 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 10d 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 — 59 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Research Architect Draft
Draft from verified research decisions and evidence; do not use prose to conceal missing research work.
Required inputs
Before new prose drafting, require:
paper_output/confirmed_research_spine.md
paper_output/evidence_bank.md
paper_output/claim_register.md
paper_output/citation_support_bank.md
paper_output/terminology_ledger.md # when terms or object identities can drift
paper_output/display_system_plan.md # for multi-display manuscripts
paper_output/evidence_display_map.md
paper_output/exemplar_adaptation_plan.md # when target references exist
recorded MANDATORY Gate 3 evidence readiness
If evidence is incomplete, create or update paper_output/execution_plan.md from ../research-architect/templates/execution_plan.md and return to evidence/design; do not draft around the gap.
Read ../research-architect/references/first-draft-architecture.md and
../research-architect/references/evidence-first-drafting.md. Read
../research-architect/references/terminology-and-object-identity.md when a
ledger is needed but absent or unresolved. Use
../research-architect/templates/promise_resolution_map.md,
../research-architect/templates/section_blueprints.md, and
../research-architect/templates/writing_rationale_matrix.csv; write tabular
artifacts as Markdown under paper_output/.
Evidence-first phases and outputs
- Lock objects. Create or refresh
paper_output/terminology_ledger.mdwhen recurring terms, metrics, datasets, cohorts, model states, conditions, or symbols can drift. Resolve material collisions before prose. - Map promises. Create
paper_output/promise_resolution_map.md. Give every material question, hypothesis, capability, comparison, mechanism, contribution, or scope promise a stable Promise ID and map it to Claim IDs, evidence/citation/display IDs, bounded closure, and any remaining gap. Produce evidence, narrow, or remove an unresolved central promise. - Order evidence. For empirical work, draft Results/findings first, then frame the Introduction around what those results resolve, draft Discussion around the supported answer and alternatives, finalize Methods from the approved/executed record, and write the title and abstract after the argument stabilizes. For other design families, draft the claim-bearing analysis, synthesis, case, or argument blocks first and adapt the architecture.
- Blueprint. Create
paper_output/section_blueprints.mdandpaper_output/writing_rationale_matrix.md. Each unit identifies its Promise IDs, Object IDs, research-spine link, reference-derived function, project-specific adaptation, evidence/citation/display anchors, planned move, closure or remaining gap, claim boundary, and draft sequence. - Prose. Create
paper_output/first_draft/main.mdandpaper_output/final_artifact_manifest.md; createmain.texonly when useful.
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.
- 10d ago First seen · 59 lines · 49 tokens per session scan A 68f6df5c1827
research-architect-draft is a skill published in the GitHub repository mmTheBest/Research-Architect (68 stars, last pushed 1mo ago), licensed MIT. It adds 49 tokens to every session and 977 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 2026-08-30.
Other skills, from other repositories
secure-auth
Secure authentication patterns (OWASP, NIST). Use for login, registration, password reset, sessions, JWT, OAuth, MFA, passkeys.
academic-writing
Scholarly writing and research compliance. Use for CRediT, preregistration, Plan S, Nelson Memo, preprints, ORCID, LLM disclosure.
page-monitoring
Web page change detection, availability tracking, and RSS feed generation. Use to monitor changes, downtime, or make a feed.
web-archiving
Web archiving and retrieval via Wayback Machine and Archive.today. Use to preserve content, reach dead pages, or save evidence.
accessibility-compliance
Web accessibility patterns for news and academic sites. Use for WCAG audits, alt text, accessible data viz, and assistive tech.
one-way-door
Flags irreversible decisions before commit. Use for data models, infra, auth boundaries, API contracts, event schemas, CI/CD.