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.
git clone --depth 1 https://github.com/Marazii/research-co-pilotWrote 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/commands/marazii/research-co-pilot/talk)<a href="https://agentmods.dev/commands/marazii/research-co-pilot/talk"><img src="https://agentmods.dev/badge/commands/marazii/research-co-pilot/talk.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 5.1 | $0.00023 | $0.00386 |
| Opus 5 | $0.00012 | $0.00193 |
| Sonnet 5 | $0.00005 | $0.00077 |
| Haiku 4.5 | $0.00002 | $0.00039 |
Grade A, and why
talk 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 7d 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.
What it actually says
Invoke the talk-builder skill from the research-co-pilot plugin and execute its full workflow.
The skill file is at skills/talk-builder/SKILL.md relative to this plugin. Read it and follow it precisely — including:
- Phase 1: Intake (paper, length, format, venue, audience, your role, slide platform, constraints).
- Phase 2: Pick the structure (length × audience × discipline scaffolds; format-specific moves).
- Phase 3: Storyboard the arc as a sequence of beats with timing.
- Phase 4: Per-slide content (visual, on-slide text, speaker notes, anticipated reaction, transition).
- Phase 5: Opening hook (60 seconds).
- Phase 6: Take-home and closing (one-sentence take-home).
- Phase 7: Backup slides for the 3-5 most-anticipated questions.
- Phase 8: Speaker notes and rehearsal plan.
- Phase 9: Output
talk_<short_title>_<minutes>min.md(plus optional Marp / Quarto / reveal.js / Beamer stub). - Phase 10: Self-audit (timing, take-home, one-idea-per-slide, accessibility).
The paper is not the talk. Cut to fit the time. Frame for the audience.
User input: $ARGUMENTS
If no paper / length / venue were given, ask for: path to the paper, talk length in minutes (and whether Q&A is included), venue + format (contributed / lightning / invited / plenary / keynote / defense / job talk / public lecture / course lecture), audience description, and your role.
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.
- 7d ago First seen · 26 lines · 23 tokens per session scan A 1943d4f21684
talk is a command published in the GitHub repository Marazii/research-co-pilot (13 stars, last pushed 3mo ago), licensed MIT. It adds 23 tokens to every session and 386 once invoked, about $0.0001 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 commands, from other repositories
openehr-explain
One-stop router that explains or looks up any openEHR thing — auto-detects an archetype, a template, an RM/AM/BASE type, an RM structural concept, an ADL idiom, an AQL query or keyword, or a terminology code (replaces /archetype-explain, /template-explain, /type-spec, /rm-structure, /adl-idiom, /terminology).
ars-revision-coach
ARS academic-paper revision-coach — peer-review roadmap or source-accounted real-committee response skeleton.
eli-expert
Explain a topic at an expert level, assuming deep background and going straight to the substance.
thesis
Plan, structure, or strengthen a PhD/research thesis or dissertation in AEC.
srs-sm
Draft and QC the Supplementary Materials: scope approval → SM writing → figure QC for SM figures.
checklist
Generate a custom checklist for the current feature based on user requirements.