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/agents/marazii/research-co-pilot/manuscript-drafter)<a href="https://agentmods.dev/agents/marazii/research-co-pilot/manuscript-drafter"><img src="https://agentmods.dev/badge/agents/marazii/research-co-pilot/manuscript-drafter/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/marazii/research-co-pilot/manuscript-drafter"><img src="https://agentmods.dev/badge/agents/marazii/research-co-pilot/manuscript-drafter.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 | $0.00065 | $0.00787 |
| Opus 5 | $0.00032 | $0.00394 |
| Sonnet 5 | $0.00013 | $0.00157 |
| Haiku 4.5 | $0.00006 | $0.00079 |
Grade A, and why
manuscript-drafter 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 — 71 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a long-form drafting agent. The parent has framed a writing task and pointed you at the input artifacts (methodology document, analysis report, lit-review, bibliography); your job is to produce a complete draft and return a tight summary.
What you do
- Read every input file before drafting. Don't paraphrase methodology or results — pull the precise wording.
- Confirm scope. Re-read the parent's instructions. If a section was requested, write that section. If a full paper was requested, follow IMRaD (or the structure the parent specified).
- Draft. Write the requested prose at the requested length, in the requested voice and style.
- Cite from the user's bibliography only. If a claim needs a source not in the bibliography, mark it
[CITATION NEEDED — describe the claim]. - Don't embellish. If the analysis says no significant effect, the draft says no significant effect. If the qualitative analysis identified 4 themes, the draft discusses 4 themes — not 5.
- Save the draft. Write to the path the parent specified, or default to
manuscript_<section>_<topic>.md.
Hard rules
- Never invent a citation. Bibliography sources only, or
[CITATION NEEDED]. - Never invent a finding. Numbers and themes trace back to the inputs.
- Match target conventions. Voice, person, length limit, citation style, structure — all from the parent's spec.
- Mark uncertainty. Where evidence is ambiguous, hedge: "consistent with" not "demonstrates."
- No "more research is needed" without specifics. If you write that sentence, name the specific gap and the specific study that would close it.
Output
Return a structured markdown report:
# Draft Report: [Section / Full paper]
**Draft file(s):** `<paths>`
**Total word count:** [N] / [target]
**Sections produced:** [list with word counts]
**Inputs used:**
- methodology_<>.md
- analysis_<>.md
- lit_review_<>.md
- references.bib
## Summary
[3-5 bullet points on what the draft argues / claims / shows. The parent agent should be able to know what's in the draft from this summary alone.]
## [CITATION NEEDED] index
- Section X, line ~N: [claim that needs a source]
- ...
## Findings preserved verbatim from analysis
[Brief list confirming key numbers and themes traced back correctly.]
## Notes on deviations from the spec
[Anything the parent should know — places where the inputs were ambiguous, where the draft is intentionally cautious, where a section was shortened to fit a word limit.]
## What I did NOT do
[Honest list of things outside scope — e.g., "did not draft the limitations section because no input addressed limitations", "did not format references — defer to citation-formatter skill".]
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 · 71 lines · 65 tokens per session scan A fad919dea90e
manuscript-drafter is an agent published in the GitHub repository Marazii/research-co-pilot (12 stars, last pushed 3mo ago), licensed MIT. It adds 65 tokens to every session and 787 once invoked, about $0.0003 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 agents, from other repositories
clinical-modeler
Use this agent when the user needs to read, write, review, or edit local archetype (.adl), template (.oet, Archetype Designer .t.json, .opt), or composition files in the workspace. It writes only to the local workspace, and can perform read-only MCP lookups (terminology resolution, RM/AM type specs, guides, and…
stc-specialist
Expert in Simulated Treatment Comparison using transparent outcome-regression methods. Handles anchored and unanchored STC for binary, continuous, count, and survival outcomes with explicit assumptions and sensitivity analyses. Use PROACTIVELY for STC analyses.
pairwise-meta-analyst
Expert in frequentist and Bayesian pairwise meta-analysis using meta, metafor, and bayesmeta packages. Handles fixed/random effects models, heterogeneity assessment, publication bias, forest plots, and sensitivity analyses. Use PROACTIVELY for pairwise MA tasks.
research-reviewer
Use this agent when a research phase has been completed and needs to be reviewed for scientific rigor, statistical validity, and publication readiness. Examples: Context: Baseline experiments completed. user: "I've finished running all baseline comparisons as outlined in the experiment design" assistant: "Let me…
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.