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 Rezenders/scientific_writing_agent --skill bootstrap-project-contextgit clone --depth 1 https://github.com/Rezenders/scientific_writing_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/skills/rezenders/scientific_writing_agent/bootstrap-project-context)<a href="https://agentmods.dev/skills/rezenders/scientific_writing_agent/bootstrap-project-context"><img src="https://agentmods.dev/badge/skills/rezenders/scientific_writing_agent/bootstrap-project-context/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/rezenders/scientific_writing_agent/bootstrap-project-context"><img src="https://agentmods.dev/badge/skills/rezenders/scientific_writing_agent/bootstrap-project-context.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 | $0.00041 | $0.01252 |
| Opus 5.5 | $0.00016 | $0.00501 |
| Sonnet 5.5 | $0.00008 | $0.00250 |
| Haiku 4.5 | $0.00004 | $0.00125 |
Grade A, and why
bootstrap-project-context 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 8d 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 — 123 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Bootstrap Project Context
Use this skill after installation and before substantive writing or review workflows.
This skill is an interactive setup workflow. Its purpose is to replace generic placeholders in .agents/context/ with author-approved project facts. Do not invent missing scientific content.
Goals
Populate or update these focused context files:
.agents/context/manuscript-context.md.agents/context/paper-model.md.agents/context/terminology.md.agents/context/contributions.md.agents/context/evaluation-claims.md.agents/context/claim-ledger.md.agents/context/do-not-say.md.agents/context/reviewer-contracts.mdwhen reviews exist
Leave .agents/context/open-findings.md empty or initialized unless there are known unresolved findings.
Workflow
Phase 1 — Inspect Existing Project Evidence
Before asking questions, inspect the repository for available facts:
- Run
python3 scripts/latex_project_map.py --root .to enumerate entry candidates and conservative dependencies. Supply--entryonly when established by build metadata or author confirmation; names likemain.texare not proof. Supply--flsfor a recent recorder from the selected build. Review its freshness/provenance limitations. - Read the entry point and identify
\input/\includesection files. - Inspect macro/config files when obvious, such as
macros.tex,preamble.tex,config/macros.tex, or files included before\begin{document}. - Inspect
Makefile,latexmkrc, CI files, or README build instructions for build and lint commands. - Scan the abstract, introduction, conclusion, and evaluation/results sections when available for contribution and evaluation claims.
- Check for existing
AGENTS.md,CLAUDE.md, reviewer-response files, or project notes.
Record the document class, engine, bibliography backend/files, active document files and dependency relationships, macro definition files, custom citation/reference commands (including argument semantics), build working directory/command, log paths, output PDF, and figures/tables directories in paper-model.md. Inspect local class/style files, graphics paths, build recipes, latexmkrc, CI, and magic comments; resolve conflicts rather than defaulting to a familiar engine. A source scan cannot resolve arbitrary macros, conditionals or TeX search paths. Use LSP definitions/references where supported to investigate important commands; do not classify every unknown command as undefined.
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.
- 8d ago Changed · +2 lines 49e988f03316
- 1mo ago First seen · 121 lines · 41 tokens per session scan A 12b909c5033c
bootstrap-project-context is a skill published in the GitHub repository Rezenders/scientific_writing_agent (14 stars, last pushed 9d ago), licensed Apache-2.0. It adds 41 tokens to every session and 1,252 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 2026-09-21.
bootstrap-project-context compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| bootstrap-project-contextRezenders/scientific_writing_agent | Skill | 14 | 9d ago | Apache-2.0 | A | 41 | Claude Code, Codex |
| instrument-data-to-allotropeanthropics/knowledge-work-plugins | Skill | 36k | 2d ago | Apache-2.0 | A | 123 | Claude Code |
| matlabK-Dense-AI/scientific-agent-skills | Skill | 57k | 6d ago | MIT | A | 44 | Claude Code |
| exploratory-data-analysisK-Dense-AI/scientific-agent-skills | Skill | 57k | 6d ago | MIT | A | 83 | Claude Code |
| phylogeneticsK-Dense-AI/scientific-agent-skills | Skill | 57k | 6d ago | MIT | A | 71 | Claude Code, Codex |
| research-engineerdavila7/claude-code-templates | Skill | 34k | today | MIT | A | 43 | Claude Code, Codex |
| mapping-to-snomedmaziyarpanahi/openmed | Skill | 5.8k | today | Apache-2.0 | A | 205 | Claude Code |