What is bootstrap-memory?

A setup tool that reads a paper project's instructions and manuscript, then fills agent memory files with project-specific knowledge. These files can store terminology, formatting rules, and details needed when editing the paper.

Use it once after setting up a new paper project, after a major rewrite, or when agents have lost track of the paper's terminology and contributions.

It gives agents the project's context at the start instead of making them rediscover the manuscript's rules over multiple sessions.

bootstrap-memory — Skill for Claude Code and Codex by Rezenders

Install

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.

Any agent

npx skills add Rezenders/scientific_writing_agent --skill bootstrap-memory

Clone the repo

git clone --depth 1 https://github.com/Rezenders/scientific_writing_agent

Made for: Claude Code, Codex.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/rezenders/scientific_writing_agent/bootstrap-memory/github.svg)](https://agentmods.dev/skills/rezenders/scientific_writing_agent/bootstrap-memory)

Your own site

<a href="https://agentmods.dev/skills/rezenders/scientific_writing_agent/bootstrap-memory"><img src="https://agentmods.dev/badge/skills/rezenders/scientific_writing_agent/bootstrap-memory/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/rezenders/scientific_writing_agent/bootstrap-memory"><img src="https://agentmods.dev/badge/skills/rezenders/scientific_writing_agent/bootstrap-memory.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 35 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 547 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

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	$0.00035	$0.00547
Opus 5.5	$0.00014	$0.00219
Sonnet 5.5	$0.00007	$0.00109
Haiku 4.5	$0.00003	$0.00055

Measured 1mo ago against content hash 0d6f0dc0179a, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

bootstrap-memory 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.

.agents/skills/bootstrap-memory/SKILL.md · 52 lines

How it starts

The opening of the file, as written. The whole thing — 52 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Bootstrap Memory

Scans project policy files, .agents/context/, and the manuscript to pre-populate optional agent memory files with project-specific knowledge.

This is not the initial questionnaire or context-filling workflow. Use bootstrap-project-context first when .agents/context/ still contains generic placeholders.

Project Layout

Manuscript entry point: <MAIN_TEX>
Section files: see .agents/context/paper-model.md or derive from <MAIN_TEX>.
Implementation checker: configure project-specific paths in .agents/context/paper-model.md when implementation verification is relevant.

Workflow

Phase 1 — Extract from AGENTS.md and focused context files

Read AGENTS.md, .agents/context/manuscript-context.md, .agents/context/paper-model.md, .agents/context/terminology.md, .agents/context/contributions.md, and .agents/context/evaluation-claims.md. Extract macros, terminology rules, style rules, section structure, implementation reference paths, contribution claims, evaluation-scope boundaries, and build commands.

Phase 2 — Extract from Manuscript

Read <SECTION_FILE> for contribution claims and key term definitions. Scan all sections under sections/ for acronym definitions and notation.

Phase 3 — Write Memory Files

Write extracted knowledge to memory files for each agent. Update rather than overwrite if a more specific file already exists.

Writer: terminology, macros, style rules, section map, contributions
Consistency auditor: canonical macro list with drift variants, defined acronyms, contribution claims, multi-meaning terms
Scientific reviewer: core claims, known overclaiming risks, evaluation setup, baselines, datasets, and metrics
Implementation checker: reference paths and key non-obvious technical facts that are easy to misstate

All memory files must use the frontmatter format with name, description, type: project.

Phase 4 — Update MEMORY.md Indices

For each agent that received new or updated files, update MEMORY.md with pointer lines.

Read the full file on GitHub · 52 lines

Changes

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 Changed · -84 lines · -26 tokens per session 0d6f0dc0179a
2mo ago First seen · 136 lines · 61 tokens per session scan A f3ff87c6727e

Subscribe to this mod's changes

bootstrap-memory is a skill published in the GitHub repository Rezenders/scientific_writing_agent (14 stars, last pushed 17d ago), licensed Apache-2.0. It adds 35 tokens to every session and 547 once invoked, about $0.0001 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.

Memory and context

bootstrap-memory next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
bootstrap-memoryRezenders/scientific_writing_agent	Skill	14	17d ago	Apache-2.0	A	35	Claude Code, Codex
knowledge-ingestopenclaw/openclaw	Skill	394k	yesterday	MIT	A	80	Claude Code, Codex
mem0-oss-to-platformmem0ai/mem0	Skill	68k	2d ago	Apache-2.0	A	217	Claude Code, Codex
forgetasgeirtj/system_prompts_leaks	Skill	71k	2d ago	CC0-1.0	A	74	Claude Code, Codex
Cortexdanielmiessler/LifeOS	Skill	20k	yesterday	MIT	A	184	Claude Code
memoryopensquilla/opensquilla	Skill	7.1k	6d ago	Apache-2.0	A	44	Claude Code, Codex
ha-data-storesshiwenwen/hope-agent	Skill	1.9k	yesterday	MIT	A	115	Claude Code, Codex