A reset command for a research wiki’s development files, with separate scopes for wiki content, raw research files, logs, checkpoints, or everything. It preserves selected scaffold files while clearing the chosen state.

Use it to clear wiki pages, collected papers and notes, logs, or saved batch checkpoints by selecting a reset scope.

It provides a controlled way to recover from a failed setup or restart development without manually deciding which generated files to remove.

How skyllwt/AutoSci configures Claude Code

About the project

AutoSci is an AI research platform organized around a wiki, with an agent that supports stages of scientific work such as reading, experimentation, writing, and retaining knowledge across projects. It is for people building or using AI-assisted research workflows, with Claude Code, Codex, and OpenCode adaptations available. The catalogue add-ons extend those agent-specific workflows.

skyllwt/AutoSci · 1,706 stars · on GitHub

Reuse

Borrowing it

Nothing to install: this file belongs to skyllwt/AutoSci. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/skyllwt/AutoSci/main/.claude/skills/reset/SKILL.md

Clone the repo

git clone --depth 1 https://github.com/skyllwt/AutoSci

Made for: Claude Code.

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/skyllwt/autosci/reset/github.svg)](https://agentmods.dev/skills/skyllwt/autosci/reset)

Your own site

<a href="https://agentmods.dev/skills/skyllwt/autosci/reset"><img src="https://agentmods.dev/badge/skills/skyllwt/autosci/reset/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/skyllwt/autosci/reset"><img src="https://agentmods.dev/badge/skills/skyllwt/autosci/reset.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 33 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,089 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. Third-party audits

NVIDIA SkillSpector pass 7 Sept 2026

How audits are shown

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	$0.00033	$0.01089
Opus 5.5	$0.00013	$0.00436
Sonnet 5.5	$0.00007	$0.00218
Haiku 4.5	$0.00003	$0.00109

Measured 2mo ago against content hash 9a73a93f3145, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

reset 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 2mo 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.

.claude/skills/reset/SKILL.md · 113 lines

How it starts

The opening of the file, as written. The whole thing — 113 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/reset

Resets the wiki to a clean scaffold by scope. Designed for development iteration and recovery after a failed setup — not a routine operation.

Trigger

Manual: /reset --scope wiki / --scope raw / --scope log / --scope checkpoints / --scope all. Multiple scopes may be combined comma-separated: --scope wiki,log.

Inputs

--scope (required): one of
- wiki — delete every *.md under wiki/<entity>/ and wiki/outputs/, plus wiki/index.md, wiki/log.md, and wiki/graph/ files. Preserves .gitkeep and wiki/CLAUDE.md.
- raw — delete every entry under raw/papers/, raw/discovered/, raw/tmp/, raw/notes/, raw/web/ (except .gitkeep).
- log — reset wiki/log.md to the empty header.
- checkpoints — clear batch state via research_wiki.py checkpoint-clear.
- all — every scope above.

Outputs

Cleared / reset files on disk.
Console summary of deleted files and reset files.

Wiki Interaction

Reads

All wiki/<entity>/*.md (to enumerate the deletion plan).
raw/<sub>/* (to enumerate raw deletions).

Writes

Deletes wiki/<entity>/*.md (preserves .gitkeep).
Rewrites wiki/index.md, wiki/graph/*, optionally wiki/log.md.
Deletes raw/<sub>/* (except .gitkeep).

Workflow

Pre-conditions: working directory contains wiki/, tools/. Set WIKI_ROOT=wiki/.

Step 1: Build the deletion plan (dry-run)

python3 tools/reset_wiki.py --scope <scope>

This prints a JSON plan listing every file that would be deleted or reset, without modifying anything. Display the plan to the user grouped by scope (wiki entity dirs, raw subdirs, log, checkpoints).

Step 2: Confirm with the user

Print the plan summary and ask for explicit confirmation:

About to delete N files and reset M files. Continue? [y/N]

If the user says no, exit. Never proceed without explicit approval — /reset is destructive and raw/ deletions are not tracked by git.

Step 3: Execute

Read the full file on GitHub · 113 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.

2mo ago First seen · 113 lines · 33 tokens per session scan A 9a73a93f3145

Subscribe to this mod's changes

reset is a skill published in the GitHub repository skyllwt/AutoSci (1,706 stars, last pushed 1mo ago), licensed MIT. It adds 33 tokens to every session and 1,089 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.

reset next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
resetskyllwt/AutoSci	Skill	1.7k	1mo ago	MIT	A	33	Claude Code
imagegenopenai/codex	Skill	134k	today	Apache-2.0	A	113	Codex
local-ai-agentsmicrosoft/ai-agents-for-beginners	Skill	79k	today	MIT	A	200	Claude Code, Codex
playwright-climicrosoft/playwright	Skill	99k	today	Apache-2.0	A	19	Claude Code
browser-automationopenclaw/openclaw	Skill	394k	today	MIT	A	36	Claude Code
systematic-debuggingobra/superpowers	Skill	314k	4d ago	MIT	A	21	Claude Code
next-cache-components-adoptionvercel/next.js	Skill	143k	today	MIT	A	95	Claude Code

AutoSci: Skill for Claude Code