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 agentmods add skills/dropfan/claude-code-plugins/conversation-exportnpx skills add DropFan/claude-code-plugins --skill conversation-exportgit clone --depth 1 https://github.com/DropFan/claude-code-pluginsWhat 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 | $0.00277 | $0.02261 |
| Opus 5 | $0.00138 | $0.01130 |
| Sonnet 5 | $0.00055 | $0.00452 |
| Haiku 4.5 | $0.00028 | $0.00226 |
Grade A, and why
conversation-export 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 2d 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 — 187 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Conversation Export
Overview
Provide the ability to export Claude Code conversation content to structured documents. Support multiple output formats (Markdown, plain text, HTML) and content scopes (full conversation, summary).
Settings Loading
Before any operation, load user settings from .claude/chat-saver.local.md following references/settings-loading.md.
Supported settings: default_format, default_scope, save_dir, stop_hook, stop_hook_threshold, custom_header, custom_footer. See references/settings-schema.md for full schema.
Users can run /chat-saver:setup to interactively initialize or update the configuration file.
Output Formats
Three output formats are supported. For complete templates with full markup, see references/format-templates.md.
IMPORTANT: Every exported document MUST include the plugin attribution footer. The footer contains the plugin name "chat-saver" and the GitHub repository link. See references/format-templates.md for the exact footer text per format. Do NOT omit the footer under any circumstances unless the user has configured a custom_footer in settings.
Markdown (default)
Use YAML frontmatter for metadata (date, project, working directory) to ensure compatibility with tools like Obsidian, Jekyll, and Hugo. Use heading-based structure with ## User / ## Assistant sections separated by ---. Preserve code blocks with original language tags and inline code formatting.
Plain Text
Use [User] / [Assistant] labels with ======== separators. Strip all Markdown formatting. Indent code blocks with 4 spaces. Clean and portable format.
HTML
Generate self-contained HTML with embedded CSS. Use .user (blue tint) and .assistant (gray tint) styled containers. Wrap code in <pre><code> tags with dark theme. Escape HTML entities in code content.
Content Scope
Full Export
Export the entire conversation history as-is. Include all user messages and assistant responses. Preserve tool call results when they contain meaningful output. Omit internal tool call metadata (tool names, parameters) unless relevant to understanding.
What ships with it
4 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 2d ago First seen · 187 lines · 277 tokens per session scan A 38b64b5d3bfd
conversation-export is a skill published in the GitHub repository DropFan/claude-code-plugins (7 stars, last pushed 27d ago), licensed MIT. It adds 277 tokens to every session and 2,261 once invoked, about $0.0014 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 2026-08-31.
Other skills, from other repositories
auto-loop
TDD-based autonomous development loop with checkpoint recovery and observability changelog.
agent-check
Validate custom agent file format and structure. Use after creating or editing an agent, before committing agent changes, or when an agent fails to load.
hook-template
Generate hook script from template. Use when adding a new hook, wiring a PreToolUse/PostToolUse/Stop/Notification hook, or scaffolding hook config for settings.json.
skill-check
Validate skill/command file format and structure. Use after creating or editing a skill, before committing skill changes, or when a skill fails to load or trigger.
agent-template
Generate custom agent from template. Use when creating a new subagent from scratch, or scaffolding an agent file with correct frontmatter.
session-relay
Continue real repository work between Claude Code, Codex CLI, and Grok Build with a privacy-bounded, drift-aware handoff packet. Use for cross-vendor takeover, context-limit checkpoints, multi-hop Claude→Codex→Grok relays, or receiving an existing Director packet. Use native resume commands for same-CLI history; never…