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 instructions/idisposable/claude-transcript-plugin/claude-mdgit clone --depth 1 https://github.com/IDisposable/claude-transcript-pluginWhat 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 | $0.00905 | $0.00905 |
| Opus 5 | $0.00452 | $0.00452 |
| Sonnet 5 | $0.00181 | $0.00181 |
| Haiku 4.5 | $0.00090 | $0.00090 |
Grade A, and why
claude-transcript-plugin CLAUDE.md 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 yesterday.
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 — 62 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Claude Code Transcript Plugin
Project Overview
A Claude Code plugin that saves readable Markdown transcripts of sessions before context compaction. It hooks into the PreCompact event, reads the session's JSONL transcript, and writes a formatted Markdown file.
Architecture
.claude-plugin/plugin.json— Plugin manifest (name, version, metadata).claude-plugin/marketplace.json— Marketplace catalog for distributionhooks/hooks.json— Registers aPreCompacthook that runs the converter via platform shimscripts/run— Unix shim that detects OS/arch and executes the correct binaryscripts/run.cmd— Windows shim for native Windows environmentscmd/save-transcript/main.go— Go entry point (reads hook stdin, writes Markdown)internal/transcript/— Core conversion logic (JSONL parsing, message classification, template rendering)internal/transcript/templates/*.tmpl— Embedded base templates (structural blocks: header, user, assistant, etc.)internal/transcript/templates/tools/*.tmpl— Embedded tool templates (one file per tool, modular/overridable)bin/— Platform-specific compiled binaries (gitignored, built by CI)skills/save-transcript/SKILL.md— Manual/transcript-saver:save-transcriptskill for on-demand use
Key Conventions
- Only
plugin.jsonandmarketplace.jsongo inside.claude-plugin/— all other files live at the repo root - The hook command uses
${CLAUDE_PLUGIN_ROOT}so paths resolve correctly when installed from the plugin cache - The shim scripts detect OS/arch at runtime to support WSL and cross-platform use
- The converter always exits 0 on error so it never blocks compaction
- Go 1.26.1+ with no external dependencies (stdlib only)
- Output goes to
~/.claude/transcripts/by default, overridable via config/env/flag - All settings follow: CLI flag > env var > project config > user config > defaults
- Config files:
<project>/.claude/transcript-saver.jsonand~/.claude/transcript-saver.json
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.
- yesterday First seen · 62 lines · 905 tokens per session scan A f735b4f19d19
claude-transcript-plugin CLAUDE.md is an instructions file published in the GitHub repository IDisposable/claude-transcript-plugin (2 stars, last pushed 3mo ago), licensed MIT. It adds 905 tokens to every session, about $0.0045 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 instructions, from other repositories
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
next.js AGENTS.md
Instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.