New: 98,000+ skills indexed from GitHub repos with 100+ stars · every skill safety-checkedBrowse top skillsTop skills
Esc to closeBrowse all skills
Submit a skillBrowse skills
Submit a skillBrowse skills

Agent skill

Transcript Search

by deadlock-mod-manager in deadlock-mod-manager/deadlock-mod-manager

Search local Cursor, Claude Code, and Codex session transcripts.

GPL-3.0Auto-check passedDevelopment

Install Transcript Search

skills CLI
$ npx skills add deadlock-mod-manager/deadlock-mod-manager --skill transcript-search -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install deadlock-mod-manager/deadlock-mod-manager transcript-search --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/deadlock-mod-manager/deadlock-mod-manager.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.agents/skills/transcript-search .claude/skills/transcript-search && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
transcript-search
GitHub stars
574
Token cost
~1.5k tokens
SKILL.md length
605 words
Files
1
Skills in repo
25
Repo updated
First seen
Licence
GPL-3.0

At a glance

Search local Cursor, Claude Code, and Codex session transcripts.

  • Works in 2 steps: Call build_index before the first FTS… → Call build_index again with semantic:…
  • Looking up past agent sessions
  • SKILL.md covers Tools, Grep vs search, Index and Session id to transcript, plus 2 more sections
  • Calls bunx and bun

What it does

Transcript Search is an agent skill from deadlock-mod-manager/deadlock-mod-manager. Search local Cursor, Claude Code, and Codex session transcripts. Use when looking up past agent sessions, choosing grep vs ranked search, building the search index, dumping a session by id, or scoping by cwd and provider.

Its SKILL.md is about 1.5k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

It sits in Development. The repository describes itself as: A mod manager for the Valve game Deadlock. The licence is GPL-3.0.

When your agent uses it

  • Looking up past agent sessions
  • Choosing grep vs ranked search
  • Building the search index
  • Dumping a session by id

Example prompts

  • “/transcript-search”

Workflow steps

2 steps, taken from the first numbered list in SKILL.md.

  1. Call build_index before the first FTS search. Incremental is the default; full: true rebuilds from scratch.
  2. Call build_index again with semantic: true before mode: "hybrid". First semantic build downloads ~23 MB ONNX (all-MiniLM-L6-v2).

What it can do on your machine

Read from SKILL.md and the folder at commit 45c273c. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Shell commands in SKILL.md call:

    • bunx
    • bun

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md. Its commands use bunx, which can reach the network depending on how they are called.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Transcript Search loads about 1.5k tokens when it runs. Until then it costs about 60 tokens; SKILL.md has 605 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~60
When it runs · the whole SKILL.md, loaded when a task matches
~1.5k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from deadlock-mod-manager/deadlock-mod-manager at commit 45c273c, republished under its GPL-3.0 licence (© deadlock-mod-manager). 605 words, ~1,535 tokens.

Download SKILL.mdSave it as .claude/skills/transcript-search/SKILL.md (or your agent's skills folder).
name
transcript-search
description
Search local Cursor, Claude Code, and Codex session transcripts. Use when looking up past agent sessions, choosing grep vs ranked search, building the search index, dumping a session by id, or scoping by cwd and provider.

Query sessions already on disk. Nothing is uploaded. Six tools, three intended search tiers.

Tools

<!-- tool-contract:start -->
ToolPurposeInputs
list_providersList transcript harnesses on this machine. Returns availability and a capped session file count.—
list_sessionsList session summaries filtered by provider, cwd, and time range. Newest first. Does not return full transcripts.provider? · cwd? · since? · until? · limit? (1–200, default 50)
get_transcriptReturn the normalized transcript for one session (provider + id, optional path). Messages are capped (default 200, max 1000).provider · id · path? · limit? (1–1000, default 200)
grep_transcriptsSearch raw transcript files without an index. Supports plain, regex, and fuzzy matching with 10 MiB file, 1 MiB line, 64 MiB scan, and 60 second fallback limits.query (max 1024 chars) · mode? (plain/regex/fuzzy, default fuzzy) · provider? · limit? (1–200, default 50)
search_transcriptsBM25-ranked search over normalized messages. mode=fts (default) or mode=hybrid after a semantic index build.query · mode? (fts/hybrid, default fts) · provider? · role? · cwd? · since? · until? · limit? (1–100, default 20)
build_indexBuild or refresh the FTS5 index. Pass full=true to rebuild from scratch. Pass semantic=true to also embed the corpus — first run downloads ~23MB ONNX (all-MiniLM-L6-v2).full? (default false) · semantic? (default false)
<!-- tool-contract:end -->

Provider ids: cursor, claude-code, codex.

Use grep_transcripts when you need a hit now and have no index, or when you want a literal, regex, or fuzzy scan of raw JSONL.

  • query (required)
  • mode: plain | regex | fuzzy (default fuzzy)
  • provider?, limit? (1–200, default 50)

Grep does not take cwd. Scope it with provider, then open the matching session.

Intended grep engine is @ff-labs/fff-bun (fuzzy / plain / regex). If the native binary is unavailable, the server falls back to a streaming scan. Do not assume the native engine is present in every install.

Use search_transcripts when you want BM25-ranked results over normalized message text, or filters grep does not have (cwd, role, since, until).

  • Requires build_index first
  • mode: fts (default) or hybrid
  • hybrid requires a later build_index with semantic: true
Show full SKILL.md (285 more words)Show less

Index

search_transcripts reads the local FTS5 index (~/.transcripts-mcp/index.db, overridable via TRANSCRIPTS_MCP_INDEX).

  1. Call build_index before the first FTS search. Incremental is the default; full: true rebuilds from scratch.
  2. Call build_index again with semantic: true before mode: "hybrid". First semantic build downloads ~23 MB ONNX (all-MiniLM-L6-v2).

If search returns INDEX_REBUILD_REQUIRED after a server upgrade, call build_index with full: true. This replaces only the local cache. Use semantic: true to recreate embeddings, and give concurrently running incompatible server versions separate TRANSCRIPTS_MCP_INDEX paths.

The server works without the semantic tier. Hybrid is optional. Do not assume embeddings are available until a semantic build succeeds; they are not guaranteed in every published binary.

Session id to transcript

Hits from grep_transcripts and search_transcripts include provider, sessionId, and path. list_sessions returns the same id, provider, and path.

Call get_transcript with:

  • provider (required)
  • id (the session id)
  • path? (pass it when you have it)
  • limit? (1–1000, default 200)

list_sessions returns summaries only. Dump the session with get_transcript.

Scope

  • Call list_providers first when you do not know what is installed.
  • Pass provider on list_sessions, grep_transcripts, and search_transcripts to stay on one harness (cursor, claude-code, or codex).
  • Pass cwd on list_sessions and search_transcripts to stay in the current project. Grep has no cwd filter — open the matching session instead.

Search tiers

  1. grep — grep_transcripts. No index. Native fuzzy/plain/regex when available; otherwise a streaming scan.
  2. FTS5 — search_transcripts with mode: "fts". Requires build_index.
  3. semantic (optional) — build_index with semantic: true, then search_transcripts with mode: "hybrid" (BM25 + vectors, reciprocal rank fusion).

The published platform binary has native fff grep and FTS5. Semantic/hybrid needs the Bun in-process path (bunx --bun or bun apps/mcp/src/index.ts). If native fff fails to load, grep falls back to a streaming scan.

© deadlock-mod-manager, GPL-3.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in .agents/skills/transcript-search of deadlock-mod-manager/deadlock-mod-manager.

Open the folder on GitHubat commit 45c273c

Compare with similar skills

Transcript Search next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Transcript Search compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Transcript Search this skilldeadlock-mod-manager/deadlock-mod-manager574—~1.5kAutomated safety check: PassGPL-3.0
Vercel Composition Patternssupabase/supabase111k59 repos~726Automated safety check: PassMIT
Finishing a Development Branchobra/superpowers296k5 repos~1.9kAutomated safety check: PassMIT
Typescript Advanced Typesrolling-scopes/rsschool-app10k25 repos~4.2kAutomated safety check: PassMPL-2.0
PR Babysitteropeninterpreter/openinterpreter69k3 repos~4.2kAutomated safety check: PassApache-2.0
Code Review ChecklistshareAI-lab/learn-claude-code78k5 repos~1.1kAutomated safety check: PassMIT

Similar skills

  • Vercel Composition Patterns

    supabase/supabase

    Official

    React composition patterns that scale. An agent skill from supabase/supabase.

    111k GitHub starsUsed in 59 repos~726 tokens
    DevelopmentAuto-check passed

  • Finishing a Development Branch

    obra/superpowers

    Walks the last step of a branch: confirm tests pass, detect the git environment, ask how to integrate, carry out your choice and clean up the worktree.

    296k GitHub starsUsed in 5 repos~1.9k tokens
    DevelopmentAuto-check passed

  • Typescript Advanced Types

    rolling-scopes/rsschool-app

    Master TypeScript's advanced type system including generics, conditional types, mapped types, template literals, and utility types for building type-safe applications.

    10k GitHub starsUsed in 25 repos~4.2k tokens
    DevelopmentAuto-check passed

  • PR Babysitter

    openinterpreter/openinterpreter

    Watches an open GitHub pull request until it merges, handling review comments, diagnosing CI failures and retrying flaky checks along the way.

    69k GitHub starsUsed in 3 repos~4.2k tokens
    DevelopmentAuto-check passed

  • Code Review Checklist

    shareAI-lab/learn-claude-code

    Reviews code against a five-part checklist covering security, correctness, performance, maintainability and testing, and reports findings in a fixed format.

    78k GitHub starsUsed in 5 repos~1.1k tokens
    DevelopmentAuto-check passed

  • Greploop

    onyx-dot-app/onyx

    Iteratively improves a PR (GitHub), MR (GitLab), or shelved changelist (Perforce) until Greptile gives it a 5/5 confidence score with zero unresolved comments.

    32k GitHub starsUsed in 4 repos~3.3k tokens
    DevelopmentAuto-check passed

More from deadlock-mod-manager/deadlock-mod-manager

All 25 skills in this repo

  • Skill Creator

    deadlock-mod-manager/deadlock-mod-manager

    Create new agent skills following the Agent Skills specification.

    574 GitHub starsUsed in 1 repo~2.9k tokens
    Auto-check passed

  • Create Auth Skill

    deadlock-mod-manager/deadlock-mod-manager

    Scaffold and implement authentication in TypeScript/JavaScript apps using Better Auth.

    574 GitHub starsUsed in 4 repos~3.4k tokens
    Auto-check passed

  • Opensrc

    deadlock-mod-manager/deadlock-mod-manager

    Fetch source code for npm, PyPI, or crates.io packages and GitHub/GitLab repos to provide AI agents with implementation context beyond types and docs.

    574 GitHub stars~910 tokensUpdated today
    Auto-check passed

  • Security Review

    deadlock-mod-manager/deadlock-mod-manager

    Security code review for Tauri/Rust/TypeScript desktop apps and Hono/oRPC APIs.

    574 GitHub stars~1.8k tokensUpdated today
    Auto-check passed

  • Babysit

    deadlock-mod-manager/deadlock-mod-manager

    Stay on one pull request until it is merge-ready, fixing the highest-priority blocker and telling the user when it is green.

    574 GitHub stars~1.8k tokensUpdated today
    Auto-check passed

  • Changeset

    deadlock-mod-manager/deadlock-mod-manager

    Generate a changeset file describing the current PR's changes.

    574 GitHub stars~1.2k tokensUpdated today
    Auto-check passed

Categories

Questions about Transcript Search

What does Transcript Search do?

Search local Cursor, Claude Code, and Codex session transcripts. Transcript Search is an agent skill from deadlock-mod-manager/deadlock-mod-manager. Search local Cursor, Claude Code, and Codex session transcripts.

When should I use Transcript Search?

Transcript Search fits situations like: looking up past agent sessions; choosing grep vs ranked search; building the search index; dumping a session by id.

How do I install Transcript Search in Claude Code?

Run `npx skills add deadlock-mod-manager/deadlock-mod-manager --skill transcript-search -a claude-code`. Or copy the skill folder (.agents/skills/transcript-search in deadlock-mod-manager/deadlock-mod-manager) into .claude/skills/transcript-search in your project. Claude Code loads it when a task matches its description.

How do I install Transcript Search in Codex?

Run `npx skills add deadlock-mod-manager/deadlock-mod-manager --skill transcript-search -a codex`. Or copy the skill folder (.agents/skills/transcript-search in deadlock-mod-manager/deadlock-mod-manager) into .agents/skills/transcript-search in your project. Codex loads it when a task matches its description.

Can I use Transcript Search in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add deadlock-mod-manager/deadlock-mod-manager --skill transcript-search -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/transcript-search, .gemini/skills/transcript-search, .github/skills/transcript-search and .opencode/skills/transcript-search in your project.

What does Transcript Search need to run?

Going by SKILL.md and its folder, Transcript Search needs the command-line tools its instructions call (bunx and bun).

Does Transcript Search access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Transcript Search safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Transcript Search use?

Transcript Search is published under the GPL-3.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Transcript Search use?

About 1.5k tokens (SKILL.md is roughly 6.1k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Transcript Search?

Skills that share tags, products or a category with Transcript Search: Vercel Composition Patterns (supabase/supabase, 111k stars), Finishing a Development Branch (obra/superpowers, 296k stars), Typescript Advanced Types (rolling-scopes/rsschool-app, 10k stars) and PR Babysitter (openinterpreter/openinterpreter, 69k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Transcript Search?

deadlock-mod-manager (a GitHub organization) maintains it in deadlock-mod-manager/deadlock-mod-manager, which has 574 GitHub stars. The repository holds 25 skills in this directory. The repository was last updated on October 8, 2026.

Source: deadlock-mod-manager/deadlock-mod-manager on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.