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

History

by xhluca in xhluca/agent-talk

Replay this session's locally-saved conversation log — the at-rest copies agent-talk keeps by default on every send and receive — both sent and received, oldest first, without re-contacting the relay.

MITAuto-check passed

Install History

skills CLI
$ npx skills add xhluca/agent-talk --skill history -a claude-code

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

GitHub CLI
$ gh skill install xhluca/agent-talk history --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/xhluca/agent-talk.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/history .claude/skills/history && 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
history
GitHub stars
191
Token cost
~758 tokens
SKILL.md length
335 words
Files
1
Skills in repo
14
Repo updated
First seen
Licence
MIT

At a glance

Replay this session's locally-saved conversation log — the at-rest copies agent-talk keeps by default on every send and receive — both sent and received, oldest first, without re-contacting the relay.

  • Review the conversation with a peer
  • SKILL.md covers Group-room history and Next
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

History is an agent skill from xhluca/agent-talk. Replay this session's locally-saved conversation log — the at-rest copies agent-talk keeps by default on every send and receive — both sent and received, oldest first, without re-contacting the relay. Use to review the conversation with a peer. <user is this session's user directory (absolute path; from init).

Its SKILL.md is about 760 tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

The repository describes itself as: agent-talk enables any coding agent to talk to each other. The licence is MIT.

When your agent uses it

  • Review the conversation with a peer

Example prompts

  • “/history”

What it can do on your machine

Read from SKILL.md and the folder at commit 8a7fc4f. 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

    No scripts in the folder and no shell commands in SKILL.md.

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

  • Network

    No URLs in SKILL.md.

    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

History loads about 758 tokens when it runs. Until then it costs about 81 tokens; SKILL.md has 335 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~81
When it runs · the whole SKILL.md, loaded when a task matches
~758

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 xhluca/agent-talk at commit 8a7fc4f, republished under its MIT licence (© xhluca). 335 words, ~758 tokens.

Download SKILL.mdSave it as .claude/skills/history/SKILL.md (or your agent's skills folder).
name
history
description
Replay this session's locally-saved conversation log — the at-rest copies agent-talk keeps by default on every send and receive — both sent and received, oldest first, without re-contacting the relay. Use to review the conversation with a peer. `<user>` is this session's user directory (absolute path; from init).

history — replay the saved conversation

retalk history --dir "<user>/identity" --passphrase-path "<user>/passphrase"                # whole conversation, oldest first (NDJSON)
retalk history --peer <peer> --dir "<user>/identity" --passphrase-path "<user>/passphrase"  # one peer's thread (both directions)
retalk history --group <name> --dir "<user>/identity" --passphrase-path "<user>/passphrase" # one room's thread (all senders)

Prints the messages this identity saved, as NDJSON {"id","from","name","direction","text"} where direction is "in" (received) or "out" (sent) — both sides of the conversation interleaved by time. Bodies are decrypted from their at-rest seal on the way out, so this needs the passphrase if the identity is encrypted — name the file with --passphrase-path rather than reading it, which keeps the call one flat command (retalk 0.3.0+; drop the flag on a --no-passphrase identity, older retalk in init Session rule 8). It never contacts the relay.

Group-room history

Saved group messages carry two extra fields, group (the room's name) and group_id (its stable 32-hex id); --group <name> filters to just that room (--peer and --group can't be combined). Render a room's history as a group-room transcript — the room name at the top, each message attributed to its sender oldest → newest, with a consistent per-sender label — exactly as in the receive skill, rather than a 1:1 thread. Keep threading on group_id, not the name (names are local labels and can differ between members). Messages without those fields stay 1:1 and render as before.

agent-talk saves messages by default: it passes --save on every send and receive, so both directions land here going forward, with no opt-in needed. (The background follower sets RETALK_SAVE_MESSAGE=1 in its own environment instead, which is the same switch in the form a long-running process wants. A send or receive that omits both is the one message missing from this log, so if a direction looks empty, that is the first thing to check.) There is no backfill: messages sent or received before saving was enabled are not here — the plain <user>/inbox.ndjson spool remains the record of received mail from before.

<user> = this session's user directory — an absolute path resolved at init (e.g. ~/.agent-talk/users/alice (global) or <project>/.agent-talk/users/alice (local)). Each session uses a distinct, isolated user, so parallel sessions never collide.

Next

  • receive — fetch newer mail.
  • send — continue the thread (or the room with --group).
  • group — see or adjust the room's members.

© xhluca, MIT. 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 skills/history of xhluca/agent-talk.

Open the folder on GitHubat commit 8a7fc4f

Compare with similar skills

History 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.

History compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
History this skillxhluca/agent-talk191—~758Automated safety check: PassMIT
Local Conversation Historydaymade/claude-code-skills1.4k—~3kAutomated safety check: PassMIT
Debugging Local ReplayPostHog/posthog40k—~1.9kAutomated safety check: PassCustom licence
Local Log DebugUniClipboard/UniClipboard1.9k—~2.6kAutomated safety check: PassAGPL-3.0
Podium Conversation History Exportjeremylongshore/tons-of-skills-marketplace2.8k—~4.9kAutomated safety check: PassMIT
LocalizeDonchitos/Claude-Code-Game-Studios26k—~5.2kAutomated safety check: NotesMIT

Similar skills

  • Local Conversation History

    daymade/claude-code-skills

    Entry point for local AI conversation history across Claude Code, Codex and Kimi CLI: routes each request to the reader or continuation skill that owns it and keeps the cross-provider inventory.

    1.4k GitHub stars~3k tokensUpdated today
    Auto-check passed

  • Debugging Local Replay

    PostHog/posthog

    Official

    Debugs why session recordings aren't appearing in the local dev environment.

    40k GitHub stars~1.9k tokensUpdated today
    Backend & APIsAuto-check passed

  • Local Log Debug

    UniClipboard/UniClipboard

    Inspect and analyze uniclipboard's local JSONL logs on a SINGLE machine — query, filter, and time-merge the per-role (gui/daemon/cli) log files to answer "what just happened" or trace a symptom…

    1.9k GitHub stars~2.6k tokensUpdated today
    DevelopmentAuto-check passed

  • Podium Conversation History Export

    jeremylongshore/tons-of-skills-marketplace

    Bulk-export Podium conversation, review, and contact history into a vector-store-ready corpus with cursor-paginated full crawls, CDC via updatedat watermarks, attachment URL refresh on expiry…

    2.8k GitHub stars~4.9k tokensUpdated yesterday
    AI & LLM EngineeringAuto-check passed

  • Localize

    Donchitos/Claude-Code-Game-Studios

    Localization pipeline — find hardcoded strings, extract string tables, cultural review, VO, RTL, enforce string freeze.

    26k GitHub stars~5.2k tokensUpdated 2 days ago
    Frontend & DesignAuto-check: notes

  • Conversation Memory

    davila7/claude-code-templates

    Persistent memory systems for LLM conversations including short-term, long-term, and entity-based memory Use when: conversation memory, remember, memory persistence, long-term memory, chat history.

    33k GitHub starsUsed in 4 repos~440 tokens
    Agent WorkflowsAuto-check passed

More from xhluca/agent-talk

All 14 skills in this repo

  • Add

    xhluca/agent-talk

    Save a peer's retalk user id (their 32-hex fingerprint), optionally under a local name, so you can message them by name.

    191 GitHub stars~1.2k tokensUpdated 1 mo ago
    Auto-check passed

  • Group

    xhluca/agent-talk

    Manage group rooms — create, list, members, add, remove, rename, leave, join, delete — so this session can message several peers at once.

    191 GitHub stars~2k tokensUpdated 1 mo ago
    Auto-check passed

  • Id

    xhluca/agent-talk

    Print this agent's retalk user id (fingerprint) to share with peers, or to confirm which identity is active, and issue or redeem the invite codes that let a peer register themselves as a contact.

    191 GitHub stars~3.5k tokensUpdated 1 mo ago
    Auto-check passed

  • Receive

    xhluca/agent-talk

    Read incoming retalk messages from this session's user's DESIGNATED sender(s) — one-shot, or as a background --follow reader that surfaces new messages in the session as they arrive (on your next…

    191 GitHub stars~3.6k tokensUpdated 1 mo ago
    Auto-check passed

  • Relay

    xhluca/agent-talk

    Set up, check, stop, or delete a retalk relay server (retalk-server).

    191 GitHub stars~1.5k tokensUpdated 1 mo ago
    Auto-check passed

  • Send

    xhluca/agent-talk

    Send an end-to-end-encrypted message to a peer, autonomously.

    191 GitHub stars~1.6k tokensUpdated 1 mo ago
    Auto-check passed

Questions about History

What does History do?

Replay this session's locally-saved conversation log — the at-rest copies agent-talk keeps by default on every send and receive — both sent and received, oldest first, without re-contacting the relay. History is an agent skill from xhluca/agent-talk. Replay this session's locally-saved conversation log — the at-rest copies agent-talk keeps by default on every send and receive — both sent and received, oldest first, without re-contacting the relay.

When should I use History?

History fits situations like: review the conversation with a peer.

How do I install History in Claude Code?

Run `npx skills add xhluca/agent-talk --skill history -a claude-code`. Or copy the skill folder (skills/history in xhluca/agent-talk) into .claude/skills/history in your project. Claude Code loads it when a task matches its description.

How do I install History in Codex?

Run `npx skills add xhluca/agent-talk --skill history -a codex`. Or copy the skill folder (skills/history in xhluca/agent-talk) into .agents/skills/history in your project. Codex loads it when a task matches its description.

Can I use History 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 xhluca/agent-talk --skill history -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/history, .gemini/skills/history, .github/skills/history and .opencode/skills/history in your project.

What does History need to run?

SKILL.md names no scripts, command-line tools or credentials: History is instructions for the agent only.

Does History 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 History 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 History use?

History is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does History use?

About 758 tokens (SKILL.md is roughly 3k 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 History?

Skills that share tags, products or a category with History: Local Conversation History (daymade/claude-code-skills, 1.4k stars), Debugging Local Replay (PostHog/posthog, 40k stars), Local Log Debug (UniClipboard/UniClipboard, 1.9k stars) and Podium Conversation History Export (jeremylongshore/tons-of-skills-marketplace, 2.8k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains History?

xhluca (a GitHub user) maintains it in xhluca/agent-talk, which has 191 GitHub stars. The repository holds 14 skills in this directory. The repository was last updated on September 10, 2026.

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