All plugins

command-ledger

Local ledger of the slash commands you run in Hermes (built-in commands in the CLI, built-in and plugin commands on messaging platforms): /command-log shows how often each command was used, its share, in how many sessions and when last, per command, platform, surface or day, for the last 24 hours, any number of hours or days, the latest session or everything recorded; /command-log recent lists the newest commands (ten, or up to 100 with /command-log recent 50) with the alias typed. Disclosure — writes command metadata (command name, alias typed, surface, platform, a 12-digit hash of the session key; no arguments, session key or user id) to plugin-data/command-ledger/commands.jsonl, trimmed to 5,000 rows past 2 MB; observer only, cannot block or change a command; no network

olric3015Toolsv1.2.0Updated 1 month ago

About

Local ledger of the slash commands you run in Hermes (built-in commands in the CLI, built-in and plugin commands on messaging platforms): /command-log shows how often each command was used, its share, in how many sessions and when last, per command, platform, surface or day, for the last 24 hours, any number of hours or days, the latest session or everything recorded; /command-log recent lists the newest commands (ten, or up to 100 with /command-log recent 50) with the alias typed. Disclosure — writes command metadata (command name, alias typed, surface, platform, a 12-digit hash of the session key; no arguments, session key or user id) to plugin-data/command-ledger/commands.jsonl, trimmed to 5,000 rows past 2 MB; observer only, cannot block or change a command; no network

command-ledger

A local ledger of the slash commands you run in Hermes, and a /command-log command that shows
which ones you use most, in how many sessions, and when you last used each.

Hermes has dozens of slash commands (/model, /new, /compress, /usage, /queue, ...), on
the CLI and on every messaging platform, and nothing remembers which of them you actually use.
command-ledger subscribes to pre_command and keeps one row per command, so you can see that you
switch models ten times a day, that /compress never gets used, or which commands you run from
Telegram rather than the terminal.

Install

hermes plugins install command-ledger --enable

Requires Hermes 0.21.5 or newer. No API key, no configuration, no dependencies.

Use

/command-log             last 24 hours, by command
/command-log session     the most recent session that ran one
/command-log all         everything in the ledger
/command-log 7d          the last 7 days (any number of hours or days: 6h, 30d)
/command-log platforms   add to any of the above to group by platform (cli, telegram, ...)
/command-log days        add to any of the above to group by day, newest first
/command-log recent      add to any of the above to list the newest 10 commands instead
/command-log recent 25   the newest 25 instead (1 to 100)
/command-log clear       delete the ledger

(/commands is Hermes's own list of the available commands; this plugin counts the ones you
run.)

Example (/command-log, from the end-to-end test on Hermes main: /help, /exit and /help
again in the CLI, then /q later and /usage from Telegram):

Slash commands, last 24 hours:

command  uses  share  sessions  last used
/help       2    40%         1     3s ago
/queue      1    20%         1     0s ago
/quit       1    20%         1     3s ago
/usage      1    20%         1     0s ago
total       5   100%         2     0s ago

The CLI counts Hermes's built-in commands; messaging platforms add plugin commands.
  • command is the command's own name: an alias counts as the command it stands for (/exit
    as /quit, /q as /queue).
  • share is the command's part of all the commands in the window.
  • sessions is how many different sessions ran it. Grouped by platforms, the first column
    is where it ran instead: cli, telegram, discord, ...; grouped by surfaces, cli or
    gateway.

/command-log recent lists the newest 10 commands of the chosen window (/command-log recent 25
lists 25, up to 100), newest first, with the
alias you typed (same run):

Slash commands, all recorded, newest 5 of 5:

when    command  typed as  platform
0s ago   /usage            telegram
0s ago   /queue        /q  telegram
3s ago    /help                 cli
3s ago    /quit     /exit       cli
3s ago    /help                 cli

/command-log days puts one day on each line, newest day first, so you can see which days you
drove Hermes by hand and in how many sessions. Days are your computer's local calendar days, and
a day with no commands has no line. Example (the plugin's own output for a sample week):

Slash commands, last 7 days:

day         uses  share  sessions  last used
2026-10-08     2    12%         2     3h ago
2026-10-07    11    69%         4     1d ago
2026-10-06     3    19%         2     2d ago
total         16   100%         8     3h ago

The CLI counts Hermes's built-in commands; messaging platforms add plugin commands.

A time window counts back from now (/command-log 6h, /command-log 7d platforms,
/command-log 30d days, /command-log 30d recent). The ledger keeps its newest 5,000 rows, so a long window on a busy
install reaches back only as far as those rows do.

What it does not see

Hermes reports a command to plugins just before its handler runs, and only there:

  • In the CLI, Hermes's built-in commands. Plugin commands and skill commands are not reported.
  • On messaging platforms, built-in and plugin commands. Skill commands are not reported, and
    neither is a command sent while a turn is running (such as /stop or /approve): Hermes keeps
    those away from plugins on purpose.
  • An unknown command, or a command a platform's access rules refuse, is not counted.
  • /command-log itself is not counted: reading the ledger is not using Hermes.

What is recorded

One JSON line per command in <HERMES_HOME>/plugin-data/command-ledger/commands.jsonl (per
profile):

ts, session, surface, platform, command, alias.

session is the first 12 hex digits of a SHA-256 of the session key: enough to tell sessions
apart, without the key itself (on messaging platforms it holds the chat id and the user id).
alias is the word you typed when it was an alias, otherwise empty.

Not recorded: the command's arguments (they can hold model names, file paths, prompts or
secrets), the session key, user ids. The hook hands the plugin the arguments and the session key;
the plugin drops the arguments and keeps only the hash of the key.

The file is bounded: once it passes 2 MB it is rewritten to its newest 5,000 rows.

Security and footprint

  • register() only registers one hook (pre_command) and one command (/command-log).
  • Observer only: it cannot block, change or delay a command. Each hook call appends one line to
    the ledger, and nothing else.
  • No network access, no subprocesses, no downloads, no credentials read.
  • Writes only commands.jsonl under its own plugin data directory. /command-log clear deletes
    it.
  • The hook never raises: if the ledger cannot be written, the failure is logged at debug level
    and the command runs as usual.
  • Standard library only.

Development

python -m pytest tests                                                # unit tests, no Hermes needed
PYTHONPATH=<hermes checkout> python tests/e2e/command_ledger_e2e.py    # Hermes's own command dispatch
hermes plugins validate command-ledger

Changes

  • 1.2.0: /command-log recent takes a row count, /command-log recent 25 (1 to 100;
    ten without one). What is recorded did not change.
  • 1.1.0: /command-log days, one line per day with commands, newest day first; works with
    every window (/command-log 30d days). What is recorded did not change.
  • 1.0.0: first release.

MIT licensed.

README from the reviewed commit bf93fe7; it updates when the author re-pins.

More by olric3015

18 plugins by olric3015 in the catalog.

olric3015approval-ledgerLocal ledger of Hermes's approval prompts (dangerous commands, protected writes, MCP consent, smart-mode verdicts): /approval-log shows how often each rule asked, how many prompts were approved, denied or left unanswered, and how long a person took to answer, per rule, per surface or per day, for the last 24 hours, any number of hours or days, the latest session or everything recorded; /approval-log recent lists the newest decisions (ten, or up to 100 with /approval-log recent 50). Disclosure — writes decision metadata (session id, surface, rule label, answer, timings; no command, description or session key) to plugin-data/approval-ledger/approvals.jsonl, trimmed to 5,000 rows past 2 MB; observer only, cannot answer or change an approval; no networkCommunitytoolsolric3015aux-ledgerLocal ledger of Hermes's auxiliary LLM calls (titling, compression, vision, approval): /aux shows tokens, time and failures per task, model, provider or day, or lists the newest calls (ten, or up to 100 with /aux recent 50), for the last 24 hours, any number of hours or days, the latest session or everything recorded. Disclosure — writes auxiliary-call metadata (ids, models, timings, token counts, no prompt or response text) to plugin-data/aux-ledger/calls.jsonl, trimmed to 5,000 rows past 2 MB; no networkCommunitytoolsolric3015b64-ref@b64: context references that decode encoded text for the model: @b64:<value> takes base64 (standard or URL-safe, padded or not), hex (0x48656c6c6f, 48:65:6c, \x48\x65), percent-encoding or a data: URI, told apart by the value's shape or picked with base64:, base64url:, hex: or url:, and attaches what it holds: text as text with control and invisible characters escaped, JSON pretty-printed, gzip and zlib inflated in memory (at most 1 MiB, one layer), and binary named by its format (PNG and GIF with their size, JPEG, PDF, ZIP, ELF, SQLite and more) with a hex dump of its first 128 bytes; notes point out a value that was cut short, padding that is off, a second layer of encoding and a JWT inside; the TUI and Desktop composer preview a value as you type it. Disclosure — reads only the text of the reference itself, using Python's base64, json, urllib.parse and zlib; nothing decoded is run, opened or saved; no network, no files read or written, no subprocess, no credentials read; the plugin keeps no copy of what it decodes, but the @b64: reference and the decoded contents become part of the message sent to your model provider and saved in the session history, so decode only values you are willing to share with it; register() only adds the @b64: reference provider.Communitytoolsolric3015chmod-ref@chmod: context references that explain a file permission mode for the model: @chmod:<mode> takes an octal mode (755, 0755, 4755), ls -l text (-rwsr-xr-x, with the file type letter and a trailing + . or @) or an st_mode as stat and git write it (100644), and attaches both forms, each class's rights in words (directory rights named as such), what setuid, setgid and the sticky bit do and where they are ignored, and notes such as a mode everyone can change, one private to the owner, or a class holding rights the class before it lacks; @chmod:"644 u+x,go-w" applies a symbolic change step by step the way GNU chmod does (u g o a, + - =, r w x X s t, copies like u=g), @chmod:"100644 100755" shows what changes between two modes, and @chmod:"umask 027" shows what new files and directories get; the TUI and Desktop composer preview a mode as you type it. Disclosure — reads only the text of the reference itself, using Python's re; it never looks at a file on disk; no network, no files read or written, no permission changed, no subprocess, no credentials read; the plugin keeps no copy of what you write, but the @chmod: reference and the explanation become part of the message sent to your model provider and saved in the session history; register() only adds the @chmod: reference provider.Communitytools

Developer Mode

Explore built-in Hermes toolsets and actions.

HermesAgent

Developer?

Create a Hermes extension for Desktop or agent workflows.

Developer Section