All plugins

edit-ledger

Local ledger of the turns in which the agent changed files with write_file or patch: /edit-log shows how many turns changed files, how many files in all, the median per turn, the most changed file type and how long ago the last one was, per model, platform or day, a table of file types (extensions), or the newest turns, for the last 24 hours, any number of hours or days, the latest session or everything recorded; /edit-log recent lists the newest turns (ten, or up to 100 with /edit-log recent 50). A turn another plugin keeps going is counted once. Disclosure — subscribes to pre_verify as an observer only: always returns nothing, so it never keeps the agent going or changes a turn; writes turn metadata (model, platform, file count, files per extension, a 12-digit hash of the session id; never a path, file name or answer text) to plugin-data/edit-ledger/edits.jsonl, trimmed to 5,000 rows past 2 MB; never opens the changed files; no network

olric3015Toolsv1.0.0Updated 1 month ago

About

Local ledger of the turns in which the agent changed files with write_file or patch: /edit-log shows how many turns changed files, how many files in all, the median per turn, the most changed file type and how long ago the last one was, per model, platform or day, a table of file types (extensions), or the newest turns, for the last 24 hours, any number of hours or days, the latest session or everything recorded; /edit-log recent lists the newest turns (ten, or up to 100 with /edit-log recent 50). A turn another plugin keeps going is counted once. Disclosure — subscribes to pre_verify as an observer only: always returns nothing, so it never keeps the agent going or changes a turn; writes turn metadata (model, platform, file count, files per extension, a 12-digit hash of the session id; never a path, file name or answer text) to plugin-data/edit-ledger/edits.jsonl, trimmed to 5,000 rows past 2 MB; never opens the changed files; no network

edit-ledger

A local ledger of the turns in which Hermes's agent changed files, and an /edit-log command
that shows which models change files, how many per turn and of which file types.

When a turn in which the agent changed files is about to finish, Hermes fires pre_verify with
the list of files that turn changed. edit-ledger subscribes to it and keeps one row per turn:
the model, the platform, how many files and their types (.py, .md, .tsx, ...). You can see
afterwards that one model touches four files a turn and another one, that most of this week's
changes were Markdown, or how many turns changed code in a session.

The plugin only watches. pre_verify is also how a plugin can keep the agent going (to run a
check first); edit-ledger always returns nothing, which lets the turn finish exactly as it would
without it, and does not change what any other pre_verify plugin decides.

Install

hermes plugins install edit-ledger --enable

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

Use

/edit-log             last 24 hours, by model
/edit-log session     the most recent session
/edit-log all         everything in the ledger
/edit-log 7d          the last 7 days (any number of hours or days: 6h, 30d)
/edit-log types       add to any of the above to list file types (or platforms, days)
/edit-log recent      add to any of the above to list the newest 10 turns instead
/edit-log recent 25   the newest 25 instead (1 to 100)
/edit-log clear       delete the ledger

Example (/edit-log all, from the end-to-end test: two hermes chat turns, the first writing a
.py and a .md file, the second writing two .py files):

Turns that changed files, all recorded:

model       turns  files  median  top type    last
fake-model      2      4       2       .py  3s ago

Counts files changed with write_file and patch, not by terminal commands.
  • turns counts turns that changed at least one file, and files the files they changed.
  • median is the middle number of files per turn.
  • top type is the file type changed most often, and last how long ago the newest turn
    was. The model with the most turns comes first.

/edit-log types lists file types instead. From the same run:

Turns that changed files, all recorded, by file type:

type  files  turns     last
.py       3      2   3s ago
.md       1      1  11s ago

/edit-log recent lists the newest ten turns of the chosen window, newest first
(/edit-log recent 25 lists 25, up to 100), with the three most changed types of each:

Turns that changed files, all recorded, newest 2 of 2:

when          model  platform  files         types
3s ago   fake-model       cli      2         .py 2
11s ago  fake-model       cli      2  .md 1, .py 1

A file type is the file's extension in lower case; (none) is a file without one (Makefile,
.env) and (other) an extension that is not a short plain one.

/edit-log days puts one day on each line, newest day first; days are your computer's local
calendar days. A time window counts back from now (/edit-log 6h, /edit-log 7d types).
session and all take precedence over a time window. 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 sees and what it does not

  • Hermes lists the files changed with its write_file and patch tools. A file changed by a
    terminal command (sed -i, a formatter, git checkout) is not on that list.
  • A turn is counted when it is about to finish with an answer. A turn that is stopped or fails
    before that is not counted.
  • If another plugin keeps the agent going (a pre_verify "continue"), Hermes fires the hook
    again in the same turn with the full list so far; edit-ledger updates that turn instead of
    counting a second one.

What is recorded

One JSON line per hook call in <HERMES_HOME>/plugin-data/edit-ledger/edits.jsonl (per
profile):

ts, session, platform, model, attempt, files, types.

types maps each file type to how many files of it the turn changed. No path, file name or
anything the agent wrote is stored. session is the first 12 hex digits of a SHA-256 of
Hermes's session id, enough to tell sessions apart; attempt is Hermes's count of times the turn
was kept going.

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_verify) and one command (/edit-log).
  • Observer only: the hook always returns nothing, so it never keeps the agent going or changes
    a turn. Each hook call appends one line to the ledger, and nothing else.
  • No network access, no subprocesses, no downloads, no credentials read. It never opens the
    changed files.
  • Writes only edits.jsonl under its own plugin data directory. /edit-log clear deletes it.
  • The hook never raises: if the ledger cannot be written, the failure is logged at debug level.
  • Standard library only.

Development

python -m pytest tests                                            # unit tests, no Hermes needed
PYTHONPATH=<hermes checkout> python tests/e2e/edit_ledger_e2e.py   # real hermes chat turns
hermes plugins validate edit-ledger

Changes

  • 1.0.0: first release.

MIT licensed.

README from the reviewed commit c0a93cb; 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