All plugins

tripwire

Logs every refused agent action (a tool blocked by a guardrail or plugin, or a dangerous command denied, cancelled or timed out at approval) as one JSON line, so a no-agent cron script can send the owner one short alert. Observer only: it stores no tool arguments, results or message text, and fails open. Disclosure — appends one JSON line per refused action (profile, tool name, block type or approval choice, session id, and the first 120 characters of the block reason or approval rule) to ~/.hermes/tripwire/events.jsonl, shared by all profiles (path overridable with TRIPWIRE_EVENTS); a pre_tool_call hook reads ~/.hermes/tripwire/TEST_BLOCK and, only while that file exists, blocks the single tool it names for the single profile it names (a drill switch to prove the alarm). No network calls, no shell commands, no background processes, no stored credentials, no telemetry.

percyhendrux123-prog1Toolsv0.1.1Updated 7 days ago

About

Logs every refused agent action (a tool blocked by a guardrail or plugin, or a dangerous command denied, cancelled or timed out at approval) as one JSON line, so a no-agent cron script can send the owner one short alert. Observer only: it stores no tool arguments, results or message text, and fails open. Disclosure — appends one JSON line per refused action (profile, tool name, block type or approval choice, session id, and the first 120 characters of the block reason or approval rule) to ~/.hermes/tripwire/events.jsonl, shared by all profiles (path overridable with TRIPWIRE_EVENTS); a pre_tool_call hook reads ~/.hermes/tripwire/TEST_BLOCK and, only while that file exists, blocks the single tool it names for the single profile it names (a drill switch to prove the alarm). No network calls, no shell commands, no background processes, no stored credentials, no telemetry.

This plugin has no README in the catalog yet.

More by percyhendrux123-prog

3 plugins by percyhendrux123-prog in the catalog.

percyhendrux123-proghandydandySession-size notices and structured handoffs. After each turn it checks the estimated input tokens and message count Hermes reports; when a limit is reached it either adds one notice to the reply (advise, the default) or asks the agent, on your next message, to finish your request and write a HANDOFF-*.md file that you open yourself in a new session. No extra model calls, and it never starts a session on its own. Disclosure — writes state.json, state.lock, events.log and short-lived atomic-save temp files under <HERMES_HOME>/plugin-data/handydandy/ (profile and session ids, paths, thresholds and error details; no conversation text); asks the agent to write handoff files to handoff_dir (default <HERMES_HOME>/handoffs/), which may hold work details from the conversation; optionally appends one row per completed handoff to a session_log_csv the owner sets (off by default). Reads its own state, the first byte and modification time of recorded handoff files, plugin settings via ctx.get_config, and HANDYDANDY_<KEY> and HERMES_HOME environment variables. No network calls, no shell commands, no background processes, no stored credentials, no telemetry; it does not auto-approve tools or change safety settings.Communitygeneralpercyhendrux123-proghermes-axiomaInline signal color in the agent's normal reply. The agent marks the few phrases that deserve a second look (stop, caution, go, whisper) and the plugin renders them per surface with color, a style cue and a word, never color alone: Desktop through KaTeX color, CLI/TUI through truecolor ANSI, Telegram/Discord/Slack as bold plus the word, SMS and email as the word only. Green renders only when a tool call Hermes reported as successful in this session backs it; a rarity budget caps marks per reply; malformed tags never leak. A color-vision-safe palette and a style-and-words-only mode are one setting away. Secondary: an advisory card (intent, light, signal, question) staged before configured send/spend/spin/scrub tool calls and shown through Hermes's own approval prompt. Each card and notice carries a short card code (a keyed hash of the exact text shown, the tool, its arguments and the card id), logged when shown and again with the answer; /signals verify <code> reports in plain words whether what was staged, shown and answered line up (spec section 5.6, shown equals staged). Advisor, not a gate: it never blocks, approves or executes anything. Disclosure — before configured send/spend/spin/scrub tool calls (by default send_message, email/post/publish tools, payment/checkout tools, cron and kanban creation, delegate_task, terminal deploy and git push/gh pr commands, and terminal rm/mv when no workspace is configured) it escalates the call to Hermes's own approval prompt with an advisory card, using a fresh rule key each time so remembered Session/Always approvals never skip later prompts; under cron and other unattended runs Hermes's approval policy (default deny) then refuses those calls; it never auto-approves or executes anything, makes no network, model or subprocess calls, reads credentials only as presence checks through agent.secret_scope, adds a short markup guide to the system context through pre_llm_call, rewrites the agent's reply text to render the marks, and writes metadata, salted span hashes and keyed card-code digests (no message bodies) to an owner-only SQLite file plus a separate owner-only key file under its own plugin data directory.Communitytools