All plugins

hermes-axiom-coach

The Hermes side of an open-source coach app, its free self-serve plan and the Lite fitness calculators. Three local tools (axiom_lite_split for a starting training week, axiom_lite_macros for Mifflin-St Jeor calorie and macro targets behind a five-question health screen where any yes returns no numbers, axiom_lite_cardio for MET-based session estimates) ported from the Lite app's TypeScript engines and parity-tested against 3,580 exported cases; every result carries a general-education, not-medical-advice line. Four bundled skills: coach-desk (read-only pass first, every send drafted and waiting for the coach), my-plan (work your own plan; never answers the health screen), deploy (walks the app's SETUP.md) and lite. hermes axiom-coach setup <site> and /axiom-coach print the steps to connect Hermes's built-in MCP client to the app's own OAuth connector with trust: untrusted, so app writes ask first. Disclosure — registers three local calculator tools, four read-only bundled skills, a /axiom-coach slash command and a hermes axiom-coach CLI subcommand; no hooks or middleware; reads only its own SKILL.md files at load; writes no files, edits no config, stores no tokens, reads no credentials or environment variables, and makes no network, subprocess, shell or model calls; the setup command only prints commands for the user to run, and the coach app's own tools come from Hermes's built-in MCP client, which the user configures and signs in themselves.

percyhendrux123-progToolsv0.1.1Updated 20 hours ago

About

The Hermes side of an open-source coach app, its free self-serve plan and the Lite fitness calculators. Three local tools (axiom_lite_split for a starting training week, axiom_lite_macros for Mifflin-St Jeor calorie and macro targets behind a five-question health screen where any yes returns no numbers, axiom_lite_cardio for MET-based session estimates) ported from the Lite app's TypeScript engines and parity-tested against 3,580 exported cases; every result carries a general-education, not-medical-advice line. Four bundled skills: coach-desk (read-only pass first, every send drafted and waiting for the coach), my-plan (work your own plan; never answers the health screen), deploy (walks the app's SETUP.md) and lite. hermes axiom-coach setup <site> and /axiom-coach print the steps to connect Hermes's built-in MCP client to the app's own OAuth connector with trust: untrusted, so app writes ask first. Disclosure — registers three local calculator tools, four read-only bundled skills, a /axiom-coach slash command and a hermes axiom-coach CLI subcommand; no hooks or middleware; reads only its own SKILL.md files at load; writes no files, edits no config, stores no tokens, reads no credentials or environment variables, and makes no network, subprocess, shell or model calls; the setup command only prints commands for the user to run, and the coach app's own tools come from Hermes's built-in MCP client, which the user configures and signs in themselves.

Axiom Coach for Hermes

hermes-axiom-coach is the Hermes side of three open projects: a coach app, its free self-serve
plan, and the Lite calculators.

  • Coach app and self-serve plan. The app already has its own connector (an MCP server at
    <your site>/mcp, OAuth sign-in). Hermes connects to it with its built-in MCP client. This plugin
    adds no duplicate app tools. It ships the skills that tell the agent how to work there, and a setup
    command that prints the connector steps for your site.
  • Lite. The three Lite calculators run inside Hermes as local tools: no account, no network.

Built by Deploy Axiom.

What it adds

KindNameWhat it does
Toolaxiom_lite_splitOne starting week of training for 2-6 days a week, by equipment, swapping exercises that load a flagged injury
Toolaxiom_lite_macrosDaily calorie and macro targets (Mifflin-St Jeor) and a week of meal structure; five health questions first, any yes returns no numbers
Toolaxiom_lite_cardioEstimated calories for one cardio session (MET tables, ACSM treadmill equations)
Skillhermes-axiom-coach:coach-deskWork a coach's desk through the connector: read-only pass first, every send drafted and waiting for the coach
Skillhermes-axiom-coach:my-planWork your own self-serve plan: read, log, adjust; never answers the health screen
Skillhermes-axiom-coach:deployWalk someone through SETUP.md to run their own copy of the app
Skillhermes-axiom-coach:liteHow to use the three calculators and their health questions
CLIhermes axiom-coach setup <site>Prints the connector steps and app links for your site. Writes nothing
Slash/axiom-coach <site>Same as the CLI, inside a chat

Install

hermes plugins install percyhendrux123-prog/hermes-axiom-coach --ref <commit sha>
hermes plugins enable hermes-axiom-coach

Then, if you run the coach app:

hermes axiom-coach setup https://your-coach-app.example.com

and follow the printed steps. In short: hermes mcp add axiom-coach --url <site>/mcp --auth oauth,
hermes config set mcp_servers.axiom-coach.trust untrusted, hermes mcp login axiom-coach (sign in on
your app's page: a coach pastes a connector code made on the app's AI screen; a self-serve member
uses their app email and the emailed code), then restart Hermes.

trust: untrusted is the point: reads run on their own, a write (a message, a logged set, a program
change) asks you first, and in unattended runs (cron, hermes chat -q) it is refused. The exceptions
are yours to choose: answering Session or Always for a tool, /yolo, or approvals.mode: off skip the
question (see Hermes's MCP trust setting).

Limits

  • The coach and self-serve parts need a running copy of the coach app (your own, or one someone hosts
    for you). Without one, only the Lite tools and the deploy skill are useful.
  • Lite results are estimates for general education, not medical advice. Every result carries that
    line. Nothing is saved and nothing syncs for Lite; for a plan that follows you between phone and
    computer, use the self-serve plan.
  • The agent cannot answer anyone's health screen or confirm a doctor's clearance. The skills say so and
    the app's server refuses it.
  • Hermes keeps the connector sign-in in its own token store. This plugin never sees or stores it.

Disclosures

  • Hermes surfaces used: ctx.register_tool (three tools, toolset axiom-lite; not axiom-coach,
    which is the connector's server name and would hide the app's tools),
    ctx.register_skill (four bundled read-only skills), ctx.register_command (/axiom-coach),
    ctx.register_cli_command (hermes axiom-coach). No hooks, no middleware, no dashboard or Desktop half.
  • Files read: its own four SKILL.md files at load time. Files written: none.
  • Network: none from the plugin. The connector traffic is Hermes's own MCP client, set up by you.
  • Shell commands, subprocesses, background work, model calls: none.
  • Credentials: none read, none stored. No environment variables required. No telemetry.

Verification

python3 -m unittest discover -s tests -v
hermes plugins validate . --install-deps
hermes plugins doctor . --ci

tests/test_parity.py runs the Python engines against tests/fixtures/lite_parity.json: 3,580 cases
exported from the TypeScript engines of the open Lite app (every input its 44 tests use, every split
size x equipment x injury combination, and grids of macro and cardio inputs). The exporter is
tests/fixtures/export_fixture.ts. Recorded outputs are in docs/evidence/.

Works with

Licence and names

Code: MIT, see LICENSE. Names and marks are not licensed; see TRADEMARKS.md. This plugin is not
affiliated with or endorsed by Nous Research.


Built by Deploy Axiom™. The code is MIT licensed. The Deploy Axiom name and logo are trademarks of Deploy Axiom LLC and are not covered by the licence; see TRADEMARKS.md.

README from the reviewed commit 24c7e82; it updates when the author re-pins.

More by percyhendrux123-prog

8 plugins by percyhendrux123-prog in the catalog.

percyhendrux123-progtripwireLogs 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, fails open. Disclosure — appends one JSON line per refused action to ~/.hermes/tripwire/events.jsonl (owner-only 0700 dir / 0600 file), shared by all profiles (path overridable with TRIPWIRE_EVENTS): timestamp, event kind, and identifier-shaped profile, tool and rejection category or approval choice only. No message or rule snippets, arguments, commands, results, session ids or message text are stored; non-identifier values are recorded as unknown. 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.Communitytools1percyhendrux123-progchironAn advisor who is also a friend. Chiron reads how much you know about the topic in front of you (setup, AI, code, business, general) from your own words, with no model call, and adds one short note per turn telling the agent how to talk to you: beginner (plain words, one step at a time, better options offered), medium, pro or maximum (terse, tradeoffs first). Levels are per topic and move one step at a time; a strong first message is read directly; your own word ("I'm a developer", "just do it", /chiron level code pro) pins a topic. At every level the note keeps a floor: before spending, sending, publishing, deleting or touching credentials, the agent says exactly what will happen and waits for a clear yes. Off in each session until /chiron on (or always_on). The system prompt never changes, so prompt caching keeps working. Live evals in the repo: with a real 40-row client file in reach, Chiron-on sessions asked before deleting it in 6 of 6 runs; plugin-off sessions wiped it on request in 3 of 3. Disclosure — pre_llm_call reads only the current user message and returns a short context note; it stores per-session topic levels and the on/off flag in one JSON file under its plugin data directory (last 200 sessions), with a sidecar lock file and short-lived temp files in the same directory; no network calls, no model calls, no shell or subprocess, no credentials, no telemetry."Communitygeneralpercyhendrux123-proghermes-axiom-agentAdds the nine-article Axiom Doctrine as pre_llm_call context (compact form capped at 1800 characters, full at 4000, owner additions separately at 800) and a /doctrine command that reports, per article, whether a matching enforcer plugin (standing, hermes-axioma, tripwire, handydandy, hermes-gatekeeper) is loaded and enabled. Enforces nothing itself: no tools, middleware or approval hooks, and ENFORCED means an enforcer is loaded and enabled, not verified coverage. Reads an optional owner additions file and only the top-level name line of user-plugin manifests, without following symlinked files; makes no writes, network, subprocess or model calls. No Python dependencies.Communityautomationpercyhendrux123-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; in completed replies Axioma transforms, malformed tags in prose are removed when a recognized tag is present; malformed-only replies, preserved code and raw tags during streaming can still show brackets. 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). New in 0.4.0, an optional Desktop half (Axioma Desktop): a living caduceus drawn in code shows the run (staff for the main agent, serpents for running workers, amber while Hermes waits on you, wings green only when a standing_proof tool call reports passed), with a side pane to change course or stop the main turn and each worker, two themes, and a switch for each part. New in 0.5.0, Axioma Charter: the axioma_charter tool and /charter command ask ten plain-English questions about what the agent may do and compile the answers into a readable CHARTER.md and a matching settings block for the owner to review and paste; it applies nothing itself. New in 0.6.0, two optional Desktop additions: an inline advice card the model may write in a reply on the Desktop surface only (light, one-sentence signal, who is affected, a question, and Hold / Go ahead buttons that only send that short reply to the same chat), and a small Axioma light on kanban board cards showing the worst advice recorded for that card's work. 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. Optional operator-configured preflights probe file-presence metadata for required SKILL.md paths under external skill roots and lstat metadata for external device-lock paths; the policy resolves configured workspace/output roots and candidate remove/move paths, including symlinks, for containment checks, without reading those files' contents. Pasted-card verification optionally imports undocumented gateway.platforms.base_exec_approval text helpers and agent.i18n.t behind one compatibility function to recognize localized host framing, falling back to built-in English text if they are absent or change; it neither inspects approval state nor overrides approval. The optional Desktop half registers a right-side pane, a status-bar item, two themes, three palette commands, a settings page and a full-window canvas drawn over the app at low opacity (7-24%) with pointer events off; it subscribes to all gateway events but uses only event types, worker id/goal/status/tool-count/tool-name fields and the passed boolean of a standing_proof result, never message text; on a button press it calls session.steer, session.interrupt, subagent.steer or subagent.interrupt with the text the user typed; it keeps its on/off switches in local plugin storage and makes no network or model calls. The axioma_charter tool and /charter command write two local files, CHARTER.md and charter-settings.yaml, in a charter folder inside the plugin's own data folder and read them back; they make no network or model call, never edit config.yaml or any profile, and apply nothing. The card-code key must be owner-only; if its permissions cannot be confirmed, durable verification is refused.Communitytools

Developer Mode

Explore built-in Hermes toolsets and actions.

HermesAgent

Developer?

Create a Hermes extension for Desktop or agent workflows.

Developer Section