Mz Release Signoff
MaterializeInc/materialize
Verify a release candidate on the Grafana dashboards and sign off in release.
The AGENTS.md file that sf hardis:org:monitor:backup writes at the root of every monitoring repository, so a coding agent can answer questions about the org, its CI/CD deployments and its Grafana…
Install Monitoring Agents Md
$ npx skills add hardisgroupcom/sfdx-hardis --skill monitoring-agents-md -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install hardisgroupcom/sfdx-hardis monitoring-agents-md --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/hardisgroupcom/sfdx-hardis.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.claude/skills/monitoring-agents-md .claude/skills/monitoring-agents-md && rm -rf skills-srcUse ~/.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/
Install the "monitoring-agents-md" agent skill from https://github.com/hardisgroupcom/sfdx-hardis/tree/main/.claude/skills/monitoring-agents-md into .claude/skills/monitoring-agents-md/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "monitoring-agents-md", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/hardisgroupcom/sfdx-hardis/tree/main/.claude/skills/monitoring-agents-mdType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add hardisgroupcom/sfdx-hardis --skill monitoring-agents-md -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install hardisgroupcom/sfdx-hardis monitoring-agents-md --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/hardisgroupcom/sfdx-hardis.git skills-src && mkdir -p .agents/skills && cp -r skills-src/.claude/skills/monitoring-agents-md .agents/skills/monitoring-agents-md && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "monitoring-agents-md" agent skill from https://github.com/hardisgroupcom/sfdx-hardis/tree/main/.claude/skills/monitoring-agents-md into .agents/skills/monitoring-agents-md/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "monitoring-agents-md", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add hardisgroupcom/sfdx-hardis --skill monitoring-agents-md -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install hardisgroupcom/sfdx-hardis monitoring-agents-md --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/hardisgroupcom/sfdx-hardis.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/.claude/skills/monitoring-agents-md .cursor/skills/monitoring-agents-md && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "monitoring-agents-md" agent skill from https://github.com/hardisgroupcom/sfdx-hardis/tree/main/.claude/skills/monitoring-agents-md into .cursor/skills/monitoring-agents-md/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "monitoring-agents-md", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/hardisgroupcom/sfdx-hardis.git --path .claude/skills/monitoring-agents-md--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add hardisgroupcom/sfdx-hardis --skill monitoring-agents-md -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install hardisgroupcom/sfdx-hardis monitoring-agents-md --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/hardisgroupcom/sfdx-hardis.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/.claude/skills/monitoring-agents-md .gemini/skills/monitoring-agents-md && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "monitoring-agents-md" agent skill from https://github.com/hardisgroupcom/sfdx-hardis/tree/main/.claude/skills/monitoring-agents-md into .gemini/skills/monitoring-agents-md/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "monitoring-agents-md", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install hardisgroupcom/sfdx-hardis monitoring-agents-mdInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add hardisgroupcom/sfdx-hardis --skill monitoring-agents-md -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/hardisgroupcom/sfdx-hardis.git skills-src && mkdir -p .github/skills && cp -r skills-src/.claude/skills/monitoring-agents-md .github/skills/monitoring-agents-md && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "monitoring-agents-md" agent skill from https://github.com/hardisgroupcom/sfdx-hardis/tree/main/.claude/skills/monitoring-agents-md into .github/skills/monitoring-agents-md/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "monitoring-agents-md", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add hardisgroupcom/sfdx-hardis --skill monitoring-agents-md -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install hardisgroupcom/sfdx-hardis monitoring-agents-md --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/hardisgroupcom/sfdx-hardis.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/.claude/skills/monitoring-agents-md .opencode/skills/monitoring-agents-md && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "monitoring-agents-md" agent skill from https://github.com/hardisgroupcom/sfdx-hardis/tree/main/.claude/skills/monitoring-agents-md into .opencode/skills/monitoring-agents-md/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "monitoring-agents-md", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
Facts
- Skill name
monitoring-agents-md- GitHub stars
- 401
- Token cost
- ~3.7k tokens
- SKILL.md length
- 999 words
- Files
- 2
- Skills in repo
- 21
- Repo updated
- First seen
- Licence
- AGPL-3.0
At a glance
The AGENTS.md file that sf hardis:org:monitor:backup writes at the root of every monitoring repository, so a coding agent can answer questions about the org, its CI/CD deployments and its Grafana…
- Tasks that involve Monitoring and alerting
- SKILL.md covers Where it lives, What impacts it, and which…, Rules for the text and Verify
- Runs JavaScript scripts from its folder; calls sf, npx and node; reaches github.com and acme.grafana.net; needs GRAFANA_API_TOKEN and GRAFANA_TOKEN
- Tasks that involve Agent instruction files
What it does
Monitoring Agents Md is an agent skill from hardisgroupcom/sfdx-hardis. The AGENTS.md file that sf hardis:org:monitor:backup writes at the root of every monitoring repository, so a coding agent can answer questions about the org, its CI/CD deployments and its Grafana history. Load it whenever a change touches something that file describes - the backup output (files, folders, manifests, filters, commit messages), the monitoring pipeline templates, monitoring commands or notification types, logs/metrics sent to Grafana, config keys of a monitoring branch (deploymentRepository…
Its SKILL.md is about 3.7k tokens, which your agent loads only when the skill is triggered. The skill folder holds 1 other file.
It sits in DevOps & Cloud, covering Monitoring and alerting, Agent instruction files and Deployment. It works with Grafana and Git. The repository describes itself as: French-army-knife Toolbox for Salesforce. Orchestrates base commands and assist users with interactive wizards to make much more than native Salesforce CLI + Allows you to define…. The licence is AGPL-3.0.
When your agent uses it
- Tasks that involve Monitoring and alerting
- Tasks that involve Agent instruction files
- Tasks that involve Deployment
Example prompts
- “/monitoring-agents-md”
Requirements
- Node.js
- A credential in GRAFANA_API_TOKEN
What it can do on your machine
Read from SKILL.md and the folder at commit 9625b22. 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
Ships script files (JavaScript), which the agent can run.
Shell commands in SKILL.md call:
sfnpxnode
From the folder's file list and the shell code blocks in SKILL.md.
Network
Hosts in commands or code, which the agent is likely to contact:
github.comacme.grafana.net
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names these keys or tokens, usually read from environment variables:
GRAFANA_API_TOKENGRAFANA_TOKEN
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Context cost
Monitoring Agents Md loads about 3.7k tokens when it runs. Until then it costs about 178 tokens; SKILL.md has 999 words of instructions outside code blocks.
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: notes
The automated check noted patterns worth knowing about, such as sudo or a known installer.
- NoteMentions a .env fileSKILL.md:50
**: tokens come from the environment, a `.env` file (git ignores it in monitoring repositories), or a CLI the user is lo - NoteMentions a .env fileSKILL.md:76
AFANA_TOKEN`), in the environment or in `.env` (a Viewer service account, with the Query permission on the Loki and Prom
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 hardisgroupcom/sfdx-hardis at commit 9625b22, republished under its AGPL-3.0 licence (© hardisgroupcom). 999 words, ~3,654 tokens.
Download SKILL.mdSave it as
.claude/skills/monitoring-agents-md/SKILL.md (or your agent's skills folder). This skill also uses 1 other file; get the full folder from GitHub.- name
- monitoring-agents-md
- description
- The AGENTS.md file that sf hardis:org:monitor:backup writes at the root of every monitoring repository, so a coding agent can answer questions about the org, its CI/CD deployments and its Grafana history. Load it whenever a change touches something that file describes - the backup output (files, folders, manifests, filters, commit messages), the monitoring pipeline templates, monitoring commands or notification types, logs/metrics sent to Grafana, config keys of a monitoring branch (deploymentRepository, grafanaUrl...), the CI/CD pipeline behavior it explains (deploy:smart, mergeTargets, delta, deployment actions, promotion branches), or git provider APIs and token variable names.
- user-invocable
- false
The monitoring AGENTS.md
sf hardis:org:monitor:backup writes an AGENTS.md (and a CLAUDE.md that imports it) at the root of each monitoring repository. Coding agents opened in that repository answer from it. It describes the product, so a change to the product that it describes makes it wrong until it is updated, and nothing fails when it is wrong: the agent just gives a confident, stale answer.
Where it lives
| What | Where |
|---|---|
| The text | defaults/templates/monitoring/AGENTS.md |
| Rendering, merge with user notes, CLAUDE.md | src/common/monitoring/monitoringAgentsMd.ts |
Address check, other-branch lookup, deploymentRepository prompt | src/common/monitoring/monitoringDeploymentRepository.ts |
| Git provider of an address | GitProvider.getProviderTypeFromRemoteUrl (src/common/gitProvider/index.ts) |
| Where the backup writes it | writeAgentsMd() in src/commands/hardis/org/monitor/backup.ts, after the BACKUP notification |
| Tests | test/common/monitoring/monitoringAgentsMd.test.ts |
| Pages that describe it to humans | docs/salesforce-monitoring-metadata-backup.md (Ask questions with a coding agent), docs/salesforce-monitoring-home.md (Ask your coding agent), docs/salesforce-agentic-automation.md (Ask Questions About Your Org History and Deployments) |
| Training | Lab 3.8 of ../sfdx-hardis-training (EN and FR) mentions the file |
Placeholders filled from the branch configuration at each backup: {{monitoringCommandsTable}}, {{deploymentRepositoryStatus}}, {{grafanaStatus}}. Everything else is static text.
What impacts it, and which section to update
| A change to... | Section of the template |
|---|---|
Files or folders the backup writes, the manifests, package-skip-items.xml, MONITORING_BACKUP_* variables, full mode, Data Cloud retrieve, installed packages, doc generation output | Files and folders, What is not in the backup, Where each kind of change comes from |
The backup commit message or schedule (defaults/monitoring/* pipelines), the jobs that run after it | How it works, Collect the changes (step 2 and 3 read the message format and the schedule) |
| The monitoring pipeline templates (job names, artifacts, provider files) | How it works, Files and folders, the last paragraph of Git server access |
Monitoring commands, notification types, frequencies, monitoringCommands, monitoringDisable, MONITORING_DISABLE | Rendered automatically by buildMonitoringCommandsTable: check the table still renders, and update Labels (Grafana) if a type changes |
Metric keys, the Loki payload (_title, _logElements, _metrics, _jobUrl, type-specific fields like topFailingApex...), labels (orgIdentifier, type, severity, gitIdentifier), metric naming (<Key>_metric, _percent...), pseudonymization, NOTIF_API_* variables | Monitoring results in Grafana (Find this org, What is sent, Grafana recipes) |
A metric used by the v2 dashboards (renamed, removed), the severity or the presence of a notification (a failed backup sends an error BACKUP line, a job that did not run sends nothing) | Grafana recipes: every query there was run against a live instance, run them again |
hardis:org:configure:grafana-dashboards, GRAFANA_API_URL, GRAFANA_API_TOKEN, the dashboards folder or uids, datasource detection | Monitoring results in Grafana (Connect, Find the datasources, Answer) |
Config keys of a monitoring branch (deploymentRepository, deploymentBranch, grafanaUrl, grafana*DatasourceUid...) | Files and folders (.sfdx-hardis.yml row) and the matching status builder in monitoringAgentsMd.ts |
hardis:org:configure:monitoring questions or flags | The status builders (they tell the agent how the user sets a value) |
CI/CD pipeline behavior: deploy:smart scope (manifest/package.xml, no-overwrite, delta, smart tests), mergeTargets, branch config files, deployment actions (types, context, runOnlyOnceByOrg, scripts/actions/), promotion branches, Pull Request comments, CI workflow file names | How the CI/CD pipeline works |
Git provider CLIs, API paths, token variable names (CI_SFDX_HARDIS_*_TOKEN...), merge commit formats | Git server access, History |
| Anonymization of user data in notifications | Labels (the pseudonymization sentence) |
When in doubt, grep the template for the name you are changing: grep -n "<name>" defaults/templates/monitoring/AGENTS.md.
Show full SKILL.md (488 more words)Show less
Rules for the text
- Describe what the product does, from the source. Read the command, not its name. Two facts were wrong in the first version and corrected by the maintainer:
deploy:smartdeploysmanifest/package.xmlminus the no-overwrite items already in the org (not the package directories), and the backup never deletes files (existence comes frommanifest/package-all-org-items.xml). - Salesforce orgs: read-only, and only with the user's explicit consent. This is a hard rule. The section Salesforce org access lists the only commands an agent may run against an org: it is an allowlist, never add a command that can write (deploy, data change, anonymous Apex, test run, permission or user change, any
sf hardiscommand). The agent asks before connecting, uses an org the user authenticated (VS Code Org Manager orsf org login webrun by the user), never the CI credentials, and refuses write requests. - The agent only reads. Never add an instruction that pushes, comments, runs a pipeline, or changes Grafana. The one write allowed is a single line of
.sfdx-hardis.yml, after asking the user, and never a secret. - Secrets stay out of
.sfdx-hardis.yml: tokens come from the environment, a.envfile (git ignores it in monitoring repositories), or a CLI the user is logged in with. - Prefer discovery to lists that rot: tell the agent how to list metric names, label values or datasources rather than hardcoding them.
- Keep the two markers and the
markdownlint-disable MD013/enablepair around the block. No em-dashes, and the "Never write like an AI" rules ofCLAUDE.md. - Placeholders are filled with replacer functions (
.replace('{{x}}', () => value)): keep it that way, config values may hold$. - A new configurable value gets a status builder (like
buildGrafanaStatus) that says what is set, or tells the agent to ask the user and which line to write.
Verify
npx mocha test/common/monitoring/monitoringAgentsMd.test.tsThen render it with and without the optional settings and lint the result: it must pass markdownlint with no finding.
// render.mts, run with: node --import tsx render.mts
import fs from 'fs';
import { buildMonitoringAgentsMdBlock } from './src/common/monitoring/monitoringAgentsMd.ts';
fs.writeFileSync('AGENTS-unset.md', await buildMonitoringAgentsMdBlock({}));
fs.writeFileSync('AGENTS-set.md', await buildMonitoringAgentsMdBlock({ deploymentRepository: 'https://github.com/acme/crm', grafanaUrl: 'https://acme.grafana.net' }));npx markdownlint-cli2 AGENTS-unset.md AGENTS-set.mdWhen the Grafana section changed, run its queries against a live instance. The script only sends GET requests; it reads the instance from GRAFANA_API_URL and the token from GRAFANA_API_TOKEN (or GRAFANA_TOKEN), in the environment or in .env (a Viewer service account, with the Query permission on the Loki and Prometheus datasources; GRAFANA_LOKI_UID and GRAFANA_PROM_UID default to the Grafana Cloud grafanacloud-logs and grafanacloud-prom). Never write a Grafana URL in the repository: it stays in .env. Pass the orgIdentifier of an org that runs the backup and all the checks (list them with sum by (orgIdentifier, type) (count_over_time({source="sfdx-hardis"}[2d]))): EMPTY only means the org does not send that type, FAIL is a broken query. Never write that orgIdentifier, or any other customer name, in a file, a commit or a Pull Request.
node .claude/skills/monitoring-agents-md/verify-grafana-recipes.mjs <orgIdentifier>Grafana stays read-only, in these checks as in the text: never create, change or delete anything there.
Last, check the three documentation pages listed above still match, and run the training-impact skill if a question the course shows changes.
© hardisgroupcom, AGPL-3.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
Files
SKILL.md and 1 other file in .claude/skills/monitoring-agents-md of hardisgroupcom/sfdx-hardis.
- SKILL.md
- verify-grafana-recipes.mjs
Open the folder on GitHubat commit 9625b22
Compare with similar skills
Monitoring Agents Md 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.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Monitoring Agents Md this skillhardisgroupcom/sfdx-hardis | 401 | — | ~3.7k | Automated safety check: Notes | AGPL-3.0 | |
| Mz Release SignoffMaterializeInc/materialize | 6.4k | — | ~7.2k | Automated safety check: Pass | Custom licence | |
| Dashboard Previewm4r1k/Eneru | 149 | — | ~1.4k | Automated safety check: Pass | MIT | |
| Agr Releasecomputerlovetech/agr | 451 | — | ~1.6k | Automated safety check: Pass | MIT | |
| Mecatl Release Cuttingstacklok/mecatl | 241 | — | ~3.9k | Automated safety check: Pass | Apache-2.0 | |
| Aqua Metricsoracle/accelerated-data-science | 125 | — | ~1.5k | Automated safety check: Pass | UPL-1.0 |
Similar skills
Dashboard Preview
m4r1k/Eneru
Visually verify Eneru browser-dashboard changes against a live daemon or audit an exact deployment.
Agr Release
computerlovetech/agr
Release process for the agr package. An agent skill from computerlovetech/agr.
Mecatl Release Cutting
stacklok/mecatl
Cuts a tagged mecatl release by dispatching the release-PR workflow, merging the bot's pull request and verifying the tag, images, Helm chart, signed archives and Homebrew formula.
- Official
Aqua Metrics
oracle/accelerated-data-science
Set up Prometheus and Grafana monitoring for AQUA vLLM model deployments on OCI.
OpenWork Release Process
different-ai/openwork
Cuts an OpenWork desktop release through a tag-driven GitHub Actions workflow that makes no commits, with pre-tag checks on open fix PRs and verification afterward.
More from hardisgroupcom/sfdx-hardis
All 21 skills in this reposfdx-hardis Training End-to-End Test
hardisgroupcom/sfdx-hardis
Walks the sfdx-hardis training course end to end as a learner would, against a real Developer Edition org and fork, fixing broken steps and screenshots that no longer match.
Promotion Branches E2E Test
hardisgroupcom/sfdx-hardis
Runs a full end-to-end test of sfdx-hardis promotion branches and backpromote against real Salesforce orgs and a throwaway repository, then writes a report.
sfdx-hardis Architecture Guide
hardisgroupcom/sfdx-hardis
Explains how the sfdx-hardis Salesforce CLI plugin is built: its TypeScript and Oclif stack, command layout, agent-mode flag and provider classes for git, notifications and AI.
Changelog Style Rules
hardisgroupcom/sfdx-hardis
Style rules for adding CHANGELOG.md entries: short, user-facing bullets grouped by command under the beta section, each linking the command's docs page.
Documentation
hardisgroupcom/sfdx-hardis
Documentation standards for sfdx-hardis commands (description format with Command Behavior and Technical explanations sections, MkDocs site, build:doc).
Fix Jscpd
hardisgroupcom/sfdx-hardis
Decision framework for fixing jscpd (copy-paste detector) errors.
Related
Categories
Questions about Monitoring Agents Md
What does Monitoring Agents Md do?
The AGENTS.md file that sf hardis:org:monitor:backup writes at the root of every monitoring repository, so a coding agent can answer questions about the org, its CI/CD deployments and its Grafana…. Monitoring Agents Md is an agent skill from hardisgroupcom/sfdx-hardis.md file that sf hardis:org:monitor:backup writes at the root of every monitoring repository, so a coding agent can answer questions about the org, its CI/CD deployments and its Grafana history.
When should I use Monitoring Agents Md?
Monitoring Agents Md fits situations like: tasks that involve Monitoring and alerting; tasks that involve Agent instruction files; tasks that involve Deployment.
How do I install Monitoring Agents Md in Claude Code?
Run `npx skills add hardisgroupcom/sfdx-hardis --skill monitoring-agents-md -a claude-code`. Or copy the skill folder (.claude/skills/monitoring-agents-md in hardisgroupcom/sfdx-hardis) into .claude/skills/monitoring-agents-md in your project. Claude Code loads it when a task matches its description.
How do I install Monitoring Agents Md in Codex?
Run `npx skills add hardisgroupcom/sfdx-hardis --skill monitoring-agents-md -a codex`. Or copy the skill folder (.claude/skills/monitoring-agents-md in hardisgroupcom/sfdx-hardis) into .agents/skills/monitoring-agents-md in your project. Codex loads it when a task matches its description.
Can I use Monitoring Agents Md 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 hardisgroupcom/sfdx-hardis --skill monitoring-agents-md -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/monitoring-agents-md, .gemini/skills/monitoring-agents-md, .github/skills/monitoring-agents-md and .opencode/skills/monitoring-agents-md in your project.
What does Monitoring Agents Md need to run?
Going by SKILL.md and its folder, Monitoring Agents Md needs JavaScript for the scripts in its folder, the command-line tools its instructions call (sf, npx and node) and credentials named GRAFANA_API_TOKEN and GRAFANA_TOKEN. Our summary lists: Node.js; A credential in GRAFANA_API_TOKEN.
Does Monitoring Agents Md access the network?
SKILL.md names 2 domains. In commands or code: github.com and acme.grafana.net; the agent is likely to contact these when it follows the instructions. This is read from the text; nothing was executed.
Is Monitoring Agents Md safe to install?
Our automated static check of SKILL.md found notes only (mentions a .env file), nothing it rates as a warning. It is not a guarantee. Review the folder before installing.
What licence does Monitoring Agents Md use?
Monitoring Agents Md is published under the AGPL-3.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
How many tokens does Monitoring Agents Md use?
About 3.7k tokens (SKILL.md is roughly 15k 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 Monitoring Agents Md?
Skills that share tags, products or a category with Monitoring Agents Md: Mz Release Signoff (MaterializeInc/materialize, 6.4k stars), Dashboard Preview (m4r1k/Eneru, 149 stars), Agr Release (computerlovetech/agr, 451 stars) and Mecatl Release Cutting (stacklok/mecatl, 241 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Monitoring Agents Md?
hardisgroupcom (a GitHub organization) maintains it in hardisgroupcom/sfdx-hardis, which has 401 GitHub stars. The repository holds 21 skills in this directory. The repository was last updated on October 8, 2026.
Source: hardisgroupcom/sfdx-hardis on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.