Async Communication Etiquette
aiming-lab/MetaClaw
A skill your agent uses when writing messages in async channels (Slack, GitHub issues, email threads) where the reader may not have context and cannot ask follow-up questions immediately.
A skill your agent uses when a Token Meter task will produce Slack, GitHub, release, contributor, or user-facing status communication.
Install Token Meter Communication
$ npx skills add splunk/token-meter --skill token-meter-communication -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install splunk/token-meter token-meter-communication --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/splunk/token-meter.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.agents/skills/token-meter-communication .claude/skills/token-meter-communication && 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 "token-meter-communication" agent skill from https://github.com/splunk/token-meter/tree/main/.agents/skills/token-meter-communication into .claude/skills/token-meter-communication/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "token-meter-communication", 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/splunk/token-meter/tree/main/.agents/skills/token-meter-communicationType 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 splunk/token-meter --skill token-meter-communication -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install splunk/token-meter token-meter-communication --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/splunk/token-meter.git skills-src && mkdir -p .agents/skills && cp -r skills-src/.agents/skills/token-meter-communication .agents/skills/token-meter-communication && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "token-meter-communication" agent skill from https://github.com/splunk/token-meter/tree/main/.agents/skills/token-meter-communication into .agents/skills/token-meter-communication/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "token-meter-communication", 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 splunk/token-meter --skill token-meter-communication -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install splunk/token-meter token-meter-communication --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/splunk/token-meter.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/.agents/skills/token-meter-communication .cursor/skills/token-meter-communication && 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 "token-meter-communication" agent skill from https://github.com/splunk/token-meter/tree/main/.agents/skills/token-meter-communication into .cursor/skills/token-meter-communication/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "token-meter-communication", 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/splunk/token-meter.git --path .agents/skills/token-meter-communication--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 splunk/token-meter --skill token-meter-communication -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install splunk/token-meter token-meter-communication --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/splunk/token-meter.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/.agents/skills/token-meter-communication .gemini/skills/token-meter-communication && 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 "token-meter-communication" agent skill from https://github.com/splunk/token-meter/tree/main/.agents/skills/token-meter-communication into .gemini/skills/token-meter-communication/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "token-meter-communication", 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 splunk/token-meter token-meter-communicationInstalls 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 splunk/token-meter --skill token-meter-communication -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/splunk/token-meter.git skills-src && mkdir -p .github/skills && cp -r skills-src/.agents/skills/token-meter-communication .github/skills/token-meter-communication && 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 "token-meter-communication" agent skill from https://github.com/splunk/token-meter/tree/main/.agents/skills/token-meter-communication into .github/skills/token-meter-communication/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "token-meter-communication", 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 splunk/token-meter --skill token-meter-communication -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install splunk/token-meter token-meter-communication --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/splunk/token-meter.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/.agents/skills/token-meter-communication .opencode/skills/token-meter-communication && 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 "token-meter-communication" agent skill from https://github.com/splunk/token-meter/tree/main/.agents/skills/token-meter-communication into .opencode/skills/token-meter-communication/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "token-meter-communication", 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
token-meter-communication- GitHub stars
- 110
- Token cost
- ~1.1k tokens
- SKILL.md length
- 580 words
- Files
- 1
- Skills in repo
- 6
- Repo updated
- First seen
- Licence
- MIT
At a glance
A skill your agent uses when a Token Meter task will produce Slack, GitHub, release, contributor, or user-facing status communication.
- Works in 9 steps: Evidence before claims. Say only what… → Channel-appropriate detail. Put durable… → Concise by default. Lead with the… → …
- A Token Meter task will produce Slack
- SKILL.md covers Purpose, Required inputs, General principles and Channel contracts, plus 2 more sections
- Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md
What it does
Token Meter Communication is an agent skill from splunk/token-meter. Use when a Token Meter task will produce Slack, GitHub, release, contributor, or user-facing status communication.
Its SKILL.md is about 1.1k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.
It sits in AI & LLM Engineering. It works with GitHub and Slack. The repository describes itself as: Open-source, local-first AI coding agent usage and cost dashboard for Claude Code, Codex, Cursor, OpenCode, Kiro, and Pi. The licence is MIT.
When your agent uses it
- A Token Meter task will produce Slack
- User-facing status communication
Example prompts
- “/token-meter-communication”
Workflow steps
9 steps, taken from the first numbered list in SKILL.md.
- Evidence before claims. Say only what the current head, checks, external state,
- Channel-appropriate detail. Put durable technical instructions and test steps
- Concise by default. Lead with the outcome, remove process narration, and include
- Privacy and data minimization. Never expose prompts, responses, reasoning, tool
- Explicit delivery state. Use the exact current state; never imply that a pushed
- No invented diagnosis, deadline, or commitment. State uncertainty plainly and
- Preserve approval scope. A message draft does not expand authority for its send
- Deduplicate before send. Inspect the destination thread or discussion and avoid
- Read back after write. The authorized operator must confirm the posted text,
What it can do on your machine
Read from SKILL.md and the folder at commit 4ff456b. 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
No scripts in the folder and no shell commands in SKILL.md.
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md.
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Context cost
Token Meter Communication loads about 1.1k tokens when it runs. Until then it costs about 35 tokens; SKILL.md has 580 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 passed
The automated check found no risky patterns in SKILL.md.
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 splunk/token-meter at commit 4ff456b, republished under its MIT licence (© splunk). 580 words, ~1,094 tokens.
Download SKILL.mdSave it as
.claude/skills/token-meter-communication/SKILL.md (or your agent's skills folder).- name
- token-meter-communication
- description
- Use when a Token Meter task will produce Slack, GitHub, release, contributor, or user-facing status communication.
Token Meter Communication
Purpose
Own the wording and channel fit of every contributor- or user-facing message produced by the Token Meter team. Ground every claim in the current handoff and external state, preserve approval boundaries, and return send-ready copy to the authorized operator.
The communication manager is a message author and quality gate, not an external-write operator. It must not post, comment, push, merge, release, close, label, or request a hosted review.
Required inputs
Read the task envelope, current evidence and findings, exact delivery state, intended
audience and channel, relevant existing discussion, approval scope, and any
channel-specific contract in .agents/workflow/routing.yaml. If a factual claim or
authorization cannot be verified, remove the claim or return a blocker.
General principles
Apply all of these principles to every message:
- Evidence before claims. Say only what the current head, checks, external state, and accepted findings support. Distinguish source-tested, installed, committed, pushed, merged, released, and deployed.
- Channel-appropriate detail. Put durable technical instructions and test steps on GitHub. Keep Slack and status replies compact unless the request requires detail there.
- Concise by default. Lead with the outcome, remove process narration, and include only details the recipient needs to act or respond.
- Privacy and data minimization. Never expose prompts, responses, reasoning, tool contents, credentials, account data, raw traces, local paths, or unrelated internal context.
- Explicit delivery state. Use the exact current state; never imply that a pushed branch is merged, a source test is installed-runtime evidence, or a PR is released.
- No invented diagnosis, deadline, or commitment. State uncertainty plainly and promise only follow-up that is actually owned.
- Preserve approval scope. A message draft does not expand authority for its send or for any adjacent GitHub, Slack, release, or repository action.
- Deduplicate before send. Inspect the destination thread or discussion and avoid an equivalent same-state or same-head reply.
- Read back after write. The authorized operator must confirm the posted text, target, link, and resulting state; discrepancies return to the coordinator.
Channel contracts
Show full SKILL.md (246 more words)Show less
GitHub
Use GitHub for durable, detailed material: verified behavior, exact head or PR link,
clone and checkout steps when needed, install and health checks, restoration,
measurement guidance, limitations, and actionable test requests. In
reporter-end-to-end, put the detailed testing handoff on the linked issue after the
pull request exists and its real URL has been read back. Keep code and commands bounded
to what the recipient needs.
Slack
Prefer one short paragraph. For reporter-end-to-end, thank the reporter, link the
pull request, briefly ask them to try it, and sign as Pratik's agent. Include no code,
commands, clone/install steps, procedural next steps, test matrix, or long technical
summary.
Status, release, and contributor updates
State the current evidence-backed outcome or next step, relevant limitation, and owner without manufacturing urgency or certainty. Use the signature requested by the applicable workflow. Do not repeat an equivalent update merely to show activity.
Procedure
- Verify the audience, channel, objective, current head/state, evidence, and approval.
- Inspect existing discussion for context and duplicate messages.
- Select the applicable channel contract and draft the smallest complete message.
- Audit every factual claim, link, instruction, promise, and requested action against the supplied evidence and approval.
- Return the exact send-ready copy, destination, evidence mapping, approval coverage, execution owner, and any blocker. Do not perform the external write.
Result contract
Return channel and destination, audience and objective, exact draft, evidence used, delivery-state wording, approval coverage, duplicate check, sensitive-data check, execution owner, blockers, and recommended next state.
© splunk, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
Files
Just SKILL.md in .agents/skills/token-meter-communication of splunk/token-meter.
Open the folder on GitHubat commit 4ff456b
Compare with similar skills
Token Meter Communication 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 |
|---|---|---|---|---|---|---|
| Token Meter Communication this skillsplunk/token-meter | 110 | — | ~1.1k | Automated safety check: Pass | MIT | |
| Async Communication Etiquetteaiming-lab/MetaClaw | 3.5k | — | ~224 | Automated safety check: Pass | MIT | |
| Qv PR Minetetherto/qvac | 674 | — | ~1.2k | Automated safety check: Pass | Apache-2.0 | |
| Report Indicator Changesowid/etl | 158 | — | ~2.6k | Automated safety check: Pass | MIT | |
| Building LoopsPostHog/posthog-foss | 721 | — | ~3.6k | Automated safety check: Pass | MIT | |
| ComposioComposioHQ/composio | 30k | 1 repos | ~1.7k | Automated safety check: Pass | MIT |
Similar skills
Qv PR Mine
tetherto/qvac
Show the current user's open PRs across every pod registered under .github/teams/, grouped by merge readiness, with copy-paste Slack ping messages routed to the owning pod's team.
Report Indicator Changes
owid/etl
Draft a short update message to a topic-owner reviewer after landing substantial dataset or chart changes on staging.
- Official
Building Loops
PostHog/posthog-foss
Build a Loop for PostHog Desktop: a workflow that creates an AI task each time its trigger fires, optionally followed by a Slack or email notification with the task's result.
Composio
ComposioHQ/composio
Route and complete Composio work across Composio For You and Composio Platform.
Triage
TalAter/annyang
Triage and close GitHub issues on TalAter/annyang. An agent skill from TalAter/annyang.
More from splunk/token-meter
Token Meter Development
splunk/token-meter
A skill your agent uses when a Token Meter issue or approved feature needs diagnosis or implementation in the repository.
Token Meter GitHub Ops
splunk/token-meter
A skill your agent uses when Token Meter GitHub issues, pull requests, review requests, checks, comments, merges, or closure need to be managed.
Token Meter Review
splunk/token-meter
A skill your agent uses when a Token Meter change needs independent requirements, correctness, regression, privacy, or cross-surface review.
Token Meter Verification
splunk/token-meter
A skill your agent uses when Token Meter changes or claims need independent source, test, runtime, native, browser, privacy, or platform verification.
Token Meter Intake
splunk/token-meter
A skill your agent uses when a Token Meter Slack or GitHub request needs contextual intake, clarification, triage, acknowledgment, or closure.
Related
Categories
Questions about Token Meter Communication
What does Token Meter Communication do?
A skill your agent uses when a Token Meter task will produce Slack, GitHub, release, contributor, or user-facing status communication. Token Meter Communication is an agent skill from splunk/token-meter. Use when a Token Meter task will produce Slack, GitHub, release, contributor, or user-facing status communication.
When should I use Token Meter Communication?
Token Meter Communication fits situations like: A Token Meter task will produce Slack; user-facing status communication.
How do I install Token Meter Communication in Claude Code?
Run `npx skills add splunk/token-meter --skill token-meter-communication -a claude-code`. Or copy the skill folder (.agents/skills/token-meter-communication in splunk/token-meter) into .claude/skills/token-meter-communication in your project. Claude Code loads it when a task matches its description.
How do I install Token Meter Communication in Codex?
Run `npx skills add splunk/token-meter --skill token-meter-communication -a codex`. Or copy the skill folder (.agents/skills/token-meter-communication in splunk/token-meter) into .agents/skills/token-meter-communication in your project. Codex loads it when a task matches its description.
Can I use Token Meter Communication 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 splunk/token-meter --skill token-meter-communication -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/token-meter-communication, .gemini/skills/token-meter-communication, .github/skills/token-meter-communication and .opencode/skills/token-meter-communication in your project.
What does Token Meter Communication need to run?
SKILL.md names no scripts, command-line tools or credentials: Token Meter Communication is instructions for the agent only.
Does Token Meter Communication access the network?
SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.
Is Token Meter Communication safe to install?
Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.
What licence does Token Meter Communication use?
Token Meter Communication is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
How many tokens does Token Meter Communication use?
About 1.1k tokens (SKILL.md is roughly 4.4k 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 Token Meter Communication?
Skills that share tags, products or a category with Token Meter Communication: Async Communication Etiquette (aiming-lab/MetaClaw, 3.5k stars), Qv PR Mine (tetherto/qvac, 674 stars), Report Indicator Changes (owid/etl, 158 stars) and Building Loops (PostHog/posthog-foss, 721 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Token Meter Communication?
splunk (a GitHub organization) maintains it in splunk/token-meter, which has 110 GitHub stars. The repository holds 6 skills in this directory. The repository was last updated on October 7, 2026.
Source: splunk/token-meter on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.