Testing Scope MCP
daydreamlive/scope
Test Daydream Scope through its stdio MCP server, including disconnected startup, connecttoscope, direct Python stdio client fallback, and lightweight smoke tests.
A skill your agent uses when working in a repo with agentacct MCP configured, or when asked to track coding-agent work, smoke-test agentacct integrations, or report objective AI-agent task evidence.
Install Agentacct Workflow
$ npx skills add mikehasa/agentacct --skill agentacct-workflow -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install mikehasa/agentacct agentacct-workflow --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/mikehasa/agentacct.git skills-src && mkdir -p .claude/skills && cp -r skills-src/integrations/hermes/agentacct-workflow .claude/skills/agentacct-workflow && 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 "agentacct-workflow" agent skill from https://github.com/mikehasa/agentacct/tree/main/integrations/hermes/agentacct-workflow into .claude/skills/agentacct-workflow/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "agentacct-workflow", 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/mikehasa/agentacct/tree/main/integrations/hermes/agentacct-workflowType 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 mikehasa/agentacct --skill agentacct-workflow -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install mikehasa/agentacct agentacct-workflow --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/mikehasa/agentacct.git skills-src && mkdir -p .agents/skills && cp -r skills-src/integrations/hermes/agentacct-workflow .agents/skills/agentacct-workflow && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "agentacct-workflow" agent skill from https://github.com/mikehasa/agentacct/tree/main/integrations/hermes/agentacct-workflow into .agents/skills/agentacct-workflow/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "agentacct-workflow", 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 mikehasa/agentacct --skill agentacct-workflow -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install mikehasa/agentacct agentacct-workflow --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/mikehasa/agentacct.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/integrations/hermes/agentacct-workflow .cursor/skills/agentacct-workflow && 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 "agentacct-workflow" agent skill from https://github.com/mikehasa/agentacct/tree/main/integrations/hermes/agentacct-workflow into .cursor/skills/agentacct-workflow/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "agentacct-workflow", 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/mikehasa/agentacct.git --path integrations/hermes/agentacct-workflow--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 mikehasa/agentacct --skill agentacct-workflow -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install mikehasa/agentacct agentacct-workflow --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/mikehasa/agentacct.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/integrations/hermes/agentacct-workflow .gemini/skills/agentacct-workflow && 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 "agentacct-workflow" agent skill from https://github.com/mikehasa/agentacct/tree/main/integrations/hermes/agentacct-workflow into .gemini/skills/agentacct-workflow/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "agentacct-workflow", 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 mikehasa/agentacct agentacct-workflowInstalls 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 mikehasa/agentacct --skill agentacct-workflow -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/mikehasa/agentacct.git skills-src && mkdir -p .github/skills && cp -r skills-src/integrations/hermes/agentacct-workflow .github/skills/agentacct-workflow && 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 "agentacct-workflow" agent skill from https://github.com/mikehasa/agentacct/tree/main/integrations/hermes/agentacct-workflow into .github/skills/agentacct-workflow/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "agentacct-workflow", 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 mikehasa/agentacct --skill agentacct-workflow -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install mikehasa/agentacct agentacct-workflow --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/mikehasa/agentacct.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/integrations/hermes/agentacct-workflow .opencode/skills/agentacct-workflow && 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 "agentacct-workflow" agent skill from https://github.com/mikehasa/agentacct/tree/main/integrations/hermes/agentacct-workflow into .opencode/skills/agentacct-workflow/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "agentacct-workflow", 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
agentacct-workflow- GitHub stars
- 765
- Token cost
- ~1.6k tokens
- SKILL.md length
- 558 words
- Files
- 1
- Skills in repo
- 1
- Repo updated
- First seen
- Licence
- MIT
At a glance
A skill your agent uses when working in a repo with agentacct MCP configured, or when asked to track coding-agent work, smoke-test agentacct integrations, or report objective AI-agent task evidence.
- Works in 3 steps: If local client identifiers are… → Before meaningful work, open a section… → During work, record important…
- Working in a repo with agentacct MCP configured
- SKILL.md covers Overview, When to Use, Workflow and Claim Boundaries, plus 3 more sections
- Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md
What it does
Agentacct Workflow is an agent skill from mikehasa/agentacct. Use when working in a repo with agentacct MCP configured, or when asked to track coding-agent work, smoke-test agentacct integrations, or report objective AI-agent task evidence.
Its SKILL.md is about 1.6k 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 Testing & QA, covering QA and bug reports, LLM cost and token optimization and MCP servers. It works with Model Context Protocol and Python. The repository describes itself as: See what your coding agents did and what it cost. Breaks each task down into work steps — tools used, files changed, tests run, time and tokens spent. Local-first dashboard for… The licence is MIT.
When your agent uses it
- Working in a repo with agentacct MCP configured
- Asked to track coding-agent work
- Smoke-test agentacct integrations
- Report objective AI-agent task evidence
Example prompts
- “/agentacct-workflow”
Workflow steps
3 steps, taken from the first numbered list in SKILL.md.
- If local client identifiers are available, call agentacct_attach_client_context
- Before meaningful work, open a section with agentacct_record_section
- During work, record important checkpoints (agentacct_record_section with the same section_id and section_status=checkpoint)
What it can do on your machine
Read from SKILL.md and the folder at commit 03f1dd8. 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 (its code samples are bash).
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
Agentacct Workflow loads about 1.6k tokens when it runs. Until then it costs about 49 tokens; SKILL.md has 558 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 mikehasa/agentacct at commit 03f1dd8, republished under its MIT licence (© mikehasa). 558 words, ~1,635 tokens.
Download SKILL.mdSave it as
.claude/skills/agentacct-workflow/SKILL.md (or your agent's skills folder).- name
- agentacct-workflow
- description
- Use when working in a repo with agentacct MCP configured, or when asked to track coding-agent work, smoke-test agentacct integrations, or report objective AI-agent task evidence.
- version
- 1.0.0
- author
- agentacct
- license
- MIT
agentacct Workflow
Overview
Use agentacct as a lightweight workflow ledger for AI-agent work. When the agentacct MCP tools are available, record a compact timeline of meaningful work rather than relying only on final chat summaries.
This skill does not mean agentacct automatically sees every token or exact provider bill. MCP events, local usage imports, and provider/proxy cost enforcement are separate capabilities.
When to Use
Use this skill when:
- Working in a repository that has agentacct initialized.
- agentacct MCP tools such as
agentacct_record_eventare available. - Running Hermes, OpenCode, OpenClaw, Claude Code, Codex, or another coding agent with agentacct integration.
- The user asks for evidence of AI-agent work, token/cost tracking, MCP smoke tests, or Agent FinOps workflow validation.
Do not use this skill to claim exact billing unless the run used a supported usage importer or provider/proxy path.
Workflow
- If local client identifiers are available, call
agentacct_attach_client_context:
source: hermes or the active coding-agent name
client: hermes, claude-code, codex, opencode, openclaw, or other
client_session_id: local session/thread id
client_transcript_id: local transcript/log id if known
parent_client_session_id: parent/root session id if this is a child agent
turn_id/message_id/request_id: current ids if known
client_event_timestamp: client timestamp if known- Before meaningful work, open a section with
agentacct_record_section:
section_id: short stable id for this piece of work
section_status: started
section_title: concise task description
source: hermes or the active coding-agent name
run_id: stable task/session id if known- During work, record important checkpoints (
agentacct_record_sectionwith the samesection_idandsection_status=checkpoint):
- major decisions
- scope changes
- repeated errors
- blockers
Sections are the work contract. Use section_status=started, checkpoint, completed, blocked, or handed_off, and include client/session/turn identifiers when known. started and checkpoint are in-progress states; completed, blocked, and handed_off are terminal.
- If visible token/cost usage is available, call
agentacct_record_agent_usage_debug:
reporting_basis: visible_client_usage
source/client/client_session_id: same values used for context when known
provider/model: visible provider and model if known
input_tokens/output_tokens/cache_read_input_tokens/reasoning_output_tokens/cost_usd: only fields actually visibleIf the client does not expose token/cost usage, call the same tool with reporting_basis: unavailable and a short summary. Do not guess.
- After tests/builds/smokes, record machine-check evidence:
- Prefer
agentacct_record_machine_checkwhen available. - Otherwise call
agentacct_record_eventwith a compact test/build result.
- At completion, close the section with
agentacct_record_section:
section_id: same section id
section_status: completed
summary: what changed, with tests, builds, diffs, tool calls, token/cost evidence actually observed- If blocked, call
agentacct_record_sectionwithsection_status=blocked:
section_id: same section id
section_status: blocked
blocker: concrete blocker
next_step: what would unblock it- If handing work to another agent/session, or stopping cleanly so the user can
continue elsewhere, close the section with
section_status=handed_off:
section_id: same section id
section_status: handed_off
summary: what is complete and what remains
next_step: the concrete continuation point- In the final response, report:
- what was changed or tested
- exact validation command/result
- agentacct event summary if checked
- token/cost data only if actually observed
- unsupported claims or blockers clearly labeled
Show full SKILL.md (237 more words)Show less
Claim Boundaries
Keep these separate:
- MCP events prove that the agent recorded work.
- MCP client context and section events prove the agent reported semantic workflow anchors and local join keys.
- MCP usage debug events prove only what the agent reported seeing about its own token/cost usage. They are comparison evidence and are not agentacct usage/cost totals.
- Local usage import proves agentacct parsed supported client-reported token data.
- Provider/API proxy data proves only traffic that actually flowed through agentacct or returned provider usage/cost fields.
Do not say agentacct hard-stopped, billed exactly, or tracked all sessions unless the relevant enforcement/import/proxy path was actually used.
Client Notes
Hermes
If agentacct MCP is configured, call agentacct tools directly. For one-shot work, load this skill explicitly:
hermes chat -s agentacct-workflow -q "..."OpenCode
OpenCode should receive equivalent instructions through repo AGENTS.md or a custom OpenCode agent. For smoke tests, use --format json when token/cost fields are needed.
OpenClaw
Confirm the actual workspace path before reading repo files. If OpenClaw is running from an isolated workspace that does not contain the repo, record a blocker/workspace mismatch instead of pretending file inspection succeeded.
Minimal Smoke Prompt
Use agentacct MCP to record a section with agentacct_record_section (section_status=started). Inspect the integration docs if available. Record the same section with section_status=completed and one objective finding in the summary. Reply exactly SENTINEL_WORKFLOW_OK.Verification Checklist
-
agentacct_record_sectionwas called withsection_status=started. -
agentacct_attach_client_contextwas used when local ids were available. -
agentacct_record_agent_usage_debugwas called with visible usage orreporting_basis=unavailable. - Meaningful checkpoints or machine checks were recorded when applicable.
- Completion, blocker, or clean handoff was recorded.
- Final response separates MCP evidence from token/cost/billing evidence.
- No secrets or raw provider bodies were printed.
© mikehasa, 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 integrations/hermes/agentacct-workflow of mikehasa/agentacct.
Open the folder on GitHubat commit 03f1dd8
Compare with similar skills
Agentacct Workflow 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 |
|---|---|---|---|---|---|---|
| Agentacct Workflow this skillmikehasa/agentacct | 765 | — | ~1.6k | Automated safety check: Pass | MIT | |
| Testing Scope MCPdaydreamlive/scope | 452 | — | ~1.2k | Automated safety check: Pass | Custom licence | |
| Connectactiveing123/mcptoon | 214 | 1 repos | ~701 | Automated safety check: Pass | Apache-2.0 | |
| Authoringactiveing123/mcptoon | 214 | — | ~559 | Automated safety check: Pass | Apache-2.0 | |
| Triageactiveing123/mcptoon | 214 | — | ~488 | Automated safety check: Pass | Apache-2.0 | |
| Glance TestDebugBase/glance | 156 | — | ~827 | Automated safety check: Pass | MIT |
Similar skills
Connect
activeing123/mcptoon
Connect any AI agent to MCP servers through mcptoon — one config synced everywhere, one stdio gateway, 99.2% fewer tokens on tool discovery.
Authoring
activeing123/mcptoon
Add or edit an MCP server entry in mcptoon's config correctly — stdio/streamable-http/sse shapes, command rules, placeholders, and validation.
Triage
activeing123/mcptoon
Diagnose and fix broken MCP servers in mcptoon — doctor, health, per-server probes, and the common failure playbook.
Glance Test
DebugBase/glance
Run E2E browser tests on any web application using Glance MCP.
Sage Wiki Integrate
xoai/sage-wiki
Pipeline skill that wires sage-wiki into an existing project — detects language, installs the client, runs a smoke test, and reports.
Related
Works with
Categories
Questions about Agentacct Workflow
What does Agentacct Workflow do?
A skill your agent uses when working in a repo with agentacct MCP configured, or when asked to track coding-agent work, smoke-test agentacct integrations, or report objective AI-agent task evidence. Agentacct Workflow is an agent skill from mikehasa/agentacct. Use when working in a repo with agentacct MCP configured, or when asked to track coding-agent work, smoke-test agentacct integrations, or report objective AI-agent task evidence.
When should I use Agentacct Workflow?
Agentacct Workflow fits situations like: working in a repo with agentacct MCP configured; asked to track coding-agent work; smoke-test agentacct integrations; report objective AI-agent task evidence.
How do I install Agentacct Workflow in Claude Code?
Run `npx skills add mikehasa/agentacct --skill agentacct-workflow -a claude-code`. Or copy the skill folder (integrations/hermes/agentacct-workflow in mikehasa/agentacct) into .claude/skills/agentacct-workflow in your project. Claude Code loads it when a task matches its description.
How do I install Agentacct Workflow in Codex?
Run `npx skills add mikehasa/agentacct --skill agentacct-workflow -a codex`. Or copy the skill folder (integrations/hermes/agentacct-workflow in mikehasa/agentacct) into .agents/skills/agentacct-workflow in your project. Codex loads it when a task matches its description.
Can I use Agentacct Workflow 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 mikehasa/agentacct --skill agentacct-workflow -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/agentacct-workflow, .gemini/skills/agentacct-workflow, .github/skills/agentacct-workflow and .opencode/skills/agentacct-workflow in your project.
What does Agentacct Workflow need to run?
SKILL.md names no scripts, command-line tools or credentials: Agentacct Workflow is instructions for the agent only.
Does Agentacct Workflow 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 Agentacct Workflow 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 Agentacct Workflow use?
Agentacct Workflow is published under the MIT licence (declared in SKILL.md). It allows redistribution, so the full SKILL.md is shown on this page.
How many tokens does Agentacct Workflow use?
About 1.6k tokens (SKILL.md is roughly 6.5k 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 Agentacct Workflow?
Skills that share tags, products or a category with Agentacct Workflow: Testing Scope MCP (daydreamlive/scope, 452 stars), Connect (activeing123/mcptoon, 214 stars), Authoring (activeing123/mcptoon, 214 stars) and Triage (activeing123/mcptoon, 214 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Agentacct Workflow?
mikehasa (a GitHub user) maintains it in mikehasa/agentacct, which has 765 GitHub stars. The repository was last updated on October 3, 2026.
Source: mikehasa/agentacct on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.