Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add skills/mikehasa/agentacct/agentacct-workflownpx skills add mikehasa/agentacct --skill agentacct-workflowgit clone --depth 1 https://github.com/mikehasa/agentacctWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/mikehasa/agentacct/agentacct-workflow)<a href="https://agentmods.dev/skills/mikehasa/agentacct/agentacct-workflow"><img src="https://agentmods.dev/badge/skills/mikehasa/agentacct/agentacct-workflow.svg" alt="Measured on agentmods" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00040 | $0.01326 |
| Opus 5 | $0.00020 | $0.00663 |
| Sonnet 5 | $0.00008 | $0.00265 |
| Haiku 4.5 | $0.00004 | $0.00133 |
Grade A, and why
agentacct-workflow scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 4d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 152 lines — stays where its author put it; the contents beside it link to each section on GitHub.
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
- handoffs between agents
- repeated errors
- blockers
Sections are the work contract. Use section_status=started, checkpoint, completed, or blocked, and include client/session/turn identifiers when known.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 4d ago First seen · 152 lines · 40 tokens per session scan A 249e31c709cd
agentacct-workflow is a skill published in the GitHub repository mikehasa/agentacct (675 stars, last pushed 5d ago), licensed MIT. It adds 40 tokens to every session and 1,326 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
api-endpoints
Adding or changing API operations in @repo/operations. One source of truth (defineOperation + a Zod schema) becomes an HTTP endpoint, an OpenAPI operation, an MCP tool, TS + Python SDK methods, a latitude CLI command, and an in-process agent tool — descriptions and contracts must be written with all of these readers…
fix-datadog-issues
Find, triage, and fix production errors captured by Datadog Error Tracking, then open a PR. Use when asked to look at "Datadog issues/incidents/errors", "find and fix bugs from Datadog", investigate the most-frequent or newest production errors, or work a specific Datadog Error Tracking issue.
web-frontend
When to use: apps/web UI — routes, @repo/ui, TanStack Start server functions and collections, navigation (Link vs useNavigate), forms (useForm with createFormSubmitHandler + fieldErrorsAsStrings when Zod validation errors should appear on fields), Tailwind layout rules, design-system updates, and useEffect /…
database-postgres
Drizzle schema, repositories, RLS, SqlClient wiring, Postgres migrations, psql / reset, or platform mappers (toDomain / toInsertRow).
notifications
Multi-channel notifications. Adding a new notification kind, group, or channel; in-app + email delivery; per-user prefs; project-level gates; idempotency.
async-jobs-and-events
Queues and workers, domain event publishers, async notifications or projections, or not doing that work inside HTTP handlers.