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 skills add Odalrick/estimate-maestro --skill recording-work-timegit clone --depth 1 https://github.com/Odalrick/estimate-maestroWrote 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/odalrick/estimate-maestro/recording-work-time)<a href="https://agentmods.dev/skills/odalrick/estimate-maestro/recording-work-time"><img src="https://agentmods.dev/badge/skills/odalrick/estimate-maestro/recording-work-time/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/odalrick/estimate-maestro/recording-work-time"><img src="https://agentmods.dev/badge/skills/odalrick/estimate-maestro/recording-work-time.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00056 | $0.01429 |
| Opus 5 | $0.00028 | $0.00714 |
| Sonnet 5 | $0.00011 | $0.00286 |
| Haiku 4.5 | $0.00006 | $0.00143 |
Grade A, and why
recording-work-time 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 8d 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 — 115 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Recording work time
Strict and mechanical. Do these things at these moments. No judgement calls, no interpretation, no estimation reasoning — this skill exists so that referencing it does not pull estimation ideas into a working session.
Starting an effort
start_effort(title, kind, plan_path, summary_text, optimistic, likely, pessimistic, rationale, work_slices) creates the effort and takes the plan's
slice titles up front, as work_slices, a list of titles. This is not
incidental: the initial slice count is what makes later drift measurable.
Do not create the effort with an empty slice list and add slices afterwards
to get to the plan's real inventory — that throws away the baseline. Once the
effort is under way, add_slice is for slices that were not in that original
list — scope growth, not initial setup.
When to clock in
- Starting work on a slice:
clock_in(effort, work_slice). - Starting effort-level work with no slice — a design conversation, a
retrospective:
clock_in(effort). - A meeting that is part of the work:
clock_in(effort, kind="meeting", internal=<people we pay for, including the user>, external=<people we do not>, participants=<names, if known now>).
clock_in refuses when an interval is already open. That refusal is correct;
clock out first rather than working around it.
clock_in also refuses when work_slice is given but is not a live slice on
that effort — dropped, or simply mistyped — raising UnknownSlice. A stale
slice identifier is a plausible mistake mid-effort; treat the refusal as a
prompt to check the identifier, not as something to route around. A closed
slice is still clockable, deliberately: a merged pull request can still need
post-merge fixes, and that time belongs to the slice it came from.
If the names were not to hand when clocking into the meeting, participants
can be left out and attached later — or corrected — with
annotate_interval(effort, interval, internal=, external=, participants=, note=). It works on any interval, not only meetings, and is also the way to
attach a note after the fact.
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.
- 8d ago First seen · 115 lines · 56 tokens per session scan A fc72db3f3214
recording-work-time is a skill published in the GitHub repository Odalrick/estimate-maestro (0 stars, last pushed 14d ago), licensed MIT. It adds 56 tokens to every session and 1,429 once invoked, about $0.0003 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 2026-08-31.
Other skills, from other repositories
things-mac
Manage Things 3 via the things CLI on macOS (add/update projects+todos via URL scheme; read/search/list from the local Things database). Use when a user asks Otto to add a task to Things, list inbox/today/upcoming, search tasks, or inspect projects/areas/tags.
gsd-ns-manage
Route to the appropriate management skill based on the user's intent. gsd-config (settings + advanced + integrations + profile) and gsd-workspace (new + list + remove) are post-#2790 consolidated entries.
slack-tools
Slack workspace management and automation specialist.
triage-inbox
Triage academic email and calendar (Gmail / Google Calendar via the session's MCP) into a prioritized digest plus a referee-obligations tracker — classifying referee requests, R&R and editor correspondence, co-author threads, seminar and conference invites, and grant/admin deadlines, and proposing a human-gated action…
ceo-setup
One-time onboarding for the executive/manager commitment workflow — delegation-heavy, meeting prep, decision capture, morning and evening digests. Creates a commitments project and installs two dashboard widgets. After successful setup this skill is excluded from selection until the marker file is deleted.
service-desk
Runs the IT service desk — intake, triage, prioritization, escalation, knowledge, and the metrics that improve service rather than distort it. Use this to set up or fix a service desk, design ticket priority and escalation, reduce repeat contacts, structure a knowledge base, or work out why a desk hitting its targets…