DevClocked
by devclocked · Time and token tracking for human and AI-agent engineering work
BenchRank score
Screenshots of DevClocked
Homepage
Overview
DevClocked tracks engineering time and AI token spend at the source through VS Code and Cursor extensions, a macOS menubar app, CLI capture, Claude Code and Codex plugins and an MCP server. It splits sessions into coding, config and debug time, records agent runs and cost, and links them to commits, PRs and Linear issues. Paid plans add timesheets, invoicing and team dashboards.
- Best for
- Solo developers, teams and agencies who need time, agent-run and token data tied to shipped work.
- Pricing
- Free plan with a 7-day full-access trial, then Pro at $16/month, Ultra at $26/month or Business at $29 per seat/month, with annual billing saving two months.
- Runs on
- WebmacOSCLI
Strengths and trade-offs
Strengths
- Captures IDE, terminal, browser and agent sessions automatically
- Token and cost broken down by project, session and agent run
- No screenshots or keystroke logging on any plan
- Automatic capture on every surface included on the free plan
Trade-offs
- Free plan is capped at 1 repository and 7 days of history
- Desktop app is macOS only; no Windows or Linux app shown
- Jira issue linking is described as landing after Linear
- Enterprise SSO, SAML/SCIM and data residency are still coming
How DevClocked markets itself
A structured read of the promise, proof and page design on DevClocked’s captured homepage.
Homepage capture
“See what you actually shipped.”
- Angle: Outcome / benefit-led
- Hero: Terminal / CLI
Pricing
Published plans and prices from DevClocked’s own pricing page.
How this score is made up
Each dimension is scored out of 100 and combined into the headline score using fixed weights.
MCP support
Whether an agent can drive the product through the Model Context Protocol, and how much setup that takes.
API quality
Public API surface: machine-readable spec, official SDKs, documented auth, errors, rate limits and versioning.
Documentation
Publicly reachable docs — coverage, freshness, code samples and machine readability.
Agent friendliness
How readable the site is to an automated client: llms.txt, structured data, server-rendered content, crawler access.
Pricing transparency
Whether real prices are published, self-serve signup exists, and usage costs are knowable without a sales call.
Changelog
A public, dated record of what shipped and when — the clearest signal that a product is still alive.
Marketing site structure
Whether the site answers a buyer's questions: clear positioning, the pages that matter, and accessibility.
Page speed
How fast the site loads for real visitors: Chrome UX Report 75th-percentile LCP, INP and CLS, with a Lighthouse mobile run standing in where a site has too little traffic for field data.
Operational trust
Status page and incident history, security disclosure, compliance and data-processing documentation.
Measured, but not part of the score
Useful to know, but not a mark for or against the product — so these do not affect the ranking.
Openness
Source availability, self-hosting, data export and open standards. Scored and shown, but not part of the composite — paid SaaS is not worse for being paid SaaS.
Maintenance
Release cadence and repository activity. Scored and shown, but not part of the composite — it is only measurable for open repositories.
This doesn’t look right — report a problem with DevClocked’s score
Where this comes from
The DevClocked pages BenchRank reads when it scores the product — its documentation, release notes, status and security pages, and its repository where there is one.
Who maintains this profile
Claimeddevclocked maintains the descriptive parts of this profile. The score and the ranking are ours, and claiming does not change them.