· 1 observation
Technical updates · 1
Package or technical metadata updated
View technical comparison →Codiedev v1.0.0
AI engineering metrics
From the developer
Codiedev Reports does not sell products or process payments.
How is engineering doing this month?
Developer declarations; not independently tested. Listing last checked Nov 4, 2026. Package observed Nov 3, 2026.
From the marketplace listing
Codiedev Reports answers engineering leaders' questions from their Codiedev reporting, right in the conversation. Ask how engineering is doing this month, whether AI-assisted pull requests actually merge faster, which repositories drive AI spend, how adoption is going on a team, or which models people use and how reliable they are. Who it's for: company admins, CTOs and team managers whose company uses Codiedev to capture AI coding sessions and pull requests. Admins see the whole company and can narrow to any team. Team managers see only their own team and never see spend. Engineers can't connect. What it can do: read delivery and cycle-time stages, the AI-vs-no-AI comparison with its classification coverage, velocity and the throughput forecast, daily activity and rate-limit pressure, adoption and skill reuse, model usage and reliability, capture coverage, and (admins only) spend versus the prior period, ROI, cost per merge, seats and the spend forecast. Limitations: it is read-only and can't change anything in Codiedev. It reports team and company aggregates, not individual session transcripts. Numbers come from stored rollups refreshed about hourly, over 30, 60 or 90-day windows, and only cover sessions Codiedev captured; every answer can quote capture coverage so you know how complete it is. A Codiedev account with the Admin or Team manager role is required.
Language: English · Automatically detected from descriptions.
Exact text from the indicated source. A mention alone does not establish support for your task.
Codiedev Reports answers engineering leaders' questions from their Codiedev reporting, right in the conversation. Ask how engineering is doing this month, whether AI-assisted pull requests actually merge faster, which repositories drive AI spend, how adoption is going on a team, or which models people use and how reliable they are. Who it's for: company admins, CTOs and team managers whose company uses Codiedev to capture AI coding sessions and pull requests. Admins see the whole company and can narrow to any team. Team managers see only their own team and never see spend. Engineers can't connect. What it can do: read delivery and cycle-time stages, the AI-vs-no-AI comparison with its classification coverage, velocity and the throughput forecast, daily activity and rate-limit pressure, adoption and skill reuse, model usage and reliability, capture coverage, and (admins only) spend versus the prior period, ROI, cost per merge, seats and the spend forecast. Limitations: it is read-only and can't change anything in Codiedev. It reports team and company aggregates, not individual session transcripts. Numbers come from stored rollups refreshed about hourly, over 30, 60 or 90-day windows, and only cover sessions Codiedev captured; every answer can quote capture coverage so you know how complete it is. A Codiedev account with the Admin or Team manager role is required.
· 1 observation
Package or technical metadata updated
View technical comparison →Find competitors to follow as you develop your plugin.
Keypup is the engineering analytics platform allowing software development teams to federate data from Git (e.g., GitHub) and project man...
Shared terms: engineering, cycle, model, report
Portable engineering skills with controlled AICtrl workflow execution
Shared terms: engineering, delivery, engineer, limitation
Ask your AI cost, runway, and guardrails from your real AtlasBurn data. Read-only.
Shared terms: cost, forecast, going, spend
Analyze calendar time, break it down by tags, clients and people, and log manual time entries in your TimeTackle workspace.
Shared terms: admin, limitation, month, per
Load and stress test AI and LLM endpoints from ChatGPT: build validated test configs, read back results, compare runs and generate CI per...
Shared terms: cost, metrics, pull, rate
--- name: get-started description: How to answer engineering-leadership questions with Codiedev Reports — which tool to call, how to scope to a team, and how to state confidence. --- # Codiedev Reports Codiedev Reports is read-only. It answers questions from the connected company's Codiedev reporting. It can't change anything, and it never returns individual session transcripts. ## Who is asking Call `list_teams` first when the user names a team, or when you need to know their access: - `access: "company_admin"` means the user sees the whole company and may pass any `teamId` from the list. - `access: "team_manager"` means the user sees only their own team. `canSeeSpend` is false, so don't call `get_finance` or `get_finance_detail`. Say spend is limited to company admins. ## Pick the tool | Question | Tool | | --- | --- | | "How is engineering doing?" or another broad health check | `get_overview` (trim with `sections`) | | "Is AI making us faster?" | `get_ai_impact` | | "Are we shipping faster or slower?" or a repo slowing down | `get_velocity` | | "When will we finish?" or predictability | `get_throughput_forecast` | | Usage patterns or hitting limits | `get_activity` | | Which models, errors or rate limits | `get_model_usage` | | Rollout or who is using it | `get_adoption` (`team_status`, `signals`, `skills`) | | How complete the data is | `get_capture_coverage` | | Spend, ROI or waste (admins) | `get_finance` | | Cost per merge, savings, what-if, seats, spend forecast (admins) | `get_finance_detail` | `windowDays` accepts 30 (the default), 60 or 90. ## Answering - Use only the numbers the tools return. When a field is null, missing, or `reason: "no_rollup_yet"`, say the data isn't available yet. Never fill in zeros. - For AI impact, quote `classificationCoveragePct`. For broad claims, quote capture coverage from `get_capture_coverage`. Every metric only counts captured sessions. - Durations are in milliseconds (`*Ms`). Convert them to hours or days for the reader. - Money is in USD.
Initial release: read-only engineering, AI impact, adoption, model usage and spend reporting for Codiedev admins and team managers.
Declared in the saved package. Remote tools may change independently.
Publisher declarations from the archived package. These are separate from our research and the live service's terms.
Package observed Nov 3, 2026.
plugin_asdk_app_6abecba03570819191dd8ec4223890de
Download plugin data (JSON)