Agent-estimate

v0.7.0 Feature

This release adds 3 notable features for engineering teams evaluating rollout.

Published 25d AI Agents & Assistants

View tool

✓ No known CVEs patched

Read the diff → Tool health → What is this tool? →

✓ No known CVEs patched in this version

Topics

ai-agents claude-code cli developer-tools effort-estimation estimation

+5 more

metr multi-agent pert python wave-planning

Affected surfaces

auth

Summary

AI summary

Updates What's New in v0.7.0, 40/60/90, and 15/25/40 across a mixed release.

Changes in this release

Type	Severity	Summary	CVE
Feature
Feature	Medium	Adds Frontend/UI task category with separate content-patch and page-build bands. Adds Frontend/UI task category with separate content-patch and page-build bands. Source: llm_adapter@2026-05-25 Confidence: high	—
Feature	Medium	Adds App-development task category with generic cold L-style prior and UI human-comparison multiplier. Adds App-development task category with generic cold L-style prior and UI human-comparison multiplier. Source: llm_adapter@2026-05-25 Confidence: high	—
Feature	Medium	Adds `3-round` review mode with a 35‑minute additive review tier. Adds `3-round` review mode with a 35‑minute additive review tier. Source: llm_adapter@2026-05-25 Confidence: high	—
Feature	Medium	Adds METR threshold entries for Opus 4.7 and GPT‑5.5; retains `opus_4_x` alias. Adds METR threshold entries for Opus 4.7 and GPT‑5.5; retains `opus_4_x` alias. Source: llm_adapter@2026-05-25 Confidence: high	—
Feature	Medium	Adds opt‑in structured audit logging via `AGENT_ESTIMATE_AUDIT_` environment variables. Adds opt‑in structured audit logging via `AGENT_ESTIMATE_AUDIT_` environment variables. Source: llm_adapter@2026-05-25 Confidence: high	—
Bugfix
Bugfix	Medium	Routes research‑grounded brainstorms to the research band instead of the flat brainstorm band. Routes research‑grounded brainstorms to the research band instead of the flat brainstorm band. Source: llm_adapter@2026-05-25 Confidence: high	—
Bugfix	Medium	Refreshes Claude `/estimate` skill to v0.7.0 parity with Codex slice (frontend/app_dev types, `3-round` review mode, refreshed METR keys). Refreshes Claude `/estimate` skill to v0.7.0 parity with Codex slice (frontend/app_dev types, `3-round` review mode, refreshed METR keys). Source: llm_adapter@2026-05-25 Confidence: high	—
Bugfix	Medium	Corrects Codex skill install path in `skills/estimate/README.md` to `.codex/skills/...`. Corrects Codex skill install path in `skills/estimate/README.md` to `.codex/skills/...`. Source: llm_adapter@2026-05-25 Confidence: low	—
Bugfix	Medium	Updates Codex model‑key alias to resolve to GPT‑5.5 METR threshold; retains GPT‑5.4 availability. Updates Codex model‑key alias to resolve to GPT‑5.5 METR threshold; retains GPT‑5.4 availability. Source: llm_adapter@2026-05-25 Confidence: low	—
Refactor	Medium	Updates repository structure: adds Makefile, scripts/preflight.py, and multi‑runtime `skills/estimate/` layout. Updates repository structure: adds Makefile, scripts/preflight.py, and multi‑runtime `skills/estimate/` layout. Source: llm_adapter@2026-05-25 Confidence: low	—

Full changelog

What's New in v0.7.0

Added

Frontend/UI task category with separate content-patch (15/25/40) and page-build (40/60/90) bands.
App-development task category with a generic cold L-style prior and app/UI human-comparison multiplier.
3-round review mode with a 35 minute additive review tier.
METR threshold entries for Opus 4.7 (current) and GPT-5.5; opus_4_x retained as a forward-compatible alias.
Opt-in structured audit logging via AGENT_ESTIMATE_AUDIT_* environment variables, emitting secret-scrubbed JSON events to stdout, stderr, or a file.

Changed

Research-grounded brainstorms now route to the research band instead of the flat brainstorm band.
Codex model-key alias now resolves to the GPT-5.5 METR threshold; GPT-5.4 remains available.
Corrected the Codex skill install path in skills/estimate/README.md to .codex/skills/....
Version bumped to v0.7.0 across package, plugin, action, issue template, and tests.
Claude runtime /estimate skill refreshed to v0.7.0 parity with the Codex slice (frontend/app_dev types, 3-round review mode, refreshed METR keys).
claude / claude_opus model-key aliases now resolve to opus_4_7 (Opus 4.7); opus_4_6 retained for backward compatibility.

This release also brings the repository structure up to date: a Makefile for dev shortcuts, a scripts/preflight.py pre-PR check, and the multi-runtime skills/estimate/ layout (shared spec + per-runtime Claude/Codex slices).

View diff on GitHub

Weekly OSS security release digest.

The CVE patches and breaking changes that affected production tools this week. One email, every Sunday.

No spam, unsubscribe anytime.

Share this release

Share on X Share on Bluesky

Track Agent-estimate

Get notified when new releases ship.

About Agent-estimate

All releases →