AutoGineer
Generated banner for Adjudicate Regression
Generated logo for Adjudicate Regression

Adjudicate Regression

Trail of BitsOfficialPublished by Trail of Bits

  • Skill
  • Review and audit
  • Security
  • CC-BY-SA-4.0
  • No issues found
Download ZIP

From the author

Use when deciding whether source and live reproduction evidence establish a new regression or an exclusion.
— the description by Trail of Bits

AutoGineer summary

Written by AutoGineer from the skill’s own files, not by the author

The adjudicate-regression skill provides a rigorous framework for evaluating evidence to determine if a software change has introduced a new regression. It requires the agent to analyze source code, reproduction packages, and logs to distinguish between genuine regressions, latent bugs, intentional changes, or unsupported expectations. The process emphasizes independent verification and evidence-based decision-making, ensuring that findings are properly categorized and documented in a sealed record.

What it does

  • Verifies evidence seals and inspects source, setup, and logs for claimed defects.
  • Assesses whether a specific change introduced the defect or if it is a pre-existing issue.
  • Validates reproduction and replay results against live interfaces.
  • Assigns severity and likelihood to confirmed regressions.
  • Identifies exclusions or unresolved gaps when evidence is insufficient.
  • Produces a sealed decision record with cited evidence for every conclusion.

When to use it

  • When you need to determine if a reported defect is a new regression or an exclusion.
  • When evaluating candidate evidence against frozen sources and reproduction packages.
  • When you need to deduplicate multiple claims based on a shared root cause.
  • When you must distinguish between a new regression and a latent, pre-existing bug.

Advantages

  • Ensures consistent and rigorous evaluation of regression claims.
  • Prevents misclassification of latent bugs as new regressions.
  • Provides a clear, evidence-backed audit trail for every decision.
  • Standardizes the reporting of unresolved gaps and missing evidence.

Usage examples

“Adjudicate the regression claim for the provided candidate and reproduction package.”
The agent reviews the evidence, verifies the reproduction against live interfaces, and returns a status of complete with a sealed decision.json confirming or excluding the regression.
“Determine if these two reported issues share a root cause.”
The agent analyzes the provided candidates and mappings to establish if they are duplicates or distinct issues, preserving the integrity of the regression report.

Install

  1. Download the skill as a ZIP:

    https://autogineer.com/agent-skills/trailofbits/adjudicate-regression/download

  2. Unzip it into the cross-client skills folder of your project:

    mkdir -p .agents/skills && unzip adjudicate-regression.zip -d .agents/skills

Documentation by Trail of Bits

Adjudicate evidence

When to Use

Input: candidate, frozen sources, available reproduction/replay packages and registry assignment. Use a fresh context distinct from the reproducer and replayer. Early exclusions may lack experiments. Follow project guidance before target work.

When NOT to Use

Producing missing evidence; return the gap to the caller.

Decide

  1. Read the standard, labels and file contract. Verify seals. Inspect source, setup, PoC, actual logs and security assumptions, not only summaries.

  2. Identify the claimed defect and assess whether the change introduced it. Rule out incomplete fixes, latent/pre-existing bugs, intentional changes, unsupported expectations and unreachable scenarios with cited evidence. Establish attacker access and applicable protections for security findings.

  3. Confirm only when reproduction and independent replay ran the same PoC/input against live S0/S1 through real interfaces, showing correct behavior before and failure afterward. Explain supported behavior, reachability and patch causality. Assign severity/likelihood with reasons.

  4. Otherwise select an evidenced exclusion or UNRESOLVED; state what remains unproved. For UNRESOLVED, put the standard's concise paragraph separating observed gaps, plausible explanations and resolving checks in reason so reports retain it. Incomplete fixes and existing bugs stay outside regression totals. Check known findings/issues/PRs before claiming novelty; report unknown if unavailable.

  5. For requested deduplication, establish whether supplied candidates share a root cause. Preserve change mappings; never deduplicate unresolved claims into confirmation.

  6. Write and seal decision.json; cite evidence for every conclusion. Record any blocker preventing adjudication.

Report Back

Keep detailed reasoning in the sealed package. Return only:

  • Status: complete or blocked, matching the record.

  • Record: sealed decision.json path, or why none was produced.

  • Result: outcome and one-sentence reason.

  • Gap: missing evidence or required caller action, if any.

A completed decision may be UNRESOLVED; task status and finding outcome differ.

Rationalizations to Reject

  • “S0 passes and S1 fails”: exposing an existing defect is a latent bug.

Files

Requirements and compatibility

Works with: Claude Code, Claude apps, OpenAI Codex, GitHub Copilot, Cursor, Gemini CLI, Kiro, OpenCode, Goose, Amp, Roo Code, JetBrains Junie, Factory Droid, Devin (ex-Windsurf), Mistral Vibe, OpenHands, Letta

“Works with” means the tool reads the open Agent Skills format; a skill written for one tool may use features others lack.

Security

No issues found by our static scan· No issues found

A static scan is not a guarantee. Skills are third-party content: review a skill before you let an agent use it.

Attribution and licence

Published by
Trail of Bits
Publisher
Trail of Bits (Official)
Source
trailofbits/skills · plugins/regression-hunt/skills/adjudicate-regression · commit e4dd0bb
Licence
Creative Commons Attribution-ShareAlike 4.0 International (redistribution allowed)
  • LICENSE (added by AutoGineer from LICENSE)
  • ATTRIBUTION.md (written by AutoGineer)
Synced

AutoGineer is not affiliated with or endorsed by Trail of Bits or Trail of Bits.

Download ZIP

The ZIP holds the skill’s files, its licence files and an ATTRIBUTION.md. Download adjudicate-regression.zip