validator-issue
Files structured GitHub bug reports for agent-validator when users ask to file, report, or open an issue for a suspected defect
Skill by Codagent-AI
Install
Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.
npx agentmarket install skill/codagent-ai-validator-issue
Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.
Get the weekly diff
The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.
About
Use cases: documents, agent-building
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
Permissions
What this skill can do and what it asks for, from its SKILL.md and code. Checked Oct 25, 2026.
- Tools
- No tools found
- Secrets
- None asked for
- Install scripts
- None found
Network hosts it talks to 1
codeload.github.com· found in install command
Files it touches
~/.claude/skills/validator-issue
Tools it pre-approves 3
From allowed-tools in SKILL.md: the agent may use these without asking you each time.
Bash,Read,Glob
What's inside
- Skill name
validator-issue- Description
- Files structured GitHub bug reports for agent-validator when users ask to file, report, or open an issue for a suspected defect
- License
- MIT
- Allowed tools
- Bash,, Read,, Glob
- Instructions
- 101 lines in SKILL.md · view on GitHub
Before installing
- Pre-approves some shell commands
Files (1)
- SKILL.md
SKILL.md (first lines)
# /validator-issue Collect runtime evidence, draft a structured GitHub issue for a suspected agent-validator bug, present a full preview, and file only after confirmation — unless invoked in auto-file mode. ## Step 1: Get the Bug Description and Mode **Check for auto-file mode**: If `$ARGUMENTS` begins with `--auto-file `, set auto-file mode to **on** and strip the prefix to get the remaining text as the bug description. Skip the confirmation step (Step 4) when auto-file mode is on. **Get the description**: - If a non-empty description remains after stripping any `--auto-file` prefix, use it as the bug description and proceed to Step 2. - If `$ARGUMENTS` is empty (or becomes empty after stripping), ask the user: > "Please describe the bug you encountered with agent-validator. What happened, what did you expect, and what were you trying to do?" Wait for their response before continuing. ## Step 2: Collect Evidence Read `.validator/config.yml` first to resolve `log_dir` (default: `validator_logs` if the field is absent or the file doesn't exist). Collect the following evidence. For each item, note if it is absent — do not fail if files are missing: 1. **Config file**: Read `.validator/config.yml` in full. 2. **Debug log (last 50 lines)**: Read the last 50 lines of `<log_dir>/.debug.log`. ```bash tail -n 50 <log_dir>/.debug.log ``` 3. **Execution state**: Read the full contents of `<log_dir>/.execution_state`. Record which files were found and which were absent. ## Step 3: Draft the Issue Draft a GitHub issue with the following structure: ``` ## Problem <A clear, concise description of the bug. Based on the user's description.> ## Steps to Reproduce <Step-by-step instructions to reproduce the issue. Infer from the description and evidence, or note "Not yet determined" if unclear.> ## Expected vs Actual **Expected:** <What should have happened> **Actual:** <What actually happened> ## Evidence > **Before including evidence, redact sensitive values**: remove or replace tokens, API keys, email addresses, and absolute local paths that may appear in config, logs, or state. Replace them with `[REDACTED]` or a generic placeholder. **Config (`.validator/config.yml`):** <Paste only relevant, non-sensitive config values. Redact tokens, emails, and absolute paths. Note "File not found" if absent.> **Debug log (last 50 lines of `<log_dir>/.debug.log`):** <Paste minimal relevant excerpt with sensitive values redacted. Note "File not found" if absent.> **Execution state (`<log_dir>/.execution_state`):** <Paste only fields needed to diagnose the bug; redact sensitive values. Note "File not found" if absent.> **Absent files:** <List any files that were not found, or "None"> ``` Choose a concise, descriptive title: `Bug: <short summary of the problem>`. ## Step 4: Show Preview and Confirm Present the full draft to the user — both title and body. **If auto-file mode is on**: Inform the user that the issue will be filed automatically (show the title and body), then proceed directly to Step 5 without asking. **Otherwise**, ask: > "Here is the draft issue. Shall I file it? (yes/no)" - If the user confirms: proceed to Step 5. - If the user declines: exit without creating an issue. Inform the user that no issue was filed. ## Step 5: File the Issue Write the issue body to a temporary file and pass it via `--body-file` to avoid shell interpolation issues with special characters in the body text: ```bash ISSUE_TITLE=$(cat <<'TITLE_EOF' Bug: <short summary> TITLE_EOF ) BODY_FILE=$(mktemp) cat > "$BODY_FILE" << 'ISSUE_EOF' <paste the full issue body here> ISSUE_EOF gh issue create --repo Codagent-AI/agent-validator --title "$ISSUE_TITLE" --body-file "$BODY_FILE" rm -f "$BODY_FILE" ``` Report the created issue URL to the user.
From Codagent-AI/agent-validator, MIT.
More from Codagent-AI/agent-validator
- 0.653score
validator-help
Codagent-AI
Diagnoses and explains validator behavior from runtime evidence for requests such as "why did validator fail", "explain validator behavior", "diagnose…
SkillAFreshness: A★ 30Claude Code +9 - 0.653score
validator-setup
Codagent-AI
Scans the project and configures checks and reviews for Agent Validator for requests such as "set up validator", "configure checks and reviews", or…
SkillAFreshness: A★ 30Claude Code +9 - 0.651score
capture-eval-issues
Codagent-AI
Capture noteworthy review violations for the eval framework.
SkillAFreshness: A★ 30Claude Code - 0.648score
validator-commit
Codagent-AI
Activates only for explicit validator-aware commit requests such as "commit with validator", "run validator then commit", "run checks before commit", or "skip…
SkillAFreshness: A★ 30Claude Code - 0.648score
validator-run
Codagent-AI
Activates only for explicit full-validator requests such as "run the validator", "run the gauntlet", "run validation", or validation before commit, push, or…
SkillAFreshness: A★ 30Claude Code +9 - 0.648score
validator-status
Codagent-AI
Shows a summary of the most recent validator session for requests such as "show validator status", "summarize last validator run", or "what failed in the last…
SkillAFreshness: A★ 30Claude Code +9 - 0.644score
validator-check
Codagent-AI
Activates only for explicit checks-only validation requests such as "run validator checks", "checks only", "check without reviews", or validation without AI…
SkillAFreshness: A★ 30Claude Code - 0.643score
validator-skip
Codagent-AI
Advances the validator execution state baseline without running checks for requests such as "skip validator", "advance validator baseline", or "mark current…
SkillAFreshness: A★ 30Claude Code +9
Signals
- Stars
- 30
- Forks
- 2
- Open issues
- 14
- Last commit (this folder)
- Mar 22, 2026 (7 months ago)
- Last release
- Sep 29, 2026 (1 month ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- MIT
- Repository
- github.com/Codagent-AI/agent-validator
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from Codagent-AI
- 0.653score
validator-help
Codagent-AI
Diagnoses and explains validator behavior from runtime evidence for requests such as "why did validator fail", "explain validator behavior", "diagnose…
SkillAFreshness: A★ 30Claude Code +9 - 0.653score
validator-setup
Codagent-AI
Scans the project and configures checks and reviews for Agent Validator for requests such as "set up validator", "configure checks and reviews", or…
SkillAFreshness: A★ 30Claude Code +9 - 0.651score
capture-eval-issues
Codagent-AI
Capture noteworthy review violations for the eval framework.
SkillAFreshness: A★ 30Claude Code - 0.648score
validator-commit
Codagent-AI
Activates only for explicit validator-aware commit requests such as "commit with validator", "run validator then commit", "run checks before commit", or "skip…
SkillAFreshness: A★ 30Claude Code - 0.648score
validator-run
Codagent-AI
Activates only for explicit full-validator requests such as "run the validator", "run the gauntlet", "run validation", or validation before commit, push, or…
SkillAFreshness: A★ 30Claude Code +9 - 0.648score
validator-status
Codagent-AI
Shows a summary of the most recent validator session for requests such as "show validator status", "summarize last validator run", or "what failed in the last…
SkillAFreshness: A★ 30Claude Code +9
Cite this page
validator-issue skill. Agent Mart. https://agentmart.dev/skills/codagent-ai-validator-issue (last updated 2026-10-24)