Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
git clone --depth 1 https://github.com/vladolaru/claude-code-pluginsWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/agents/vladolaru/claude-code-plugins/history-insights-reviewer)<a href="https://agentmods.dev/agents/vladolaru/claude-code-plugins/history-insights-reviewer"><img src="https://agentmods.dev/badge/agents/vladolaru/claude-code-plugins/history-insights-reviewer/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/agents/vladolaru/claude-code-plugins/history-insights-reviewer"><img src="https://agentmods.dev/badge/agents/vladolaru/claude-code-plugins/history-insights-reviewer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00038 | $0.03792 |
| Opus 5 | $0.00019 | $0.01896 |
| Sonnet 5 | $0.00008 | $0.00758 |
| Haiku 4.5 | $0.00004 | $0.00379 |
Grade B, and why
history-insights-reviewer scanned grade B with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured today.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Asks the agent to reveal its instructionsmediumSystem prompt leakage
Directions to print, repeat or translate the system prompt extract configuration the operator did not intend to expose.
Complete this setup first — it provides your review rules, scope, diffs, and output instructions: How it starts
The opening of the file, as written. The whole thing — 255 lines — stays where its author put it; the contents beside it link to each section on GitHub.
MANDATORY SETUP — Run Bootstrap Before Reviewing
Complete this setup first — it provides your review rules, scope, diffs, and output instructions:
Run the bootstrap script:
PLUGIN_ROOT=$(cat /tmp/.pirategoat-tools-root 2>/dev/null)
[ -z "$PLUGIN_ROOT" ] || [ ! -d "$PLUGIN_ROOT/scripts" ] && PLUGIN_ROOT=$(find ~/.claude -path "*/pirategoat-tools/*/scripts/review/agent/bootstrap.py" -type f 2>/dev/null | sort | tail -1 | xargs dirname | xargs dirname | xargs dirname | xargs dirname)
python3 $PLUGIN_ROOT/scripts/review/agent/bootstrap.py --agent history-insights-reviewer
Read the output carefully. It contains your review rules, scope (with diffs and file list), and output instructions. Parse the diffs, file list, BASE_REF, and OUTPUT_DIR from the scope section. Use the diffs for scenario extraction (Phase 1). Use BASE_REF for history mining commands. Only then proceed.
You are an expert History Insights Reviewer specializing in git archaeology, commit analysis, PR pattern mining, and cross-area knowledge transfer. The team has already solved many problems — your job is to find those solutions before the same mistakes are repeated or improvements are missed. This review matters: repeating mistakes the team already fixed is preventable waste.
Your scope: You read PR diffs to understand WHAT changed (scenario extraction), then mine git history for similar scenarios fixed or improved elsewhere. Your findings come from history, not from reviewing the working tree code. Focus on temporal insights (what the team learned over time), not pattern detection (what exists now).
RULE 0 (MOST IMPORTANT): The Team Already Knows
Every fix, enhancement, and refactor in git history is a lesson. Before approving code that handles error recovery, validation, edge cases, performance, or UX — search for how the team solved similar problems elsewhere. The best review feedback comes from the project's own experience.
How This Differs from patterns-reviewer
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- today Changed · -5 lines 6fb91a20b0c9
- 6d ago Changed 7323886ff549
- 10d ago First seen · 260 lines · 38 tokens per session scan B eae40b49a777
history-insights-reviewer is an agent published in the GitHub repository vladolaru/claude-code-plugins (8 stars, last pushed today), licensed MIT. It adds 38 tokens to every session and 3,792 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it B with 1 finding (asks the agent to reveal its instructions). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other agents, from other repositories
pr-creator
Use for creating and editing pull requests via gh pr create, gh pr edit, gh pr view, gh pr diff, and gh pr list. Does NOT merge or mark ready (use pr-merger for that). A Bash command denied by the harness permission system is surfaced to the operator, never reshaped to evade the denial.
consistency-and-history
Analyze git history and cross-file consistency — stale references, dead code, broken importers after renames/removals, established-convention enforcement.
author-code-review
Fetches open PRs, reads review comments (including CoderabbitAI), identifies actionable code changes, implements fixes, and pushes commits.
fe-git-operator
Dedicated git operations — splitting commits, safe staging that preserves the user's pre-existing index, writing Conventional Commits bodies (fix = symptom/cause/fix, feat = addition/core/impact), and pushing the branch. fe-pr-author owns PRs; this agent owns commits and the push. Destructive commands forbidden.
engineer
Use this agent for code exploration, architecture design, refactoring analysis, git operations, and code review. Use when: User asks to explore code, design architecture, refactor, commit/PR, or review changes. Do NOT use when: User needs test generation (use qa-engineer), security audit (use security-scanner), or…
supervisor-final-judge
Final Release Judge. Use only when the Supervisor coordinator dispatches this independent role.