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/joaquimscosta/arkhe-claude-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/commands/joaquimscosta/arkhe-claude-plugins/double-check)<a href="https://agentmods.dev/commands/joaquimscosta/arkhe-claude-plugins/double-check"><img src="https://agentmods.dev/badge/commands/joaquimscosta/arkhe-claude-plugins/double-check/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/commands/joaquimscosta/arkhe-claude-plugins/double-check"><img src="https://agentmods.dev/badge/commands/joaquimscosta/arkhe-claude-plugins/double-check.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 | $0.00050 | $0.02036 |
| Opus 5 | $0.00025 | $0.01018 |
| Sonnet 5 | $0.00010 | $0.00407 |
| Haiku 4.5 | $0.00005 | $0.00204 |
Grade A, and why
double-check scanned grade A with 0 findings 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 10d ago.
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.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 216 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Double-Check Verification
Ultrathink!
Systematically verify the work just completed to ensure quality and completeness.
Parse arguments from: $ARGUMENTS
- If arguments contain
--deep, enable deep mode (multi-agent review) and strip--deepfrom focus area - Remaining text is the focus area (optional)
Step 1: Scope Detection
Establish what was completed and what ecosystem this project uses.
- Check git status: !
git status --short - Check staged changes: !
git diff --cached --stat - Check unstaged changes: !
git diff --stat - Check recent commits (if no uncommitted changes): !
git log -3 --oneline - Check todo list: Review any in-progress or recently completed todos
- Detect ecosystem: !
ls package.json Makefile pyproject.toml build.gradle build.gradle.kts pom.xml 2>/dev/null || true
Scope Summary: Summarize what will be verified (files changed, features affected, ecosystem detected). If the user specified a focus area, prioritize that scope.
Step 2: Backpressure Gates
Before reasoning-based review, run automated quality checks. Auto-detect available commands based on the ecosystem detected in Step 1.
Detection
Node.js (if package.json exists):
!node -e "try{const s=require('./package.json').scripts||{};console.log(JSON.stringify({test:s.test||null,lint:s.lint||s['lint:check']||null,typecheck:s.typecheck||s['type-check']||s.tsc||null,build:s.build||null}))}catch(e){}" 2>/dev/null
Python (if pyproject.toml exists):
!grep -c '\[tool\.pytest' pyproject.toml 2>/dev/null && echo "pytest detected" || true
!grep -c '\[tool\.ruff' pyproject.toml 2>/dev/null && echo "ruff detected" || true
!grep -c '\[tool\.mypy' pyproject.toml 2>/dev/null && echo "mypy detected" || true
JVM (if gradlew or pom.xml exists):
!test -f gradlew && echo "gradle" || (test -f pom.xml && echo "maven") || echo "none"
Makefile (if Makefile exists):
!grep -E '^(test|lint|check|build)[[:space:]]*:' Makefile 2>/dev/null | cut -d: -f1 || true
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.
- 10d ago First seen · 216 lines · 50 tokens per session scan A 250d6b254ade
double-check is a command published in the GitHub repository joaquimscosta/arkhe-claude-plugins (21 stars, last pushed 26d ago), licensed MIT. It adds 50 tokens to every session and 2,036 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other commands, from other repositories
p5-impl-refactor
Improves code quality without changing behavior. All tests must continue to pass.
p5-review-code
Checks code for quality, clean code, logic errors and test coverage. Delivers review findings with severity level.
analyze-pr
Review PR for quality, security, and coverage (GitHub/GitLab/Forgejo).
review-skills
Review changed skills: automated bash checks + 9 structural dimensions (D1-D9) + 5 intent checks (M1-M5). PASS/FAIL verdict. Fix in-place.
ship-ci-review-loop
Command "ship-ci-review-loop" from composio-community/awesome-claude-plugins, covering phase 4: ci & review monitor loop - reference, this phase is mandatory, pr auto-review process, why all comments matter and the monitor loop algorithm.
audit-project
Multi-agent code review with iterative improvement.