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.
npx agentmods add skills/geoloeg-ist/agents-reverse-engineer/are-implementnpx skills add GeoloeG-IsT/agents-reverse-engineer --skill are-implementgit clone --depth 1 https://github.com/GeoloeG-IsT/agents-reverse-engineerWrote 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/skills/geoloeg-ist/agents-reverse-engineer/are-implement)<a href="https://agentmods.dev/skills/geoloeg-ist/agents-reverse-engineer/are-implement"><img src="https://agentmods.dev/badge/skills/geoloeg-ist/agents-reverse-engineer/are-implement.svg" alt="Measured on agentmods" 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 | $0.00014 | $0.00546 |
| Opus 5 | $0.00007 | $0.00273 |
| Sonnet 5 | $0.00003 | $0.00109 |
| Haiku 4.5 | $0.00001 | $0.00055 |
Grade A, and why
are-implement scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 5d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
Execute the implementation phase with and without ARE documentation to measure impact.
Steps
-
Read version: Read
.claude/ARE-VERSION→ store as$VERSION. Show the user:agents-reverse-engineer v$VERSION -
Run the implement command:
npx agents-reverse-engineer@$VERSION implement --backend claude $ARGUMENTSNote: When
--plan-id <id>is provided, the task description is loaded from the stored plan — no need to pass it explicitly. -
Wait for completion — the command runs two sequential AI implementation sessions (without docs, then with docs) and outputs a comparison table.
-
On completion, summarize the comparison results:
- Implementation metrics (files created/modified, lines added/deleted)
- Test results (if
--run-testswas used) - Build and lint results (if
--run-build/--run-lintwas used) - Cost and latency comparison
- Quality evaluation scores (if
--evalwas used)
This re-uses branches created by /are-plan and executes the implementation in both worktrees:
- With ARE docs: Full documentation available during implementation
- Without ARE docs: Source code only (ARE artifacts stripped)
The comparison measures how much ARE documentation improves implementation quality.
Options:
--eval: Run AI quality evaluator on both implementations--eval-model <name>: Model for the evaluator (default: same as --model)--model <name>: AI model to use for implementation--task-slug <slug>: Reference existing plan by slug (default: auto-generate from task)--plan-id <id>: Reference existing plan by ID (shown byare planon completion)--run-tests: Execute test suite and include results in metrics--run-build: Execute build and verify success--run-lint: Run linter and include error/warning counts--dry-run: Show what would happen without executing--list: List all saved implementation comparisons--show <id>: View a previous comparison by date--force: Overwrite existing branches for the same task--debug: Show verbose AI execution details
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.
- 5d ago First seen · 52 lines · 14 tokens per session scan A c8db8ddcf367
are-implement is a skill published in the GitHub repository GeoloeG-IsT/agents-reverse-engineer (20 stars, last pushed 28d ago), licensed MIT. It adds 14 tokens to every session and 546 once invoked, about $0.0001 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 skills, from other repositories
audit-onboarding-proposal
Independently audit a brownfield onboarding transcript, operational map, or exact proposed documentation patch before application. Use when a fresh reviewer must verify an $onboard-repository first pass, distinguish environment-caused Unknowns from reasoning defects, score its safety and evidence gates, or run a…
engineering-wisdom
Provide an explicitly requested, repository-grounded engineering review using contextual heuristics for code clarity, SOLID and design, testing, refactoring, architecture, and professional practice. Use only when the user invokes $engineering-wisdom or explicitly asks for this installed engineering-wisdom pack; do not…
proxmox-full
Complete Proxmox VE hypervisor management via REST API - VMs, containers, snapshots, backups, storage.
red-team-adversarial
Adversarial security and resilience analysis — auto-triggered during /review and /test based on task classification. Provides attack surface analysis, boundary testing, auth bypass attempts, dependency chain attacks, and Beast Mode stress testing.
marketing-copy
Write outbound promotional copy for a product or project: launch and update posts for community platforms and social media, store page descriptions and short blurbs, landing page headlines and calls to action, press-style announcements, and the naming of a product for another language or market. Covers what may be…
verification-before-completion
Enforce "no evidence = no completion"; run Gate Function verification before declaring done.