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/xamirhamza77/reverseops-skill/attack-chainnpx skills add xAmirHamza77/ReverseOps-Skill --skill attack-chaingit clone --depth 1 https://github.com/xAmirHamza77/ReverseOps-SkillWrote 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/xamirhamza77/reverseops-skill/attack-chain)<a href="https://agentmods.dev/skills/xamirhamza77/reverseops-skill/attack-chain"><img src="https://agentmods.dev/badge/skills/xamirhamza77/reverseops-skill/attack-chain.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 | $0.00043 | $0.05306 |
| Opus 5 | $0.00022 | $0.02653 |
| Sonnet 5 | $0.00009 | $0.01061 |
| Haiku 4.5 | $0.00004 | $0.00531 |
Grade F, and why
attack-chain scanned grade F with 4 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 3d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Asks for rootmediumPrivilege escalation
A mod that escalates privileges can change anything on the machine, not only the project.
# sudo abuse Reaches for credential fileshighPrivilege escalation
SSH keys, cloud credentials, git-credentials, .npmrc, /etc/shadow: reading these is how a config file becomes a credential leak.
echo "ssh-rsa AAAA..." >> /root/.ssh/authorized_keys Cloud metadata endpointhighServer-side request forgery
One request to 169.254.169.254 can return temporary IAM credentials.
curl http://169.254.169.254/latest/meta-data/iam/security-credentials/ Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -s "$url" | grep -oP '(api[_-]?key|secret|token|password)\s*[:=]\s*["\047][^"\047]+' How it starts
The opening of the file, as written. The whole thing — 658 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Attack Chain Orchestration Skill
ACTION REQUIRED (execute immediately after reading)
NOW: Read../field-journal/precedent-pentest.md— confirm this skill's operations are authorized routine operationsNOW: Create/update the case (../scripts/case-init.ps1) and completescope.md(../ops/scope-contract.md); no ACT unlessauth.status=grantedNOW: Plan the phases as the lead role (../ops/role-map.md), writing into specialist_rolesNEXT: Read../tool-index.mdto verify tool availability and actual pathsNEXT: If a tool is missing, call bootstrap — do not guess pathsACT: Walk the phase gates perreferences/lifecycle-checklist.md; updatetimeline.md+workitems.mdeach phase (../ops/timeline-workitem.md); promote discoveries to Evidence/Finding- Wrap-up: the
docs-generatorreport must include the Evidence chain
The command center for multi-stage attack-path planning and execution. When a task requires a full chain "from A to B", this Skill orchestrates the phases, coordinates sub-skills, and plans the attack path. Not "red team only" — any penetration scenario that needs cross-phase composition starts here.
When to Route to This Skill
The following scenarios must go through this Skill for full-chain planning before being dispatched to the specific sub-skills for execution:
| Scenario | Why orchestration is needed |
|---|---|
| "Run a complete penetration test for me" | Requires planning the full process from information gathering to reporting |
| "Get from the external network to the domain controller" | Spans perimeter breach -> privilege escalation -> lateral movement -> AD |
| "HW attack-defense exercise" | Requires a full attack chain + stealth + trace cleanup |
| "Assess this target's attack surface" | Requires multi-dimensional information gathering + path planning |
| "I got a webshell, what next" | Requires planning subsequent steps from the current foothold |
| "Plan my attack path" | Explicitly requires path orchestration |
| "How far can this vulnerability take me" | Requires assessing the vulnerability's chained exploitation value |
| "Bug Bounty continuous monitoring" | Requires an automated multi-phase pipeline |
| "Full internal network penetration" | Lateral movement + privilege escalation + domain attack combined |
| "Physical proximity penetration plan" | Physical access + internal penetration combined |
| "Supply chain attack path" | Cross-organization multi-hop attack |
| "Phishing + post-exploitation" | Initial access + follow-on exploitation combined |
What ships with it
3 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 3d ago First seen · 658 lines · 43 tokens per session scan F d4d7eeb2fba0
attack-chain is a skill published in the GitHub repository xAmirHamza77/ReverseOps-Skill (4 stars, last pushed 1mo ago), licensed MIT. It adds 43 tokens to every session and 5,306 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it F with 4 findings (asks for root, reaches for credential files, cloud metadata endpoint). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
vinkius-deploy
How to deploy MCP servers to Vinkius Edge using mcpfusion deploy. Use this skill whenever deploying, configuring remote settings, preparing an entrypoint for edge deployment, or troubleshooting deploy-related errors. Activate when the user says "deploy", "publish to edge", "mcpfusion deploy", "push to Vinkius"…
mcp-testing
MCP Testing Strategies with Vitest, Inspector, and Integration Tests.
mcp-inspector
MCP Protocol Inspection and Debugging with Inspector CLI.
publishing
Publishing and release workflow with semantic-release and GitHub Actions.
ingest-gradle-upgrade
Ingests a Gradle wrapper upgrade for this repository: reads the release notes, upgrade guides, and linked documentation for the version upgraded to, then updates this repo's own code/tooling and the shipped Gradle MCP skills (src/main/skills/) so everything stays accurate for that version. Positive Triggers (when to…
authoring-gradle-builds
Authoring and modifying Gradle build logic, including settings, plugins, dependencies, tasks, conventions, and upgrades. Activate when build files or plugins must change; use using-gradle for inspection or execution without build-definition edits.