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 skills add grahama1970/agent-skills --skill hackgit clone --depth 1 https://github.com/grahama1970/agent-skillsWrote 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/grahama1970/agent-skills/hack)<a href="https://agentmods.dev/skills/grahama1970/agent-skills/hack"><img src="https://agentmods.dev/badge/skills/grahama1970/agent-skills/hack/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/skills/grahama1970/agent-skills/hack"><img src="https://agentmods.dev/badge/skills/grahama1970/agent-skills/hack.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 | $0.00023 | $0.06539 |
| Opus 5 | $0.00012 | $0.03270 |
| Sonnet 5 | $0.00005 | $0.01308 |
| Haiku 4.5 | $0.00002 | $0.00654 |
Grade A, and why
hack 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 9d 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.
The source is not reproduced here
No licence file
A repository with no LICENSE is all rights reserved by default, so the body is not copied here. The metadata, the measurements and the link are.
What ships with it
60 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.
- __init__.py 431 B runs code
- .ask/browser-oracles.yaml 35 B
- advanced_sanity.sh 1.4 KB runs code
- audit_receipts.py 6.9 KB runs code
- battle_mode.py 2.4 KB runs code
- cache.py 5.9 KB runs code
- cascade_integration.py 20 KB runs code
- chaos_campaign.py 32 KB runs code
- chaos.py 4.5 KB runs code
- commands.py 27 KB runs code
- compose_policy.py 25 KB runs code
- config.py 4.6 KB runs code
- container_manager.py 9.2 KB runs code
- correlation.py 4.6 KB runs code
- docker/Dockerfile.security 1.3 KB
- docker/offline-security.yml 3.2 KB
- docs/01_RESEARCH.md 1.8 KB
- docs/02_RESEARCH.md 3.0 KB
- docs/HACK_OPENCLAW_CLOSURE_NOTES.md 3.0 KB
- docs/HACK_THREE_LANE_INFOGRAPHIC_DESIGN_BRIEF.md 12 KB
- docs/PROJECT_KNOWLEDGE.md 2.7 KB
- docs/REMEDIATION.md 2.4 KB
- docs/request.md 892 B
- env.py 704 B runs code
- evolutionary_campaign.py 99 KB runs code
- exploit_writer.py 6.6 KB runs code
- fixtures/agentic_eval.json 9.7 KB
- fixtures/authorization/valid-local.json 1.5 KB
- fixtures/compose-policy/malicious/cap-device.yml 110 B
- fixtures/compose-policy/malicious/docker-socket.yml 103 B
- fixtures/compose-policy/malicious/env-file.yml 74 B
- fixtures/compose-policy/malicious/extra-hosts.yml 92 B
- fixtures/compose-policy/malicious/host-bind.yml 79 B
- fixtures/compose-policy/malicious/host-network.yml 63 B
- fixtures/compose-policy/malicious/outside-build.yml 81 B
- fixtures/compose-policy/malicious/privileged.yml 61 B
- fixtures/compose-policy/malicious/public-port.yml 75 B
- fixtures/compose-policy/malicious/source-write.yml 75 B
- fixtures/compose-policy/safe/docker-compose.yml 182 B
- fixtures/compose-policy/safe/public/index.html 13 B
- fixtures/hack-scan-request/evidence/web-result.md 231 B
- fixtures/hack-scan-request/source-packet.json 543 B
- fixtures/hack-scan-request/valid.json 1.2 KB
- fixtures/proof-authority/authorization-manifest.json 128 B
- fixtures/proof-authority/observed-signal.json 143 B
- fixtures/proof-authority/probe-spec.json 103 B
- fixtures/proof-authority/replay-receipt.json 177 B
- fixtures/proof-authority/replay-spec.json 93 B
- fixtures/proof-authority/runtime-state.json 95 B
- fixtures/proof-authority/scan-request.json 113 B
- fixtures/sterile-environment/reject-undeclared/docker-compose.yml 130 B
- fixtures/sterile-environment/safe/docker-compose.yml 392 B
- hack_scan_request.py 13 KB runs code
- hack.py 5.8 KB runs code
- install_tools.sh 821 B runs code
- local/compose-policy-1110-20260729/compose-policy-receipt.json 1.3 KB
- local/compose-policy-1110-20260729/matrix-summary.json 2.8 KB
- local/compose-policy-1110-20260729/proof-summary.json 1.3 KB
- local/compose-policy-1110-20260729/sanitized-compose-config-readback.json 1.0 KB
- local/compose-policy-1110-20260729/sanitized-compose.yml 655 B
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.
- 9d ago First seen · 701 lines · 23 tokens per session scan A 6864715a6d37
hack is a skill published in the GitHub repository grahama1970/agent-skills (6 stars, last pushed today), with no licence file. It adds 23 tokens to every session and 6,539 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 2026-09-03.
Other skills, from other repositories
deploy-docker-compose
Run the Omnigent server as a Docker compose stack (server + Postgres) on any Docker host — your laptop, a VPS, EC2 by hand, or as the base layer of any container-platform deploy. Invoke when the user wants to build the image, bring up the compose stack, debug the stack on a host they already have, or extend the stack…
compute-env-setup
Set up a reproducible Feynman compute environment for research jobs. Use when a task needs Python/R packages, GPU libraries, containers, Modal, SSH, caches, or managed model runtime setup.
securing-kubernetes-on-cloud
This skill covers hardening managed Kubernetes clusters on EKS, AKS, and GKE by implementing Pod Security Standards, network policies, workload identity, RBAC scoping, image admission controls, and runtime security monitoring. It addresses cloud-specific security features including IRSA for EKS, Workload Identity for…
detecting-privilege-escalation-in-kubernetes-pods
Detect and prevent privilege escalation in Kubernetes pods by monitoring security contexts, capabilities, and syscall patterns with Falco and OPA policies.
implementing-rbac-hardening-for-kubernetes
Harden Kubernetes Role-Based Access Control by implementing least-privilege policies, auditing role bindings, eliminating cluster-admin sprawl, and integrating external identity providers.
docker-socket-mount
Docker / containerd socket mounted into a container → host RCE. Common in CI runners, GitOps controllers (ArgoCD, Flux), and 'Docker-in-Docker' setups. Single-command escape via docker run --rm --privileged -v /:/host alpine chroot /host.