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 Hmbown/Wizards-of-the-Ghosts --skill forcecagegit clone --depth 1 https://github.com/Hmbown/Wizards-of-the-GhostsWrote 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/hmbown/wizards-of-the-ghosts/forcecage)<a href="https://agentmods.dev/skills/hmbown/wizards-of-the-ghosts/forcecage"><img src="https://agentmods.dev/badge/skills/hmbown/wizards-of-the-ghosts/forcecage/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/hmbown/wizards-of-the-ghosts/forcecage"><img src="https://agentmods.dev/badge/skills/hmbown/wizards-of-the-ghosts/forcecage.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 | $0.00064 | $0.01102 |
| Opus 5.5 | $0.00026 | $0.00441 |
| Sonnet 5.5 | $0.00013 | $0.00220 |
| Haiku 4.5 | $0.00006 | $0.00110 |
Grade A, and why
forcecage 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 1mo 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 — 87 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Forcecage
Contain untrusted code, agents, or operations inside a tested cage before anything leaves it.
Sigil
+-------------+
| x x |
| .-. |
| (###) |
| `-' |
| x x |
+-------------+
What This Skill Does
Forcecage creates a pre-tested containment boundary around a subject that has not yet run. It is not about stopping, pausing, or muting something already in motion. The cage is built first, self-tested, then the subject enters. The operator watches from outside and decides whether to release. In this grimoire, Forcecage is treated as a literal spell with a prototype delivery profile. Canonical reference input: Forcecage (spell).
When To Use
- Trigger this spell when the user asks to contain, cage, sandbox, isolate, or box untrusted/experimental/dangerous code, agents, tools, or operations before they run. Look for:
- Explicit boundary requests: "only inside", "cannot reach", "blocked from", "disposable", "throwaway"
- Subject types: untrusted code, third-party binaries, experimental agents, red-team samples, vendor scripts, refactor tools
- Observation intent: "watch what it does", "log denied actions", "see what it reaches for", "observe from outside"
- Release conditions: "before we trust it", "prove itself first", "step-down after", "authorize descent"
Prerequisites
- No extra runtime dependencies beyond Hermes Agent and the normal toolset for this session.
Procedure
- Restate the target, the success condition, and any no-touch boundaries before taking action.
- Define the boundary: List exactly what the subject CAN access (specific files, URLs, namespaces) and what is BLOCKED (network egress, credential stores, process spawning, writes outside a target directory). Default to deny-all.
- Build and self-test the cage: Create the containment environment (disposable workspace, copied repo, fake namespace, egress-blocked container). Run probes to confirm blocked surfaces actually block. A cage that hasn't been challenged is not trusted.
- Run the subject inside, observe from outside: Execute the subject within the boundary. Collect audit logs of denied actions, attempted escapes, and resource access patterns. The operator stays outside the cage.
- Set release condition before descent: Define what must be true for the subject to leave the cage (e.g., zero unauthorized writes, specific test pass, operator sign-off). If the condition is not met, the subject stays cage-only. If met, authorize a single step-down to a less restricted environment.
- Stop for explicit confirmation before taking a live action that changes access, triggers an alert, or touches a real system boundary.
- Package the result as the deliverables below, with confidence, assumptions, and unresolved risk called out explicitly.
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.
- 1mo ago First seen · 87 lines · 64 tokens per session scan A 58755d3bdb0b
forcecage is a skill published in the GitHub repository Hmbown/Wizards-of-the-Ghosts (112 stars, last pushed 6mo ago), licensed CC0-1.0. It adds 64 tokens to every session and 1,102 once invoked, about $0.0003 per session on Opus 5.5. 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
hermes-s6-container-supervision
Modify or debug s6 services in the Hermes Docker image.
docker-management
Manage Docker containers, images, volumes, and Compose.
docker-management
Manage Docker containers, images, volumes, networks, and Compose stacks — lifecycle ops, debugging, cleanup, and Dockerfile optimization.
tooluniverse-nfcore-pipelines
Run real end-to-end bioinformatics pipelines (nf-core rnaseq, sarek, atacseq) via Nextflow + Docker/Singularity, for raw FASTQ/BAM data — either local files or public GEO/SRA datasets. Use when someone asks to "run RNA-seq alignment", "quantify gene expression from FASTQs", "call germline or somatic variants from my…
remotion-create
Creating a new Remotion video.
qa-investigation
Investigate a specific test failure to its root cause and document the why. Detects whether a failing test is flaky (intermittent) or a deterministic bug during reproduction. Use when a test fails and you need the real cause, not just to make it green. Execution layer, not strategy review. Keywords: flaky test…