Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/crypdick/pynchynpx agentmods add skills/crypdick/pynchy/pynchy-opsWrote 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/crypdick/pynchy/pynchy-ops)<a href="https://agentmods.dev/skills/crypdick/pynchy/pynchy-ops"><img src="https://agentmods.dev/badge/skills/crypdick/pynchy/pynchy-ops/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/crypdick/pynchy/pynchy-ops"><img src="https://agentmods.dev/badge/skills/crypdick/pynchy/pynchy-ops.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 | $0.00110 | $0.04976 |
| Opus 5.5 | $0.00044 | $0.01990 |
| Sonnet 5.5 | $0.00022 | $0.00995 |
| Haiku 4.5 | $0.00011 | $0.00498 |
Grade B, and why
Pynchy Ops scanned grade B with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 1mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Asks for rootmediumPrivilege escalation
A mod that escalates privileges can change anything on the machine, not only the project.
ssh "$PYNCHY_HOST" 'sudo k3s kubectl get namespace pynchy' How it starts
The opening of the file, as written. The whole thing — 429 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Pynchy Ops
The live Pynchy host and checkout path are deployment-specific. Public repo instructions must not assume a private hostname or home-directory layout. Set PYNCHY_HOST and PYNCHY_REMOTE_ROOT from local memory, environment, or the operator before running remote commands.
Deployment Mode Gate
First check whether the authenticated local control-plane socket is available
(see Quick Status Check below). Reading local status does not require an SSH
profile. Identify the deployment before remote operations or changes. A pynchy
Kubernetes namespace means the Kubernetes path applies:
PYNCHY_HOST="${PYNCHY_HOST:?set the live host}"
ssh "$PYNCHY_HOST" 'sudo k3s kubectl get namespace pynchy'
For Kubernetes deployments:
- Read Kubernetes installation and operations.
- Treat
SCHEDULER__AUTO_DEPLOY=falseas authoritative. A Git pull updates the persistent checkout but does not replace the running image. - Use
sudo k3s kubectl -n pynchy; do not usepynchy deploy, LaunchAgent commands, standalone systemd commands, or direct container deletion. - A successful push to
mainpublishes immutable images. The namespace-scopedpynchy-release-monitorCronJob preflights and releases them. - Do not manually patch the Deployment or delete a Pod for a normal release. Observe the monitor Job, rollout, exact release annotation, and application status.
- The monitor applies the selected release’s
deploy/k3s/applicationmanifests, including probes, with its images. Namespace, storage, Secret, RBAC, Pocket TTS, and private MCP image changes remain explicit operator work; follow the application release boundary. - Keep unrelated Docker Compose and Dockge services outside Kubernetes.
The standalone sections below apply only when the live host has no Kubernetes Pynchy Deployment.
Standalone Auto-deploy: Never Restart Manually
Pynchy self-manages. Two mechanisms trigger automatic restarts:
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.
- 1mo ago Changed · +1 lines 62dccd611be2
- 1mo ago Changed · +29 lines c12ad06d34e8
- 1mo ago First seen · 399 lines · 110 tokens per session scan B f85d6e7a2e3c
Pynchy Ops is a skill published in the GitHub repository crypdick/pynchy (10 stars, last pushed 1mo ago), licensed MIT. It adds 110 tokens to every session and 4,976 once invoked, about $0.0004 per session on Opus 5.5. A static security scan graded it B with 1 finding (asks for root). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
add-dial-tool
Give chosen NanoClaw agents a real phone number as a container tool — the dial CLI baked into the agent image plus OneCLI credential injection for api.getdial.ai, scoped per agent, so the agents you pick can send SMS, place AI voice calls, and receive verification codes from inside the sandbox. Independent of the Dial…
add-iron-proxy
Install or refresh Iron Proxy and its official Iron Control web console for NanoClaw. Use when selecting the Iron gateway, adding its management UI, configuring credentials and grants, or restoring the proxy, approval bridge, and agent guidance.
add-signal
Add Signal channel integration via signal-cli device-link. Native adapter — no Chat SDK bridge.
add-telegram
Add Telegram channel integration via Chat SDK.
add-gchat
Add Google Chat channel integration via Chat SDK.
add-matrix
Add Matrix channel integration via Chat SDK. Works with any Matrix homeserver.