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 Knuckles-Team/epistemic-graph --skill epistemic-graph-deploygit clone --depth 1 https://github.com/Knuckles-Team/epistemic-graphWrote 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/knuckles-team/epistemic-graph/epistemic-graph-deploy)<a href="https://agentmods.dev/skills/knuckles-team/epistemic-graph/epistemic-graph-deploy"><img src="https://agentmods.dev/badge/skills/knuckles-team/epistemic-graph/epistemic-graph-deploy/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/knuckles-team/epistemic-graph/epistemic-graph-deploy"><img src="https://agentmods.dev/badge/skills/knuckles-team/epistemic-graph/epistemic-graph-deploy.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00103 | $0.01964 |
| Opus 5.5 | $0.00041 | $0.00786 |
| Sonnet 5.5 | $0.00021 | $0.00393 |
| Haiku 4.5 | $0.00010 | $0.00196 |
Grade A, and why
epistemic-graph-deploy 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 8d 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 — 162 lines — stays where its author put it; the contents beside it link to each section on GitHub.
epistemic-graph deploy / promote
The live production shape is a Kubernetes graph-os Deployment running the
graph-os-unified image. The image contains the epistemic-graph-server executable and
its Python package; the graph-os process starts that engine as its managed child. The
authoritative redb data lives on the deployment-owned durable volume. There is no supported
host-path binary hot-swap and no second standalone engine to scale up: an engine change is
an image change followed by a digest-pinned Kubernetes rollout.
The serving-plane source may be mounted from the canonical agent-utilities checkout.
That means an AU-only change can ship by restarting the Deployment, but it does not replace
the engine artifact in the image. Keep the engine image and the mounted AU revision as one
tested release pair. Full artifact details and rationale: docs/deploy/binary_promotion.md.
Artifact helper and live delivery
promote_engine.sh is a deployment-neutral binary helper, not the live Kubernetes image
builder. Its --build option runs Cargo for a raw epistemic-graph-server; it does not
produce the Python wheel or the graph-os-unified image. This repository ships no live
Kubernetes promotion hook. Use the script for artifact staging/validation, or only with an
explicitly supplied deployment adapter:
ENGINE_BIN_DEST=<absolute-staging-destination> \
ENGINE_BUILD_FEATURES=full,ast-extended \
scripts/promote_engine.sh --build
ENGINE_BIN_DEST is an absolute, non-symlink destination controlled by the caller.
ENGINE_SOURCE_BINARY may point at an already-built executable; otherwise --build
produces the current ENGINE_BUILD_FEATURES release (default full,ast-extended). The
current options are --build, --activate, --activate-consumers, and --verify.
The latter three require a regular executable supplied through ENGINE_PROMOTION_HOOK;
without that explicit adapter the script does not activate Kubernetes or restart clients.
If an adapter is supplied, it receives these bounded actions:
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.
- 8d ago Changed 995b8dd3954d
- 1mo ago Changed · +89 lines · +28 tokens per session b50c7afb337c
- 1mo ago First seen · 73 lines · 75 tokens per session scan A 3dbd8e78a32f
epistemic-graph-deploy is a skill published in the GitHub repository Knuckles-Team/epistemic-graph (11 stars, last pushed today), licensed MIT. It adds 103 tokens to every session and 1,964 once invoked, about $0.0004 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 2026-08-31.
Other skills, from other repositories
oracle-aidb-docker-setup
Bring up Oracle 26ai Free in Docker, create a project-scoped app user with USERS tablespace + ONNX-friendly grants, and write a .env ready for the rest of the build-paths skills. Idempotent — safe to re-invoke. Use when any project needs a fresh local Oracle 26ai instance.
kubernetes
Kubernetes operations playbook for deploying services: core objects, probes, resource sizing, safe rollouts, and fast kubectl debugging.
access-matrix
Access matrix of role-by-module permissions, with per-role scope, confidentiality level and SME tier, as CSV, SQL, JSON Schema or Notion on request. Use for access reviews.
admin-access-register
Admin account register: system, main and backup admin, seats, plan, 2FA, shared logins and access-review dates, as CSV, SQL, JSON Schema or Notion on request. Use for access reviews.
advanced-analytics-dashboard
Dashboard metric register: metric, source module, formula, period, value, target, trend, owner and last-updated, as CSV, SQL, JSON Schema or Notion on request. Use for KPI dashboards.
alumni-re-hire-tracker
Alumni and re-hire register: former role, last working day, re-hire eligibility, current employer and re-engagement date, as CSV, SQL, JSON Schema or Notion on request. Use for alumni outreach.