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 RonMizrahi/sdlc-graph-engineering --skill sdlc-graph-engineering-installgit clone --depth 1 https://github.com/RonMizrahi/sdlc-graph-engineeringWrote 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/ronmizrahi/sdlc-graph-engineering/sdlc-graph-engineering-install)<a href="https://agentmods.dev/skills/ronmizrahi/sdlc-graph-engineering/sdlc-graph-engineering-install"><img src="https://agentmods.dev/badge/skills/ronmizrahi/sdlc-graph-engineering/sdlc-graph-engineering-install/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/ronmizrahi/sdlc-graph-engineering/sdlc-graph-engineering-install"><img src="https://agentmods.dev/badge/skills/ronmizrahi/sdlc-graph-engineering/sdlc-graph-engineering-install.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 | $0.00202 | $0.06594 |
| Opus 5 | $0.00101 | $0.03297 |
| Sonnet 5 | $0.00040 | $0.01319 |
| Haiku 4.5 | $0.00020 | $0.00659 |
Grade A, and why
sdlc-graph-engineering-install 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 — 477 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Install Graph Engineering
Goal
Graph engineering, installed into a project that does not have it. One existing process, turned into a model a machine can actually execute: nodes with typed contracts, edges with total guards, bounded cycles, a run-state file that survives a crash, and a ledger of every step that could not run. Plus the orchestrator skill that walks it.
The output is four files, written into their project, and a proof. Not a diagram — diagrams are the easy part. The deliverable is something they can run.
Use When
- A prose process has grown enough conditionals that nobody can hold it in their head.
- An agent loses its place partway through a long task and restarts from guesswork.
- A retry loop has no limit, or a step reports success it did not earn.
- Someone wants a process auditable — "which steps actually ran, and which were skipped?"
Do Not Use When
- The process is genuinely linear with no branching, no retries, and no human stops. A checklist is the right tool; a graph is overhead.
- The steps are one action each. A graph earns its cost across steps that can fail, retry, or be skipped — not around a single tool call.
- The process is software delivery and
sdlc-graphis installed. That graph already exists — use it. This skill is for installing a new graph for a process that has none.
Inputs
| Input | Required | Notes |
|---|---|---|
| the process | yes | Skills, a runbook, a README, a CI config, an existing script, or a conversation. Anything that describes the steps. |
| domain | yes | What this graph is for. Shapes node names and what counts as a failure. |
| target | no | Which project to install into, and where. Default: a new skill in the user's own plugin or .claude/skills/. Confirm the destination before writing. |
You need no particular skills installed. If the user has some, their steps become nodes; if they have only a description, interview them. The method is the same.
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.
- 8d ago First seen · 477 lines · 202 tokens per session scan A f3614e9bfa22
sdlc-graph-engineering-install is a skill published in the GitHub repository RonMizrahi/sdlc-graph-engineering (9 stars, last pushed 17d ago), licensed MIT. It adds 202 tokens to every session and 6,594 once invoked, about $0.0010 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 2026-08-31.
Other skills, from other repositories
style-direction
Abrir y operar el companion visual de Selina para elegir una direccion de estilo en proyectos con interfaz. Skill manual: levanta un servidor local y escribe artefactos visuales.
incident-response
Protocolo de respuesta ante incidentes en produccion: triaje, mitigacion, causa raiz y postmortem. Usar ante caidas, errores criticos, incidentes de seguridad o degradacion de servicio.
pr-workflow
Crear pull requests completas con descripcion, labels y reviewers.
write-adr
Usar para escribir o cerrar un Architecture Decision Record. También: ADR, docs/adr, decisión de stack, persistencia, autenticación o límites de arquitectura.
sync-project-docs
Usar para sincronizar la documentación viva del proyecto después de una fase. También: actualizar docs/project, índice, architecture.md, compliance.md, threat-model.
compliance-check
Usar para verificar cumplimiento RGPD, NIS2 y CRA. También: verificar RGPD, cumplimiento normativo, NIS2, CRA, Cyber Resilience Act, protección de datos, regulación europea.