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 GiustoPiedimonte/agentic-engineering-marketplace --skill graphgit clone --depth 1 https://github.com/GiustoPiedimonte/agentic-engineering-marketplaceWrote 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/giustopiedimonte/agentic-engineering-marketplace/graph)<a href="https://agentmods.dev/skills/giustopiedimonte/agentic-engineering-marketplace/graph"><img src="https://agentmods.dev/badge/skills/giustopiedimonte/agentic-engineering-marketplace/graph/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/giustopiedimonte/agentic-engineering-marketplace/graph"><img src="https://agentmods.dev/badge/skills/giustopiedimonte/agentic-engineering-marketplace/graph.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 | $0.00113 | $0.01024 |
| Opus 5 | $0.00056 | $0.00512 |
| Sonnet 5 | $0.00023 | $0.00205 |
| Haiku 4.5 | $0.00011 | $0.00102 |
Grade A, and why
graph 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.
How it starts
The opening of the file, as written. The whole thing — 78 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/graph — draw the work as a graph, then run it
Most multi-step agents are a straight line: step one, step two, step three, each waiting politely for the last, until the context window fills and the agent forgets what it was doing. Half those steps never needed to wait. This skill turns the line into a graph: nodes do the thinking, edges carry the results, and independent work runs at once.
$ARGUMENTS is the objective (e.g. "audit every route under src/ for missing auth").
Read references/GRAPH_MODEL.md for the grammar and references/WORKFLOW_LIBRARY.md
for copy-ready scripts.
Process
-
Draw the graph before running it. Sketch nodes and edges. For every "and then", apply the edge test: does the next step read the last step's output? If not, cut the arrow — those nodes are independent and will run in parallel. Name the topology (diamond / router / verifier / cycle) — see the model reference.
-
Give every node a contract. Bounded input, validated output, one job. When the work should return structured data, hand the
agent()call a JSONschemaso the sub-agent is forced to return validated data — no free text to parse. -
Choose the runtime.
- Dynamic workflow (default for real fan-out) — describe the objective and
let Claude write a plain-JavaScript orchestration script that spawns a
coordinated fleet of subagents. The coordination costs zero model tokens
because it's code, not a conversation, and each subagent carries its own
context so the session never drowns. Say the word "workflow", run a saved one
from
.claude/workflows/, or adapt a template from the library. - Inline subagents — for a one-off diamond of a few nodes, spawn the researcher / reviewer / verifier / measurer agents directly.
- Dynamic workflow (default for real fan-out) — describe the objective and
let Claude write a plain-JavaScript orchestration script that spawns a
coordinated fleet of subagents. The coordination costs zero model tokens
because it's code, not a conversation, and each subagent carries its own
context so the session never drowns. Say the word "workflow", run a saved one
from
-
Put the reduce in code, not in an agent. Flatten, dedupe, filter, rank-by-key are
results.flatMap(...)and aSet— deterministic, instant, zero tokens. Save agents for judgment, not for plumbing.
What ships with it
2 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.
- 9d ago First seen · 78 lines · 113 tokens per session scan A 2b3930cb0e7c
graph is a skill published in the GitHub repository GiustoPiedimonte/agentic-engineering-marketplace (13 stars, last pushed 1mo ago), licensed MIT. It adds 113 tokens to every session and 1,024 once invoked, about $0.0006 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 2026-08-30.
Other skills, from other repositories
grill-me
Internal requirements-interview engine for the CCF commands plan, fix and init. Invoked only by those commands through the Skill tool with a mode argument (plan / fix / init); it interrogates the user one question at a time, exploring the code to self-answer first, and returns a summary of the decisions. Not a…
adr-new
Create a new Architecture Decision Record with append-only, status-gated supersession, and update the ADR index. Invoke with /adr-new, or let /tdd-author invoke it on approval of an ADR action (this skill stays model-invocable for that reason).
cco-tools
Show what tools actually cost in tokens — learned per-tool averages from observed results, replacing the hardcoded MCP/Agent guesses.
github-pr-creation
Creates GitHub Pull Requests with automated validation and task tracking. Use when user wants to create PR, open pull request, submit for review, or check if ready for PR. Analyzes commits, validates task completion, generates Conventional Commits title and description, suggests labels. NOTE - for merging existing…
test-run
Run plugin test suites in this monorepo and report a concise pass/fail summary. Optional plugin slug arg; without arg, runs all plugins under plugins/.
design-system-reference
Style guides and implementation rules for frontend design. Works with design-discovery agent which handles context gathering and VS-based style recommendations. Contains detailed style guides, anti-patterns, and implementation checklists.