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 synaptiai/synapti-marketplace --skill project-modelinggit clone --depth 1 https://github.com/synaptiai/synapti-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/synaptiai/synapti-marketplace/project-modeling)<a href="https://agentmods.dev/skills/synaptiai/synapti-marketplace/project-modeling"><img src="https://agentmods.dev/badge/skills/synaptiai/synapti-marketplace/project-modeling/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/synaptiai/synapti-marketplace/project-modeling"><img src="https://agentmods.dev/badge/skills/synaptiai/synapti-marketplace/project-modeling.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 | $0.00123 | $0.01972 |
| Opus 5.5 | $0.00049 | $0.00789 |
| Sonnet 5.5 | $0.00025 | $0.00394 |
| Haiku 4.5 | $0.00012 | $0.00197 |
Grade A, and why
project-modeling 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 — 125 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Project Modeling
Phase 2. Builds the one model that all 23 documents are views over, and the vocabulary they all use.
Iron Law
ONE MODEL, MANY VIEWS. If a view needs a new fact, the fact goes in the model first.
The moment a document invents a component name, an owner, or a boundary that the model does not carry, the package has two models. It will not notice, and the contradiction surfaces during diligence rather than during drafting.
What the model contains
| Element | Captures | Where it surfaces |
|---|---|---|
| Product intent vs implemented behaviour | What it is for, and what it actually does — separately | 01-project/ |
| Actors, journeys, roles, permissions | Who does what, and what they may do | 01-project/, 02-architecture/ |
| Components and deployment units | Purpose, owner, runtime, interfaces, state, criticality | 02-architecture/components-and-codebase.md |
| Interfaces and contracts | Producers, consumers, transport, versioning | 02-architecture/interfaces-and-integrations.md |
| Data and its lifecycle | Stores, classes, residency, retention, deletion | 02-architecture/data-and-ai.md |
| Infrastructure and environments | Topology, promotion path, differences between environments | 02-architecture/infrastructure-and-deployment.md |
| Boundaries | Control, data, trust, failure, tenancy | Everywhere. The most load-bearing element |
| Owners and decision rights | Who owns, who decides, who escalates | 00-control/terminology-and-ownership.md |
| Lifecycle and target state | What exists now vs what is planned | Every document, kept visibly distinct |
| Assets, dependencies, licenses, risks | Provenance and exposure | 05-due-diligence/ |
Every element is an evidence-backed claim. A component with no evidenced owner is unassigned — never the last committer, never the most active contributor. During an incident, a fabricated owner is worse than an admitted gap.
Classify first
Classify the project from evidence before modelling it, and record the classification with its supporting evidence IDs. The classification changes which elements carry weight — not which files exist. See references/project-type-adaptation.md.
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 · 125 lines · 123 tokens per session scan A bbabfaceb563
project-modeling is a skill published in the GitHub repository synaptiai/synapti-marketplace (7 stars, last pushed 10d ago), licensed Apache-2.0. It adds 123 tokens to every session and 1,972 once invoked, about $0.0005 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
step4-archive-spec
Archive a completed spec — moves it to specs-archived and blocks agent access.
plan-roadmap
Create or update a prioritized product roadmap with phased milestones.
x-tech-design
A technical-design document workflow that turns an approved feature specification into a separate architecture and implementation plan. It records modules, protocols, data flow, constraints, and test references for later task breakdown.
x-verify-spec
A delivery record check for one development task. It compares the feature specification, assigned requirements, checklist, development report, content versions, and verification evidence.
pocket-closing
Close a reviewed Pocket phase or plan when the user explicitly requests closeout, including as part of an end-to-end request. Reconcile verdicts with log.json, advance only a passing phase, append a readable per-phase closeout, and finalize the plan when all phases are done. A passing verdict alone does not authorize…
wayfinder
Chart a too-big effort as a shared map of decision tickets on the Gaia headquarters issue tracker, then resolve them one at a time until the way to the destination is clear. Use when someone says: "this is too big for one session", "chart a map", "wayfinder map", "plan this effort", "what do we need to decide first"…