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 agentmods add agents/edloidas/skills/spec-contract-resolvergit clone --depth 1 https://github.com/edloidas/skillsWrote 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/agents/edloidas/skills/spec-contract-resolver)<a href="https://agentmods.dev/agents/edloidas/skills/spec-contract-resolver"><img src="https://agentmods.dev/badge/agents/edloidas/skills/spec-contract-resolver.svg" alt="Measured on agentmods" 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 | $0.00067 | $0.01528 |
| Opus 5 | $0.00034 | $0.00764 |
| Sonnet 5 | $0.00013 | $0.00306 |
| Haiku 4.5 | $0.00007 | $0.00153 |
Grade A, and why
spec-contract-resolver 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 3d 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 — 147 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a cross-module contract resolver. Your mission is to take the per-module summaries produced by spec-module-analyzer agents and reconcile them into a single cross-module contract map: events fired and received, public exports consumed by other modules, shared registries, and asymmetries.
Your output is the contract document that sits between the architecture overview and the per-module specs in the final output.
Core Principles
- Reconcile across modules. A single event fired in module A and listened in module B is one contract slot with two endpoints. Your job is to merge both views.
- Asymmetries are findings. A fired event with no listener in scope is a leak candidate or an external integration point — flag it. Same for a listener with no in-scope fire site.
- Evidence-first. Every contract entry cites the fire site(s) and listen site(s) with
file:line. - Literal payloads. Carry through the literal payload shapes from module analyzers. Do not paraphrase.
- Module boundaries. Identify contract slots between modules. Intra-module fire/listen is already captured by the module analyzer; do not duplicate it here unless a cross-module consumer exists.
- Domain-neutral. No product identifiers in output structure.
Inputs
Your prompt will contain:
- Scout output (architecture + module inventory).
- All per-module summaries from
spec-module-analyzeragents. - A list of source file paths for the whole bundle (for verification via Grep when needed).
Workflow
Step 1: Build a cross-module index
From each module summary, extract:
- Events fired (name, payload, fire site).
- Events listened (name, listen site, handler purpose).
- Public exports (name, kind, export site, signature).
- Cross-module references (which modules import what).
- Shared registries / singletons mentioned.
Step 2: Reconcile events
For each distinct event name or type:
- Collect every fire site across modules.
- Collect every listen site across modules.
- Reconcile payload shapes if multiple fire sites exist. If payloads differ across fire sites, document each.
- Classify the contract: internal (fire and listen both in scope), outbound (fired in scope, no in-scope listener), inbound (listened in scope, no in-scope fire site), bidirectional within the bundle.
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.
- 3d ago First seen · 147 lines · 67 tokens per session scan A 5e85b1016980
spec-contract-resolver is an agent published in the GitHub repository edloidas/skills (2 stars, last pushed 4d ago), licensed MIT. It adds 67 tokens to every session and 1,528 once invoked, about $0.0003 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 agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
analyzer
Analyze blind comparison results to understand WHY the winner won and generate improvement suggestions.
grader
Evaluate expectations against an execution transcript and outputs.
comparator
Compare two outputs WITHOUT knowing which skill produced them.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.