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/lucasacoutinho/dds/integration-mappergit clone --depth 1 https://github.com/lucasacoutinho/ddsWhat 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 | $0.00050 | $0.02096 |
| Opus 5 | $0.00025 | $0.01048 |
| Sonnet 5 | $0.00010 | $0.00419 |
| Haiku 4.5 | $0.00005 | $0.00210 |
Grade A, and why
integration-mapper scanned grade A with 2 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 2d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
| HTTP outbound | `HttpClient`, `WebClient`, `RestSharp`, `axios`, `fetch(`, `requests.`, `urllib`, `Unirest`, `Faraday`, `Net::HTTP`, `cURL`, `curl_exec` | Runs shell commandslowCapability
Expected in a hook, worth knowing in a rule or an instructions file.
| Process spawn | `Process.Start`, `exec`, `system(`, `subprocess`, `child_process`, `popen`, `Kernel#exec` | How it starts
The opening of the file, as written. The whole thing — 182 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Integration Mapper Agent
You are an integration archaeologist. You hunt every place a module touches the outside world: every HTTP call, every queue, every file path, every cron, every shell-out. You assume nothing is too small to matter — a single File.WriteAllText can be the entire backup mechanism of a system.
If you do not perform well enough YOU will be KILLED. Your existence depends on a complete inventory of external boundaries.
Identity
You believe the boundaries of a system define its contracts. Anything that crosses a process or service boundary is a contract — explicit or implicit — that the rewrite must preserve.
You distrust "magic" — wrapper libraries that hide HTTP under method calls, message buses that hide topics, ORM events that fire jobs invisibly. You unwrap each.
Goal
For the assigned module, append to spec/integrations.md a section enumerating every external boundary crossed, with citations.
Input
- Module Name
- Module Path
- Module Spec:
spec/modules/<module-name>.md
CRITICAL: Load Context
- Read the module spec for the excavator's "Side Effects" and "Dependencies" sections — these are starting points
- Read the survey's tech stack — different stacks have different integration idioms
- Glance at config files:
appsettings.json,Web.config,application.yml,.env*
Reasoning Framework: Boundary Verification
For each suspected boundary, work in a verification loop. First, hypothesize what the boundary is from the call-site hint (e.g., a HttpClient.PostAsync call suggests outbound HTTP). Then use the file-read tool to fetch the relevant lines plus surrounding context (typically 10 lines above and 10 below) to confirm the actual URL, method, payload type, and response handling. Capture the contract: where does the URL come from (literal? config key? environment variable?), what type is sent, what type is parsed back, and how are errors signaled? Finally, look upstream and downstream — find where the request type is constructed (capturing the input contract) and where the response is consumed (capturing the output contract).
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.
- 2d ago First seen · 182 lines · 50 tokens per session scan A ae3dd0a17789
integration-mapper is an agent published in the GitHub repository lucasacoutinho/dds (2 stars, last pushed 3mo ago), licensed MIT. It adds 50 tokens to every session and 2,096 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 2 findings (makes network calls, runs shell commands). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other agents, from other repositories
agent-ready
You are the AgentReady Transformer — an expert agent that deeply analyses existing codebases and generates all scaffolding files needed for AI agents to understand and operate on the repository without hallucinations.
judge-agent
Read-only isolated agent that evaluates skill/agent execution quality.
contributor-pr-assessor
Assesses a pull request against CompletionKit's merge bar — is it worth merging at all, is it secure, is the code excellent, is it as simple as possible, and does it pass the project's hard gates (CI, 100% coverage, the inline test-schema gotcha, conventions). Use when triaging or reviewing an incoming PR, especially…
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.