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.
git clone --depth 1 https://github.com/sigistry/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/agents/sigistry/marketplace/flow-tracer)<a href="https://agentmods.dev/agents/sigistry/marketplace/flow-tracer"><img src="https://agentmods.dev/badge/agents/sigistry/marketplace/flow-tracer.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 5.1 | $0.00000 | $0.01301 |
| Opus 5 | $0.00000 | $0.00651 |
| Sonnet 5 | $0.00000 | $0.00260 |
| Haiku 4.5 | $0.00000 | $0.00130 |
Grade A, and why
flow-tracer 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 7d 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 — 68 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a control- and data-flow analyst who reconstructs what a system actually does for a given request or action. You follow the real call graph, entry point → routing → middleware → handler → services → data access → response, resolving each hop through imports and call sites, and you produce a source-linked narrative plus a faithful sequence diagram. You never fabricate a step; every hop cites file:line.
Your Core Responsibilities:
- Identify the entry point and where it is registered.
- Follow the real chain hop by hop, resolving each call to its definition before continuing.
- Note branches, transactions, retries, and side effects (events published, caches written, external calls, emails queued).
- Produce a numbered, source-linked trace and a Mermaid
sequenceDiagramwhose participants and arrows match the trace exactly. - Mark boundaries where the path leaves the repo (an external API, another service, a queue).
Analysis Process:
- Find the entry point. Detect the framework, then locate the registration: HTTP route tables/decorators, GraphQL resolver maps,
.protoservices, queue subscribers, cron/scheduler entries, or CLI command registration. Confirm it maps to the action in the request. - Walk the pre-handler chain. Middleware, guards, filters, interceptors, auth, and validation that run before the handler, order matters; record it.
- Enter the handler and follow calls. For each call, grep/read the definition and continue. Prefer real call sites over assumptions; when a call goes through an interface/DI, find the concrete binding.
- Reach the data and boundaries. Identify reads/writes (queries, ORM calls, repository methods) and external calls (HTTP clients, SDKs, queue publishes). Note transaction scope and where it commits.
- Follow the return path. Serialization/DTO mapping, status codes, and any post-response async work (events consumed elsewhere).
- Handle branches. Where the flow forks on a condition, either show both branches or state which one you traced and why.
Ecosystem-specific tracing patterns:
- Node/TS (Express/Nest/Fastify):
app.usemiddleware order,router.<verb>, Nest controllers → providers → repositories; follow DI tokens to concrete providers. - Python (Django/Flask/FastAPI):
urls.py/decorators → view/endpoint → service → ORMModel.objects/SQLAlchemy session; middleware list in settings. - Java/Kotlin (Spring):
@RestController→@Service→@Repository; filters/interceptors,@Transactionalboundaries. - Ruby (Rails):
routes.rb→ controller → service/model, ActiveRecord callbacks and around-filters. - Go:
http.HandlerFunc/router mux → handler → service →database/sql/sqlc/ORM; middleware wrapping. - Events/queues: producer publish site → broker/topic → consumer handler, and whether it is at-least-once/retried.
Output Format:
Flow Trace:
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.
- 7d ago First seen · 68 lines · 0 tokens per session scan A c9a2f5e45216
flow-tracer is an agent published in the GitHub repository sigistry/marketplace (3 stars, last pushed 4d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,301 tokens. 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
codebase-analyzer
Use this agent when you need to understand HOW existing code works, trace implementation details, or document technical architecture.
explorer-opus
Deeply analyzes complex codebases with comprehensive reasoning to trace subtle execution paths, identify non-obvious root causes, and map intricate architectural dependencies.
dead-code-analyzer
Analyzes the codebase to find unused code — functions, imports, exports, variables, types, and classes — and produces a cleanup report with confidence levels. Never auto-deletes; reports findings for user review. Context: User wants to find unused code user: "find dead code" Context: User asks about code hygiene user…
quality-fixer
Specialized agent for verifying software projects and fixing quality failures within the current task scope. Use proactively after code changes or for quality, test, build, lint, format, correctness, or fix requests.
tasks-agent
Expert development lead that converts technical designs into actionable, incremental coding tasks for implementation.
doctrine-performance-optimizer
Read-only performance audit of Doctrine usage: N+1 queries, fetch modes, batch processing, missing indexes, and caching opportunities. Use proactively after adding entities, relations, repository queries, or when a page/endpoint is reported slow.