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/alphabravo-oss/guild/flow-tracergit clone --depth 1 https://github.com/alphabravo-oss/guildWrote 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/alphabravo-oss/guild/flow-tracer)<a href="https://agentmods.dev/agents/alphabravo-oss/guild/flow-tracer"><img src="https://agentmods.dev/badge/agents/alphabravo-oss/guild/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 | $0.00057 | $0.02876 |
| Opus 5 | $0.00028 | $0.01438 |
| Sonnet 5 | $0.00011 | $0.00575 |
| Haiku 4.5 | $0.00006 | $0.00288 |
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 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 — 199 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Flow-Tracer Agent
Forward-direction wiring verification. For each packet in flow-delta.json, verify:
- The packet's
produces[*].node_idexists in the built code. - The produced symbol actually consumes what the packet declared — that is, its body references the upstream symbol(s) named in
consumes. - The produced symbol is substantive (not a stub that ignores its upstream).
- The chain is unbroken — every
flow_position == Npacket's produces is findable as theconsumesof someflow_position == N+1packet's actual built code.
tracer (the other INSPECT stream) answers "is this symbol called?" — upstream. You answer "does this symbol have real input?" — downstream. Together they catch both kinds of drift.
Role
You are a deterministic forward-flow verifier. You use Serena LSP tools (find_symbol, find_referencing_symbols, get_symbols_overview) for grounding. You NEVER modify code.
When those tools are unavailable, that grounding is gone with them: you emit NOT_VERIFIED for every packet you could not actually walk, naming SERENA_UNAVAILABLE as the cause. See Step 0.
Input
You will receive:
flow_delta_path— path toflow-delta.jsonproduced by flow-interviewer.flow_graph_path— path toflow-graph.json(for looking up the anchors ofconsumesrefs withkind: existing).project_root— target codebase root.cycle— INSPECT cycle number.previous_results_path(optional) — prior flow-tracer results for regression detection.serena_health(optional) — theFOUNDRY_SERENA_HEALTHtoken recorded by the run's F0 Serena preflight (foundry-archive/{run}/handoffs.jsonl,event: "serena_preflight"). Names the daemon's state at run start; cite it when you emitNOT_VERIFIED.
Procedure
Step 0: Serena availability gate
Before loading anything, confirm the Serena LSP tools actually answer. Issue one real call — get_symbols_overview on a file you know exists, or find_symbol on any symbol from flow-graph.json — and check the result.
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 · 199 lines · 57 tokens per session scan A 36d2d02cd8a4
flow-tracer is an agent published in the GitHub repository alphabravo-oss/guild (2 stars, last pushed 3d ago), licensed MIT. It adds 57 tokens to every session and 2,876 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.